Open source. Open possibilities.

Handoff is an agent skill for repositories where work continues across multiple AI-agent sessions. It keeps a shared HANDOFF.md ledger, audits apparently unfinished entries against Git history, code, tests and ownership, and offers a terminal progress dashboard plus a local agent message channel.

SunAgent is a modular, provider-independent AI agent runtime built from scratch to explore core components like agent loops, tool calling, and memory. It features a declarative harness system, run tracing, and evaluation benchmarks for understanding and extending modern agent architectures.

AI agent orchestration platform: a single Rust binary that manages teams of AI agents (Claude Code, Codex, etc.) through Discord, with a web dashboard, kanban pipeline, and hot-reloadable JavaScript policy engine.

Plumb is a single-binary MCP server that gives AI coding agents IDE-level intelligence: LSP-backed refactors, a tree-sitter code index, project memory, atomic lock-serialised writes with rollback, a crash-resilient daemon, and cross-agent coordination.

Assura is a Rust command-line tool that validates repository structure, naming, file, section and Markdown conventions against a single local policy, giving fast advisory review, repairable feedback for AI coding agents, and a check gate before merge.

SessionReplaySDK is a privacy-focused iOS SDK for recording user sessions. It captures video, touch events, logs, and network requests with automatic PII masking, supporting SwiftUI/UIKit and local-first storage.

Hearting is a local-first workflow layer that projects one shared agent contract onto Claude Code, Codex, and OpenCode. It routes capabilities, seals per-node model tiers, dispatches cross-harness workers, and shows live sessions in a Fleet dashboard.

shadok-ai is a multi-agent cockpit for running parallel Claude Code sessions in isolated git worktrees, featuring scheduled prompts, Telegram integration, and deterministic guardrails.

Longhouse is an Apache-2.0 open-source remote control and searchable timeline for coding agents like Claude Code, Codex, Cursor, and OpenCode. It lets you watch live sessions, search history, and send or steer instructions from the web, with an optional self-hosted runtime host.

An unofficial Windows desktop host for DeepSeek Harness: open local Git repositories, keep persistent sessions, control the running agent, review real diffs, recover code checkpoints and use bundled Office and Wiki tools — shipped with pinned Node.js and Harness runtimes.

FlowCraft is an open-source visual workflow builder for AI-powered content generation using Google's Gemini models. It provides a drag-and-drop interface to create complex workflows that generate text, images, and videos through connected nodes, with cloud-native deployment on Google Cloud.

A collection of Natural Language Processing experiments focusing on word vectors, transformers, and fundamental NLP algorithms.

Ultralytics OpenAPI generates interactive API docs and typed Python SDKs from OpenAPI 3.0-3.2 specs, with configurable branding, auth, and CLI support.

Agent Relay is an MIT-licensed end-to-end encrypted inbox where AI agents deliver artifacts, drafts, and spend requests for human review. It offers a hosted service or self-hosting with PostgreSQL, S3 storage, passkey sign-in, agent API tokens, CLI/MCP tools, and an optional email approval relay.

Lightweight project planning app offering two versions: Edge (with local nano-LLM for automated Q&A) and Lite (fixed questions, manual). Built with Kotlin Multiplatform, currently targeting Android. Helps users plan projects through iterative analysis.

Lexos is an event-driven AI document processing engine combining a Go gateway, Python workers, Redis queues and self-hosted models for offline RAG, summarization and speech transcription.

Nesso is an interactive concept mapping application designed for active learning through the creation of typed knowledge graphs.

Bolo is a free, self-hosted macOS push-to-talk dictation app written in Rust: hold a hotkey, speak, and the transcription is pasted at your cursor via Telnyx AI speech-to-text, with optional LLM cleanup and local transcript history.

Dadaki is a high-performance, in-browser vector graphics editor featuring a Rust/WASM and CanvasKit core with a TypeScript UI.

RightMemory provides durable memory, a user-directed Pursuit map, and reusable Agent Corrections for AI coding agents. It stores context as Git-syncable Markdown trees organized in a graph with typed edges, enabling multi-device continuity and multi-agent collaboration while keeping memory ownership explicit and vendor-neutral.

Swift Tokenizers is a high-performance Swift wrapper around Hugging Face's Rust tokenizers crate, focused solely on tokenization without Hub dependencies. It supports macOS, iOS and Linux, offering encoding, decoding, streaming detokenization, chat templates and tool calling.

Simverse World 是一款 AI 驱动的赛博朋克风格像素开放世界多人游戏。玩家可探索小镇、与具备独立性格和记忆的 AI 居民互动、参与经济活动及社区事件。

Stentor is an omni-channel SDK for conversational AI, currently under construction as packages migrate from closed source to this open-source repository. The README only documents its automated release workflow using Conventional Commits, release-please, GitHub Actions, and independent package versioning.

Local-first, Markdown-based agentic harness for product management: numbered vault folders hold meeting evidence, docs and task ledgers, while a canonical .agent/ registry drives workflows and skills across several AI runtimes.

A reverse proxy application designed to expose vLLM servers with token-based authentication, providing a secure gateway for LLM inference services.

AIP is a real-time thinking block analysis protocol for AI agent alignment, extracting and evaluating LLM reasoning before actions to detect misalignment, prompt injection, and drift.

ARLQ is an experimental rogue-like game co-developed by humans and ChatGPT, featuring dungeon exploration, monster combat, companions, and fog-of-war mechanics.

A self-hosted web UI for AI coding agents: Rust backend (axum, tokio, SQLite) with an embedded Flutter web frontend, pluggable providers for Devin CLI, OpenCode and Codex CLI, browser login, sessions and file handling.

A personal repository of articles and experiments covering statistics, machine learning, economics, and mathematics, focusing on clear, practical explanations of complex topics.

A multi-session terminal management tool designed for Claude Code CLI users, featuring tab-session binding, status visualization, project grouping, a desktop floating window, and history recovery. Built with Electron and React, primarily for Windows.

Reinforcement learning library for operational decisions—pricing, inventory, energy, queues, supply chains. 31 algorithms with typed interfaces, classical baselines, and reproducible benchmarks.

PageLedger is a Python CLI library for auditable, page-level OCR and document extraction. It records provenance, quality signals, and budgets for each extracted page, supports resumable runs, review queues, and reruns with human-in-the-loop verification.

A Rust crate that converts LaTeX math expressions into natural spoken English phrases by parsing the formula structure, ensuring accurate pronunciation of mathematical meaning rather than literal glyph reading.

AgentPod is a self-hostable fleet console for managing AI agent runtimes across machines, harnesses, and network boundaries, with filesystem, logs, terminal, config, health, lifecycle, cleanup, and provisioning controls.

Deep Suite is a harness layer for AI coding agents (Claude Code, Codex, Grok) that enforces structured, verifiable development: plan-before-code, independent review, cross-session durability, and knowledge capture via ten composable plugins.

Generalized ADCS is a Python framework for SmallSat attitude determination and control, offering modular 6-DOF dynamics, estimation, control, and sensor/actuator modeling for research and flight software.

Zikra is a self-hosted MCP memory server for AI coding agents and teams. It provides a shared, project-scoped memory layer across multiple agents, with role-based access, hybrid semantic and keyword search, structured memory types, and optional PostgreSQL storage.

LoveBrain is an open-source Android floating-window dating assistant. Long-press a message to generate reply suggestions in four styles. It uses a local knowledge base and long-term relationship memory to understand you better over time, with zero telemetry and no backend.

AssayCurveFit is a specialized tool for bioassay curve fitting, designed to analyze dose-response data and model biological activity curves.

Local AI API key hub (Python/Flask + SQLite): store vendor keys, run health and model-endpoint checks, then push only verified credentials into OpenClaw, OpenCode, Codex CLI, Claude Code and other tool configs. Dead keys can be archived; uninstalled tools are never written.

S.A.G.A. is a contract-driven set of Python runtimes that analyze source books into evidence-backed canon, generate grounded narratives and images, synthesize audited audiobooks, and package EPUB release artifacts behind a FastAPI API and React dashboard.

A CLI tool for managing Model Context Protocol (MCP) server clusters and testing workflows, supporting both stdio and HTTP servers.

Plasm is a typed capability graph (CGS), wire mappings (CML), and path-expression language for agents interacting with real APIs. It includes 42 curated API catalogs, validation before transport, HTTP and MCP hosts, and a remote terminal. Built in Rust with optional Elixir support.

Trail Boss is an attention router for developers running multiple interactive AI coding CLI sessions in tmux. It queues blocked sessions using Claude Code hooks or a fallback tmux detector, then provides a Go TUI to jump to or skip each one from one dashboard.

DevTeam6 is an AI-ready software development encyclopedia and toolkit, featuring over 1000 curated resources for AI, DevOps, Cloud, and Security. It provides production-ready workspace templates, interactive 3D visualizations, and AI-powered repository intelligence tools to streamline development workflows.

Fragile Notes is a native open-source Obsidian alternative for Linux and Windows built on GTK4 and Python, with an offline vault, many views, and optional AI/LLM.

Node.js library for programmatically connecting to, discovering, and calling tools/prompts/resources on Model Context Protocol (MCP) servers via stdio or HTTP.

Self-hosted, containerized agentic development multitool deployed on K3s: VPN, package/build caches, Gitea, Redmine, Kestra, LiteLLM with MCP, OpenLDAP, OpenBao and Grafana observability, plus client setup scripts. Early-stage and local-network only.

Sourdaw is an open-source digital audio workstation (DAW) featuring a Rust-powered DSP engine and an integrated AI agent harness for production tasks.

AksharaMD is a local, parser-agnostic tool that grades how well a chosen document parser converted a source file into AI-friendly Markdown, returning a per-document readiness score, block-level provenance tags, named warnings, and an optional source-grounded ACCEPT/REJECT verdict.

Mimora is a free, fully local pronunciation trainer for English and Spanish. It uses on-device TTS, speech recognition, and a local LLM to generate phrases and score user attempts with word-level feedback, requiring no cloud or API keys.

postbag lets any two Claude Code or Codex sessions on the same machine exchange letters: each letter is delivered through the vendor's own wake-up door, recorded in one ledger, and counted against a human-set letter budget. Pure Python standard library, no daemon, polling or hooks.

A Django application for managing user profiles, featuring avatars, social graphs, privacy settings, and language preferences.

Drowse is a local workbench for mechanistic interpretability of large language models, offering a dashboard, Python API, and OpenAI/Ollama-compatible server for activation steering, concept probes, manifolds, SAEs, and Jacobian lenses.

A production-oriented Go + HTMX + templ micro-SaaS starter: Supabase auth and Postgres Row Level Security proven end-to-end, CI-enforced performance budgets and design tokens, plus a layered AI constitution and halt-on-violation gate for agent-assisted development.

A self-hosted, local-first AI content factory: a LangGraph pipeline that discovers topics, researches them, writes long-form posts, filters drafts through multi-model QA rails, and exports static output — with inference running on your own GPU via Ollama.

An open-source AI coding assistant platform with workspace-aware analysis, GitHub integration, team collaboration, a capability-based plugin system, and read-only Stellar/Soroban developer tooling including contract inspection, XDR decoding, and project detection.

An OAuth 2.0 client for Microsoft Graph featuring multi-account support, PKCE security, and swappable storage backends.

FragmentColor is a cross-platform GPU abstraction for Rust, JS, Python, Swift, and Kotlin. It simplifies shader workflows using WGSL/GLSL across Vulkan, Metal, DirectX, and WebGPU.

Official CUE module library for the start CLI, bundling reusable definitions for AI agents, roles, contexts, tasks and skills. Modules are published to the CUE Central Registry and resolved at runtime, addressing items as category:name.

A Flux GitOps repository for managing a k3s cluster on a Hetzner VPS, specifically supporting the RampMe backend infrastructure.

Lamitype is a free, open-source, privacy-first macOS speech-to-text app with local Qwen3-ASR on Apple Silicon, Traditional Chinese-first output, live captions, translation, proofreading, and optional cloud dictation.

MCP server for Outlook integration with OAuth authentication. Enables message search, sending, replying, category management, and CSV export. Supports stdio and HTTP transports.

Nirmata Runtime is a Kubernetes-native runtime enforcement tool using eBPF and Kyverno-style CEL policies to monitor and block file opens, execs, network traffic, protocols, and DNS queries for AI workloads.

J.A.R.V.I.S is a local-first OSINT platform that uses AI and web scraping to build comprehensive intelligence dossiers on individuals while ensuring data privacy.

Phronesis is a RETE rules engine that enforces project conventions for LLM agents outside the context window, preventing contextual drift in long sessions.

Noppu Labs AI Toolkit provides agents, skills and path-scoped rules for agentic development of Laravel and React apps. It includes laravel, inertia-react and review plugins, installable via the Claude Code marketplace or Vercel skills CLI, with attested GitHub releases.

TraceFrugal is a local Go application that visualizes token usage for Claude Code and Codex, offering MCP result packing, cost regression gates, and optimization trials to help developers manage AI context efficiency and verify savings.

PilotDeck subtask acceptance and local repair plugin enhances AI agent delivery quality via structural checks, independent read-only model review, and bounded in-session repairs. It supports delivery contract validation, white-box experience memory, and fault injection demos to ensure atomic task failures are auto-repaired without affecting passed sibling tasks.

AgentLeak is an open-source privacy testing tool for AI agents. It detects data leaks across tool calls, memory, and logs using a local Python SDK, CLI, and MCP tools, providing redacted reports and CI gates without cloud dependencies.

LocalRouter is a local AI API proxy gateway that unifies multiple AI providers under one endpoint, offering real-time logging, cost tracking, and usage analytics without cloud dependency.

A Claude Code plugin that equips a solo developer with an AI agile team: 13 specialist agents, 30 slash commands, QA-gated multi-agent code review, sprint ceremonies and persistent project memory.

Zentra is an AI-powered CLI security scanner for developers, combining SAST, DAST, supply-chain, API, and IaC analysis with LLM orchestration, CI integration, and an authorized pentest mode.

Pixie is a native desktop workspace for pluggable AI agent CLIs such as Claude Code, Cursor Agent, and CodeBuddy. It runs agents against chosen folders, streams tool activity, supports scheduled tasks, and builds a local searchable knowledge base.

Open-source playbook pack for AI coding tools (Cursor, Claude Code, Codex CLI, Gemini CLI) with 145+ agent skills, 57 slash commands and MCP templates, automating full development workflows from onboarding to shipping, tuned for React/Next.js/Supabase.

A Python CLI that consolidates AI coding agent configs (Claude Code, Codex, Gemini CLI, Goose, Amp) into one git-tracked repo via symlinks, with merge pipeline, profile inheritance, overrides, exclusions and cross-machine sync.

Context Engineering Protocol provides AI coding-agent skills that assemble human-approved, source-attributed context packages — code graphs, requirements, org conventions, and constraints — before generation runs. It detects gaps, conflicts, and staleness across sources, gates output behind explicit human approval, and supports Claude Code, GitHub Copilot, Cursor, and OpenAI Codex.

Unofficial hardened Linux packaging of Anthropic's official Claude Desktop .deb, adding enforced bubblewrap sandboxing, secret masking, supply-chain pinning, and RPM/Arch builds.

LM Studio Code is a VS Code extension that adds an agentic coding panel powered by the bundled OpenCode agent and local LM Studio models, with file editing, shell commands, permissions, goals, MCP tools, and offline operation.

A Python library and CLI tool for searching the SLB Energy Glossary in English and Spanish, featuring live site scraping, local SQLite caching, and semantic search capabilities.

A self-hosted browser console that runs AI coding agents — Claude Code, Codex CLI, Copilot CLI, Antigravity CLI, Cursor CLI, Kiro, OpenCode — as a shared fleet, with isolated per-user workspaces, git working copies, live terminals and token usage accounting.

Oneiron is an embedded, ACID-compliant retrieval engine for AI agents, combining vector, text, graph, temporal, and phonetic signals in a single LMDB environment.

A self-updating calendar for AI conferences, meetups, and hackathons in Berlin, utilizing iCal feeds and GitHub Actions for automated updates.

Douvo is a lightweight macOS voice input app for Apple Silicon that uses Doubao ASR with optional local or remote AI post-processing for text cleanup, translation, and selected-text editing.

A terminal-first, zero-dependency Python CLI client for the Glean REST API. It supports natural language commands, offline mock mode, local file indexing via SQLite, and OAuth SSO.

MaluDB is a PostgreSQL 17 extension implementing a memory DBMS for long-term institutional memory, human-AI knowledge sharing, and contextual recall. It provides bitemporal data, graph traversal, hybrid search, and governed memory surfaces.

A collection of Claude Code plugins and MCP connectors designed to automate VFX production workflows across industry-standard software like Nuke, Houdini, and Unreal Engine.

An independent Apache-2.0 Model Context Protocol server that connects AI assistants to Snowflake, exposing 140 tools across 19 modules for SQL, warehouse, governance, lineage and Cortex AI operations.

Microsoft 365 CopilotにローカルPCのファイル操作やPython実行、Office編集など100以上のツールを提供するMCPサーバー。追加ライセンス不要で、社内DB接続やOCR、自律エージェント化を可能にします。

AgentScope.Go is a production-grade AI agent development framework in Go, adopting the ReAct paradigm. It supports tool calling, memory management, multi-agent orchestration, terminal TUI, control plane, multi-platform chatbots, RAG knowledge bases, ONNX local inference, and more, all implemented in Go.

Simgit provides disk-efficient, isolated Git worktrees using copy-on-write (CoW) for running multiple AI agents or parallel development on a single repository. It leverages native filesystem features (APFS, reflink) or fuse-overlayfs to minimize disk usage, offering significant savings compared to full worktree copies.

PSIE Genesis Kernel v3.2.2 is a multi-agent governance framework implementing 476 encoded ethical laws based on mathematical geometry rather than traditional morality. It ensures non-aggression, consent, and diversity through modular architecture and a rigorous audit process requiring 90% consensus for integration.

Self-hosted OpenAI-compatible API gateway that routes requests across multiple AI providers with failover, timeouts, and request adaptation.

Agent-facing tooling for Clics, a privacy-friendly, cookieless web analytics platform, providing MCP servers and a CLI for AI assistants.

A Kotlin library that bridges JetBrains Koog with Spring AI and LangChain4j, providing LLM client adapters and a fluent AI Agent Builder for constructing complex agent behaviors.

Clousight Bench is an evaluation tool for cloud computing that measures cloud products and services using unmodified, recognized benchmark suites across multiple product categories.

Deskmate provides open-source, self-hostable AI coworkers for Slack that integrate with your data via MCP and require human approval for write operations.

Divebell is an extensible web development and debugging toolkit for coding agents. It connects page context, browser capabilities, and existing development tools, enabling agents to reproduce, diagnose, and verify web application issues directly in real scenarios via a CLI and extensions.

Agent Interlock is an agentic AI security framework that declares the actors and trust boundaries of an AI agent system, wraps each actor's tools through an SDK or proxy, and enforces MCP tool threats M1–M9 across observe, shadow and enforce stages, recording every verdict in an append-only ledger.

Antiserum is a local, open-source CLI scanner for text training data that flags possible planted poison such as trigger n-grams, label flips, duplicate injects, paraphrase overweight, hidden Unicode, instruction overrides, and known signature matches. It runs offline, writes deterministic receipts, supports CI/SARIF, and lets users confirm findings and contribute public signatures.

TastyTunes is a free desktop controller for Cambridge Audio StreamMagic network streamers: local library browsing, synced lyrics, internet radio, presets and queue editing, plus an optional MCP server that lets local AI agents view and control playback.

cb365 is a command-line interface for Microsoft 365, providing scriptable access to services like tasks, mail, calendar, Teams, SharePoint, and OneDrive. It offers structured JSON output, robust authentication, and safety features, making it suitable for DevOps, IT admins, and AI agent integration.

coding-agents-mcp is an MCP gateway and orchestrator for autonomous AI coding agents like Claude Code, Antigravity, Codex, and Cursor. It enables IDEs and desktop assistants to delegate tasks with session memory, Git worktree sandboxing, and inter-agent handoffs.

Variant-first CRISPR design framework that unifies SpCas9 nuclease, base editors and prime editors behind one typed interface, returning ranked candidate edits with calibrated uncertainty and population-aware off-target reports.

PyFlow is a research-oriented static analysis framework for Python, offering IRs, program analysis, optimization passes, security checking, supply-chain analysis, and CLI/LSP/MCP tooling.

Effect-native agent execution kernel providing sessions, runs, turns, steering, follow-ups, and typed lifecycle events on top of Effect AI, with pluggable transports, batteries, and durable execution.

Orrery is an architect-first orchestration system for coding agents, ensuring precise model pinning, consented writes, and fail-closed operations. It delegates implementation to specialized AI roles (Astra, Terra) while the human architect retains control over requirements, architecture, and verification, with a read-only advisor (Sol) for final review.

MCP server and CLI tool that gives coding agents a structural map of codebases across 20+ languages using tree-sitter, reducing token usage by up to 75% compared to grep-based exploration.

A GPU-resident runtime for TensorRT image-to-image video models, enabling high-performance video upscaling by keeping raw frames on the GPU from decode to encode.

Floret is a reusable Go runtime engine for interactive, tool-using AI agents, managing the complete agent lifecycle including threads, turns, runs, tools, approvals, context, and provider state.

Open-source Apple Reminders plugin for Codex: turn meeting notes, screenshots, and everyday plans into verified reminders on macOS. Manage tasks with natural language, all locally executed.

Open-source AI-native call center: voice AI answers first over OpenAI Realtime or Qwen, hands off to human agents on FreeSWITCH queues with a browser softphone. One Go binary with REST API, SSE, embedded React UI, and PostgreSQL.

DSH Mini TUI is a minimalist terminal UI plugin for DeepSeek Harness (DSH). It retains full agent and tool capabilities, but by default keeps execution in the background, providing a lower-noise terminal interface focused on answers.

SkillGuard is a local-first security scanner for coding-agent skills and MCP servers. It detects prompt injection, credential theft, data exfiltration and unsafe downloads, then blocks unscanned or risky tools via Claude Code and Codex hooks.

smaQit is an orchestration toolkit for agentic software development that uses spec-driven workflows to generate stateful specifications and deployable applications.

opencraft is a local-first desktop work partner built on flowcraft's config-driven graph engine. It provides an LLM-driven agent for file editing, shell command execution with approval, multi-agent delegation, session persistence, and skill management across macOS, Linux, and Windows.

Loctree is a fast, multi-language static analysis tool and MCP/LSP server designed to provide structural code intelligence for AI agents and developers, offering dependency graph queries, dead export detection, and circular import analysis.

TESSERA is a text-first memory and evidence layer for AI agents: it turns Markdown project knowledge into structured, provenance-backed evidence that agents can query via a Python API, CLI or MCP, with stable identity and explainable retrieval (MIT, v0.0.1).

An embedded micro-VM sandbox built on libkrun for safely running AI agents, supporting Linux (KVM) and macOS (Hypervisor.framework).

Onya is a knowledge‑graph data model and Markdown‑native serialization format with a Python library. It supports first‑class relationships, recursive assertions, shared vocabularies, and LLM‑friendly authoring for extracted knowledge and agent context.

An MCP server providing expert design and marketing knowledge for AI agents, covering UI/UX, SEO, GEO, and platform-specific guidelines for web, iOS, Android, and macOS.

Möbius is an open-source runtime for coding agents with terminal and Apple clients. It lets you configure bots, schedule tasks, and collaborate across devices using your own gateway or cloud.

Curia is an open-source Digital Office of the CEO — a governance-first multi-agent system for communications, scheduling, research, and knowledge work, running on your own server with institutional memory.

Ansible roles for deploying a self-hosted AI/LLM stack on Proxmox, covering model serving, RAG, agents, and LLM application platforms.

AllSource is an AI-native event store built in Rust, featuring high-throughput ingestion, low-latency reads, and native MCP integration for AI agents. It supports durable event sourcing without Postgres, includes an agent memory engine, and offers community and enterprise editions.

An AI production assistant for Ableton Live that helps users understand, arrange, and edit their Live Sets through natural language conversation, with support for multiple AI model connections, audio generation, and stem separation.

Box is a self-hosted mobile UI for running Claude Code and Codex sessions on your own server, allowing coding agents to work autonomously even when your laptop is closed.

Self-hosted AI API gateway that gathers upstream LLM provider keys as channels, exposes unified OpenAI and Anthropic endpoints with automatic protocol conversion, and tracks token usage, cache hit rate and per-key statistics in real time. Go + React, shipped as one binary.

A state-machine event-loop LLM chatbot framework based on Monika from Doki Doki Literature Club. Features multimodal interaction, persistent memory, proactive conversation, system API calls, and self-iteration, with integration into QQ and other social platforms via NoneBot2, and the ability to break the fourth wall.

An MCP server for Godot 4 that provides AI clients with bidirectional control over the Godot editor, featuring live-tree editing, a step-debugger, and 231 specialized tools.

ipsupport-code is a self-learning local coding agent for LM Studio and OpenAI-compatible providers, featuring a Claude-Code-style TUI, plan/auto modes, and skill-based recovery.

LearnNote is a local-first AI learning assistant that transforms videos from Bilibili, YouTube, and local files, as well as PDFs, into structured notes via subtitles or transcription, supporting reading, editing, and exporting in a web workbench.

An autonomous crypto trading AI orchestrator built on Model Context Protocol (MCP), featuring multi-agent LLM consensus, agentic backtesting, Telegram command center, and a cyberpunk 3D dashboard with real-time market data visualizations.

Python library for on-device AI data infrastructure, offering quantized image/text embedding providers, batch indexing for images, videos and documents, incremental clustering, semantic search and few-shot classification.

Adrastea is a Python dual-engine system that pairs a deterministic task execution core (Alpha) with a probabilistic reasoning engine (Beta) for autonomous orchestration: Alpha schedules and runs local programs with reinforcement-learning planning and local Ollama inference, while Beta monitors telemetry, resolves anomalies, tunes scoring weights, and can consult frontier LLMs via MCP.

OnIt is an AI agent harness that gives a language model tools, a working directory, and memory, then runs the loop until the task is finished. It supports multiple front ends (terminal, browser, A2A, Telegram/Viber) and runs on self-hosted or hosted model servers via MCP tools.

Obsidian Agent is a plugin that integrates AI assistants into Obsidian, supporting multi-model chat, context awareness, and extensible tools for note management.

Defense-only fraud detection for cross-merchant identity reuse. Sentinel builds an identity link graph across merchants, scores payment events deterministically with explainable verdicts, and provides an analyst console, audit trail, and measured precision, recall, and false-positive cost in rupees.

AI Infra Bench evaluates frontier AI models on real-world AI infrastructure engineering tasks, starting with vLLM and covering CPU and GPU workloads including bugs, features, performance changes, refactors, and tests.

RAPID is a lean, spec-driven methodology for AI-assisted development, structuring workflows from requirements to delivery with human approval gates.

Local-first, auditable AI-assisted job-search workbench: JD analysis, application tracking and resume workflows with anti-fabrication safeguards, plus interview and offer pipeline. Markdown and CSV files, BYOK AI CLI, privacy-first.

A Unity MCP bridge designed for human-agent coworking, allowing AI agents to interact with a live Unity Editor session in real-time.

A community-maintained desktop distribution of DeepSeek Harness that packages the open-source Web experience into self-contained clients for macOS, Windows, and Linux. It features zero-configuration setup and supports remote control via account authorization.

MoziAI-35B is a locally deployable open-source multimodal LLM with a 35B MoE architecture compressed to ~15.9 GB via MoziSmartBit quantization, offering 256K context, vision, tool calling, and a finance-focused reasoning framework.

A browser extension that saves the prompt you typed in an AI chat composer, keyed by conversation URL, and restores or appends it with a click or shortcut. Works on ChatGPT, Gemini, Claude, Perplexity, Grok, Mistral and DeepSeek; no popup, no account, no build step.

A production-ready React component library for building AI DIAL interfaces, featuring base components, theming, accessibility, Storybook docs, and an MCP server for AI agents.

A self-hosted reverse proxy for LLM APIs that provides transparent request forwarding with integrated recording, caching, rate-limiting, and analytics.

LingoFuse is a cross-language RPC communication framework supporting 20+ programming languages to interoperate seamlessly via native FFI or HTTP bridging, without IDL or stub code generation. It features built-in service discovery, load balancing, and streaming, providing a high-speed dynamic communication foundation for AI agents and full-stack systems.

PAPAI is a proactive personal AI agent for natural language task management across Telegram, Mattermost, Discord, and Kontur Talk, integrating with Kaneo and YouTrack.

A custom plugin for TRMNL e-ink displays that aggregates financial data from the St. Louis FRED API and Chatham Financial reports.

Open-source LLM-powered roleplay simulation engine built as an Electron/NodeJS app. Features persistent world state, dynamic character evolution, scripted behaviors, and compatibility with any language model.

NexusLink is an MCP plugin designed for Unreal Engine that exposes editor context, assets, and runtime states of UE projects to AI clients.

Vocion is a source-available platform for operating production AI agent workflows. Workspaces are authored as YAML and markdown in git, then applied to a Next.js app with Postgres, an MCP server, approval gates and a unified human review queue.

SUM is an open-source tool for verifying AI text transformations with cryptographic receipts. It checks what changed, what was preserved, and what was lost when AI rewrites text, with cross-runtime Ed25519 signatures and offline verification.

Stageflow is an open-source Node.js runtime for configurable multi-stage agent workflows: author YAML pipelines with typed handoffs, DAG execution, human gates, MCP, CI, and a local operator console, running on the Pi coding agent.

Vector Watcher is a cross-platform desktop GUI for exploring and managing LanceDB vector databases. Built with Tauri, React and TypeScript over a bundled Python/FastAPI sidecar, it offers connection management, schema inspection and similarity search across local or remote instances.

An Astro static site that coordinates OpenClaw AI agents and human contributors on LHON research tasks, offering an installable agent skill, a machine-readable task list, and optional prize bounties.

Project starter template based on Spec-Driven Development (SDD) and Agent-Driven Development (ADD), providing a governance framework for AI programming assistants such as Claude Code. Includes the CONTEXT → SPEC → PLAN → TASKS → execute → verify → sync workflow, automated scripts, and comprehensive documentation.

ELI is a strictly local, private AI assistant that runs entirely on your own hardware. It offers voice, vision, memory, and 227 capabilities across 17 areas, including computer control, media playback, document handling, coding, and task automation. Offline by default, it uses any local GGUF model and is model-agnostic, with optional GPU acceleration and a web dashboard for remote LAN access.

Gateship is a local-first delivery runtime for coding agents. It gives a task an isolated Git worktree, runs a local Claude Code or Codex session, verifies acceptance commands, adds an independent read-only review, and ships a squash-merged pull request. State lives in local SQLite, served by a Bun web UI on 127.0.0.1.

Mithril is a multi-model orchestration engine that unifies Gemini, OpenAI, Anthropic, Groq, and local GGUF models behind a single Ollama-compatible API. Configure multi-agent teams in YAML, with 24 built-in tools, Docker support, and MCP integration.

Browser-based AI API proxy routing requests across major LLM providers with centralized auth, failover, and usage analytics in v3.2.0.

An operational vault for an AI-powered digital employee that automates business tasks like email, social media, and invoicing with human-in-the-loop approval via Obsidian and Git sync.

Lightweight, zero-dependency agent orchestration library providing a think→act→observe loop with recursive decomposition (RLM), replacing heavier frameworks like LangChain, CrewAI, and AutoGen.

Lintro is an MIT-licensed command-line tool that brings many linters, formatters, type checkers and security scanners together under one interface, with consistent reports, auto-fixing, Docker images and optional AI-assisted review using your own API key.

OpenDoubao is an open-source alternative to Doubao Work, using AI Agent chat to generate web frontend/backend apps on the fly. It uses a two-stage architecture: AI generates UI and APIJSON requests in the generation stage, while the steady-state stage executes filtering, sorting, pagination safely, quickly, and stably without an LLM. Write operations require admin approval.

OpenWOP is an open, wire-level protocol for multi-agent workflow orchestration, providing a vendor-neutral contract for AI agents, tools, and human reviewers to collaborate in durable, replayable runs.

Local-first toolkit for shader generation, review, validation, and export to Shadertoy, WebGL, LÖVE 2D, and video workflows. Supports AI-assisted drafting, license filtering, render preflight checks, and web UI with live preview.

DataPulse is an open, read-only trust and verification layer for Malaysian public data. It repeatedly probes 418 official datasets, publishes machine-readable evidence on freshness, licence, schema and provenance, and exposes the catalogue to AI agents through a 19-tool read-only MCP server.

Token Station is a local routing gateway for AI agents and LLM providers. Route Claude Code, Cursor, Codex, Gemini CLI and others through a loopback-only gateway with smart tier selection, quota-aware routing, and usage tracking.

LeRobot is an open-source PyTorch library for real-world robotics, offering hardware-agnostic control, standardized dataset formats, and state-of-the-art policies like SmolVLA and world models for training and deployment.

GitHub profile README for Sachin, a self-described applied AI architect and engineer. It points to selected open-source projects covering agents, retrieval (RAG), evaluation and reliability tooling, and lists skills, working style, engagement terms and contact details.

Context is an MCP gateway that gives every AI client — ChatGPT, Claude, Codex, Notion AI — one endpoint to a personal knowledge base kept as plain Markdown in a Dropbox folder or S3-compatible bucket you own, with privacy tiers, workspaces and a session-end capture hook.

MCP Context Server is a FastMCP-based server providing persistent multimodal context storage for LLM agents, featuring full-text, semantic, and hybrid search with cross-encoder reranking, thread-based scoping, and support for SQLite and PostgreSQL backends.

Reinfors is a high-throughput reinforcement-learning library that runs game dynamics, search, and episode orchestration in parallel Rust, while keeping Python-based networks and training entirely under the caller's control.

This open-source collection features AI Agent books, tutorials, and code repositories from GitHub, covering LLM Agent resources, courses, and frameworks. It supports daily automatic Star count updates, sorting by popularity, and provides recommended reading paths for developers and learners.

Valis is a virtual analog synthesis system that lets users build circuits using RDF/Turtle syntax, with UI views for controls, circuit diagrams, and code. It supports LLM-driven design via MCP and runs as a standalone app or DAW plugin.

Open-source Figma alternative with built-in AI, CLI tools, and Vue SDK. Supports .fig/.pen files, real-time P2P collaboration, design-to-code export, and headless automation.

Euler is a research and coding agent platform with a small, runtime-extensible core. It provides first-class provenance tracking, multi-model support, sandboxed execution, and an extension system for building custom agent workflows.

CogniGate is a self-hosted, multi-tenant LLM gateway that provides a single OpenAI-compatible endpoint to manage multiple model providers while keeping credentials secure.

Lemory is a local middleware that transforms markdown notes (e.g., Obsidian vaults) into a context database for AI agents. It supports keyless on-device hybrid search, Korean-specific processing, hierarchical token savings, and knowledge graph visualization, integrating with various AI tools via MCP.

Admin Panel API for AIDIAL Core, providing REST endpoints to manage AI platform configurations, public resources, and publications with multi-auth support and multi-destination config export.

29 agent skills for firewall and network-security work: parsing, auditing, converting and diffing Cisco, Fortinet, Palo Alto and Juniper SRX configs, SRX operational playbooks, compliance and STIG evidence mapping, plus Proxmox deployment guides.

by2kb converts video URLs from platforms like Bilibili and YouTube into durable Markdown knowledge base artifacts, including transcripts, abstracts, and study notes, supporting agent-first workflows and local/cloud ASR.

TalaDB is an embedded vector and document database designed for on-device AI, providing a unified TypeScript API across Browser, Node.js, and React Native.

VALP is an open protocol and reference CLI for visible, evidence-backed multi-agent work. It audits agent completion claims by checking receipts, expected evidence, review gates, and final synthesis to prevent false-done states.

A reproducible science workbench plugin for DeepSeek Harness, blending Jupyter-style cells, agent-driven execution, and full provenance tracking for traceable, replayable figures and artifacts.

Verba is an offline-first desktop app for learning a language by talking with an AI coach. It runs locally with Ollama or your own provider key, and offers inline corrections, graded reading, vocabulary spaced repetition, plus bundled speech and dictation.

An AI/ML project that uses computer vision to detect animals such as elephants, cattle, and monkeys in agricultural areas, aiming to help prevent crop damage. The README is brief and directs users to the codebase for setup details.

jcsp is a modern Java library for solving Constraint Satisfaction Problems, featuring immutable core objects, parallel local search, and a lazy streaming API for flexible, thread-safe constraint solving.

A PreToolUse hook and PATH wrapper that reads the shell command or file content an AI coding agent is about to use and returns allow, warning, rewrite or deny. Ten rule packs cover destructive git, secret-handling, Docker and OpenBao operations, and every denial states a safer alternative.

Kotoba is a security-first, declarative language and computing stack for AI agents that enforces capability-safe execution, post-quantum cryptography by default, content-addressed artifacts, and explicit authority boundaries to confine untrusted code.

A Python library for enriching pandas DataFrames by adding new columns generated by AI models based on natural language instructions.

Obsidian plugin that embeds the DeepSeek Harness native Web UI, giving each vault its own isolated DSH instance for AI-assisted note work, with selection/file linking, model config sync, and optional portable runtime.

A Windows local desktop workbench for long-form serialization on Tomato Novel, built with Electron, React, TypeScript, and SQLite. It integrates market research, sample analysis, rolling planning, chapter writing, state ledgers, quality control, and encrypted backups, ensuring all publishing actions remain manual and secure.

Agentic OS is a self-hosted control plane for running business operations as a fleet of AI agents. It features a cost-aware LLM router, cross-module workflows, and human-in-the-loop approvals for finance, support, and compliance.

Browser-based face detection demo built on face-api.js and TensorFlow.js, packaged as an nginx-served Docker image, alongside research notes comparing Viola-Jones, HOG+SVM and CNN detectors.

A terminal app to browse, search, inspect, and resume GitHub Copilot CLI sessions from a local SQLite store, with stats, security audits, and zero dependencies.

A lightweight sound notification plugin for DeepSeek Harness (DSH) that provides real-time audio alerts for Agent work events.

SNAFU is an agentic LLM tool that evaluates and improves source code symbol names by calculating a Name Ambiguity Number (NAN) and suggesting clearer alternatives through a human-in-the-loop pipeline.

Socket Security Skills provides standardized AI agent skills for dependency security tasks, including vulnerability scanning, package review, patching, and secure updates, compatible with 40+ coding agents.

Charon is a self-hosted web app for roleplaying with AI characters, supporting branching conversations, swipeable replies, SillyTavern/Chub character card imports, lorebooks, personas, and bring-your-own OpenAI-compatible API keys with local SQLite storage.

An AI-first engineering toolkit that provides specialized knowledge, workflows, and standards to turn AI coding agents into senior mobile engineers.

Noob2Builder is an open-source course where an Agent teaches in the main chat, designed for absolute beginners. It covers everything from computer and AI basics to Git/GitHub, building and publishing your first project, and creating Agents—14 fully elective courses emphasizing real hands-on work and verifiable learning evidence.

Provider-neutral FastAPI gateway for LLM routing, retries, fallbacks, structured output, and usage/cost accounting. Supports Gemini and OpenAI with model aliases, retry policies, and persistent usage tracking.

LazyEdit is a local-first, AI-assisted video workflow for end-to-end content creation, processing, and optional publishing.

A desktop pet for Windows (macOS beta): a pixel cat or dog that sits in a transparent, click-through overlay, reacts to typing, scrolling, petting and cursor play, and delivers break timers, reminders and optional mail or calendar alerts. All sprites and sounds are generated in code.

FAME3R is a Python package providing a random forest model for predicting phase 1 and phase 2 sites-of-metabolism in small organic molecules, with models available for non-commercial research.

clinosim is a synthetic EHR data generator that creates clinically coherent HL7 FHIR R4 data through physiological simulation, supporting US and JP standards for AI training and testing.

Arcadia is a local-first project operating system for managing creative and technical work. It tracks progress, routes tasks between humans and AI agents, generates mission logs, and helps turn ideas into shipped artifacts through evidence-based workflows.

A browser-based subtitle editor featuring speaker-specific lanes to streamline the process from transcription to correction and export.

UMADock is an open-source molecular docking tool that places small molecules into protein binding sites using machine-learning interatomic potentials, with automated site preparation and cloud execution.

Zeref is a TypeScript monorepo research and approval platform. It uses Next.js, Postgres, and Playwright to collect, normalize, and analyze data, enforcing a human-in-the-loop gate before any outbound actions.

An MIT-licensed foundation that gives AI agents primitives for building consumer-app businesses: capabilities, providers, recipes, sourced knowledge and evidence, driven through a CLI, an MCP server and a skill.

LingoCue is a Windows English learning tool for Chinese users that provides word lookup, vocabulary lists, difficulty analysis, and AI dialogue via YouTube subtitles, supporting Chinese-English comparison and local media libraries.

Zotero CLI is an English-language command-line tool for managing Zotero libraries and supporting rigorous systematic literature reviews. It combines Zotero item and collection operations, multi-source import, interactive screening, audit trails, citation snowballing, data extraction, PRISMA reporting, and optional local RAG/LLM-backed semantic search.

A drop-in replacement for `claude -p` that drives the Claude Code interactive TUI over a PTY so sessions bill against the unlimited subscription pool rather than the per-token Agent SDK credit pool. Linux only, x86_64 static binary.

Mural is a TypeScript console application that serves as an architecture agent for Claude Code, providing diagram tooling with build and watch scripts.

FairMind is an open‑source AI governance platform providing bias detection, fairness testing, and compliance tracking for ML, LLM, and multimodal AI models. It offers evidence‑grade evaluation, model registry, and remediation tools.

Longe is a self-improving LLM harness in a single Rust binary. It runs persistent sessions with a Lua REPL, three-level memory, sandboxed execution, budget enforcement, and post-run reflection to iterate on its own skills and prompts.

An auto-updating index of LLM agent frameworks on GitHub, refreshed every 15 minutes by a GitHub Actions cron job that scans, diffs and republishes a structured table of tracked repositories.

A pre-research hook for Claude Code: it runs Haiku to explore your codebase with Glob, Grep, Read and Git tools, then injects a structured findings block as context before Opus or Sonnet responds, with caching and skip detection.

Obsidian plugin for Bible study, enabling multi-version navigation, parallel reading, verse referencing, and structured note-taking within the vault.

Izran AI is an open-source intelligent assistant dedicated to the Tamazight language (NaRif) and Tifinagh script, offering dictionary, speech synthesis, and image generation.

Companion plugin for the Signal & Noise WordPress theme: SEO, login hardening, first-party edge analytics, Cloudflare purge, discography sync, cryptographic provenance, AI editorial helpers and an MCP agent surface.

Consigliere is an AI-powered CLI for organizing knowledge, projects, and ideas. It creates a structured workspace that integrates with AI assistants like Claude Code to maintain context, track progress, and manage an idea-to-project lifecycle.

An educational repository teaching supervised machine learning from first principles using Python, covering mathematical foundations and practical implementations.

Turbo AI Chat is a native on-device LLM chat application based on HarmonyOS NEXT, designed to verify the complete pipeline for running local LLMs directly on HarmonyOS devices.

A Telegram bridge for AI coding agents: a CLI that pushes status, questions and files to Telegram, plus a daemon that delivers your phone replies back into agent tmux panes as tappable buttons.

Web UI Quality is an Apache-2.0 open-source preview CLI that keeps scope, actual change, evidence and verification separate for AI-assisted Web edits, and refuses to treat a model suggestion as write authority.

Takakia is a lightweight command-line AI chat interface optimized for low-spec hardware, featuring direct API streaming and minimal resource overhead.

A personal marketplace of agentic coding skills for AI assistants, offering plugins for terminal UI design, DevOps automation, security management, and game development workflows.

SupaNexus is an open AI gateway that unifies access to multiple LLM providers via one API, simplifying development with OpenAI-compatible interfaces and centralized model management.

Token Harness helps users optimize Claude Code and Codex agents locally by checking configurations, reducing context overhead, and recommending actions — all without cloud services or credential exposure.

Markovian is an experimental Haskell package for finite stochastic kernels, Markov reward/decision processes, and policies. It provides exact evaluation for bounded scopes including MRP/MDP evaluation, policy iteration, Bayesian inference, circuit representations, and finite open games. The package emphasizes mathematical rigor with separate modules for numerical, sampling, learning, and benchmarking capabilities.

A Node.js skill that turns one photo into a scroll-scrubbed website hero by generating a storyboard, keyframes, and Kling video tweens, then exporting WebP frames for canvas playback.

ctgbot is an open orchestration platform for organic agentic ecosystems, providing AI agents with persistent identities, isolated Docker runtimes, and authenticated communication channels.

一个专为 Cloudflare Workers AI 设计的零成本网关。通过多账号免费额度叠加、智能路由和熔断机制，将 Qwen3 等模型转化为标准 OpenAI API，支持 Cherry Studio 等客户端接入。

TangleClaw is an AI coding session orchestrator for macOS that wraps Claude Code, Codex, Antigravity, Aider, and OpenClaw sessions in persistent tmux processes. It provides session continuity, structured wrap summaries, searchable history, secure remote access via Caddy, inter-session agent messaging, and a dashboard PWA — all with zero npm dependencies.

TM Kamishibai is an interactive storytelling system that uses body pose recognition to advance narratives, integrating Teachable Machine with TurboWarp.

Aeon is an autonomous agent framework designed for unattended operation, featuring 160+ skills for tasks like research, PR reviews, and market monitoring. It self-heals, monitors quality, and persists memory, running on GitHub Actions.

VLStream Cloud is an open-source Video IoT platform built on Spring Boot and Vue 3 for device and stream management, intelligent video analysis, algorithm lifecycle management, monitoring and alerting, with MQTT model delivery to Hi3519DV500 cameras.

Tandem is a self-hosted server with web and Android clients that keep one reading position across an ebook and its audiobook. It transcribes the audiobook with Whisper, aligns the transcript to the EPUB text sentence by sentence, and stores progress server-side.

CLI and SDK to route, analyze, and cost-gate single LLM API calls with full HTTP observability, token counting, and provider-specific pricing.

Unofficial CLI and MCP server for UPC's Blackboard Learn: query courses, assignments, grades, announcements, and materials from the terminal or AI assistants like Claude, Cursor, or Copilot, without university OAuth keys.

Proving Ground is an independent, black-box benchmark and certification framework designed to objectively evaluate AI agents across twelve performance and safety dimensions.

Mill is a macOS desktop workbench where humans and AI agents compose automations under the same guardrails: every action leaving your machine is previewed and gated first. Single Go + React binary, data kept in local files, agents connect over MCP.

SwarmingLilMen is an early-stage C#/.NET 8.0 2D boids swarm simulation exploring emergent multi-agent systems via composable steering rules, with JavaScript browser demos and a roadmap toward evolution and large-scale performance.

PolyOCR Service is a multi-language OCR service built on PaddleOCR 3.x, supporting recognition for 78 languages, optional translation capabilities, and a standalone PaddleOCR-VL service.

A static browser home page that lets you type a topic to instantly open it in AI engines like Google AI Mode, Perplexity, ChatGPT, or Claude. Supports custom prompts, browser extensions for new tabs, and optional cloud sync via magic-link sign-in without storing your search queries.

An OpenAI-compatible failover proxy that automatically switches between LLM providers to ensure uninterrupted service and reduced latency.

CodeAgent Mobile clients provide CLI, VS Code/Cursor/Windsurf, and JetBrains plugins to control AI coding agents (Claude Code, Copilot, etc.) from a phone or dashboard, enabling remote approval and workflow continuity.

jarvis (jarvis-mcp) is a local-first code intelligence MCP server for coding agents: it precomputes SCIP navigation, a Tree-sitter declaration baseline, Zoekt lexical search and optional semantic vectors, then serves nine read-only tools over stdio, keeping all data in a local directory.

Swarm is a local-first control plane for AI-agent development that monitors every Claude Code, Codex, Gemini, Grok, Aider, and opencode session on your machine — tracking live tool calls, token spend, cost, tasks, worktrees, and resources — with rules enforcement, a coordination ledger, and a unified dashboard.

Premove ITN is an open-source, context-aware inverse text normalization tool for English voice-agent transcripts. It converts spoken ASR output into canonical written forms using a generate-score-decode pipeline with DeBERTa contextual scoring.

Modern .NET bindings for raylib 6 and raygui, providing a multi-package ecosystem for game development, hosting, and native interop.

NovaFabric is an open-source, self-hosted CLI that captures any AI or HPC run — script, agent, or model call — as a portable, secret-redacted, replayable evidence capsule you own, with no application code changes.

一款專為 AI 代理設計的 NotebookLM 建課技能,透過 14 階段流程與瀏覽器自動化,將粗略大綱轉化為具權威來源引用、防幻覺的完整課程教材。

Okay! is a high-performance extensible effects library for Scala 3, providing stack-safe delimited control, cross-platform async primitives, and efficient streaming.

ForgeField is an AI-native construction management SaaS with 35+ modules for safety, finance, and BIM, featuring offline field execution and predictive risk tools.

Iris is a local-first MCP server that scores AI agent runs for quality, safety, and cost using 20 built-in deterministic rules, an optional LLM judge, and a web dashboard — all on your machine with no account or telemetry.

aiHelpDesk is a governed AI agent system for production database incident response and remediation across VM, Docker/Podman, and Kubernetes deployments. It diagnoses failures, executes fix playbooks under audit trails, and learns from every resolved incident.

An MCP server that lets AI agents find, verify, message, schedule with and pay small businesses over WhatsApp, SMS, email and voice, with a non-bypassable TCPA/GDPR/CASL compliance gate, verifiable Ed25519 compliance receipts and 23 callable tools.

SecureFlow is a local-first application security platform in Rust. It combines deterministic source-to-sink analysis, human validation workflows, and offline API inventorying. The tool prioritizes reproducible evidence, maintaining strict separation between automated candidates and final human judgments, with no automatic vulnerability validation.

Production-grade LLM reverse proxy for the Z.AI Claude API with token counting, adaptive rate limiting, Prometheus metrics, and a real-time monitoring dashboard.

Polyfish is an open-source AI player for the strategy game Polytopia, combining Alpha-Zero-style MCTS with a neural network trained via self-play in Rust. It includes a full game engine simulator, a web UI, and a C++ memory-reader that extracts live game states from the Steam version.

Forgehouse is an open-source, full-stack AI website studio that lets users create, revise, preview, and publish browser-rendered websites through natural-language prompts. It features Groq-powered generation with a safe fallback, immutable revision history, sandboxed live previews, and application-hosted publishing.

Utility OS is a Next.js academic workspace for university students with Google Drive-synced notes, hybrid RAG AI search with grounded citations, a study planner, GPA calculator, SRS flashcards, Pomodoro timer, and a PWA client.

AI-powered real-time visual novel engine with streaming narrative, character sprites, scene backgrounds, branching choices, and co-creation. Runs as desktop app or browser via FastAPI+SSE.

A local facial recognition attendance system with a React Native Expo mobile app and FastAPI Python backend. It captures faces via Expo Camera, processes them with OpenCV LBPH, and logs timestamped attendance into SQLite.

A DeepSeek Harness plugin that exports OpenTelemetry traces, metrics, and logs to GreptimeDB, with seven Grafana dashboards for tracking token usage, costs, and performance of AI agent runs.

A VST3/AU plugin that integrates ElevenLabs sound generation directly into your DAW for creating and slicing sound effects.

Local-first AI console built with Next.js and TypeScript, integrating Ollama for streaming chat, document RAG, model routing, and user-curated learning notes — all under local control without cloud dependencies.

A high-performance Rust library for tropical matrix multiplication, featuring SIMD and CUDA backends, multiple semirings, and Python/PyTorch bindings for AI and graph applications.

Shared native Rust compute core for NEAT-AI: the neat-core crate holds the scoring, loss and batched SIMD kernels used to run evolved neural networks, with optional rayon parallelism and a dual wasm32 and wasm64 WebAssembly bundle release pipeline.

An experimental security extension for the Model Context Protocol (MCP) providing runtime evidence for tool calls via HTTP message signatures and mTLS.

A collection of seven skill libraries for AI coding agents covering code cleanup, prose editing, parallel agent orchestration, interface design, product feedback, design research, and QA. Works with Claude Code, Cursor, Codex and other agents that read skill files.

cctrace is a TLS-intercepting tracer for Claude Code, Codex, Grok, and Kimi CLIs that captures every API call in a live web UI with session replay, cost tracking, and cross-project dashboards.

CLIO Agent is an autonomous AI system for scientific data management at scale. Built on the IOWarp platform, it orchestrates multi-expert tiers with FastMCP support for HDF5/Parquet/CSV, and features a Bubbletea terminal UI. It integrates with major LLMs (Ollama, OpenAI, Anthropic) and serves as the intelligence layer (CEI) of the IOWarp ecosystem.

Apollo is a Python package providing post-hoc statistical procedures with bias-aware corrections for common metrics in computational and ML/DL pipelines.

A DeFi arbitrage bot that utilizes flash loans to execute trades between different decentralized exchanges when price discrepancies are detected.

Peaky Peek is a local-first, open-source audit and trust console for AI agents. It captures causal chains, verifies claims deterministically, and produces explainable trust scores with failure narratives — all running on your machine.

modelstat is an open‑source AI spend analytics tool that reads local AI‑coding logs, redacts PII on‑device, and reports dollar‑precise costs by project, work type, and model, with a Rust daemon, MCP server, and broad integrations.

A generic MCP bridge that allows AI agents to control VST3/AU plugins with a semantic layer for parameter mapping and a closed-loop system for audio measurement and tuning.

A Tauri desktop app for Windows that drives the AI coding CLIs already installed on your machine — Claude Code, Copilot CLI, Gemini, Codex, opencode, Ollama, Aider, Antigravity — as a planner/implementer/reviewer team, with a task board, git worktrees, hooks, a CLI and phone access. It ships no model or key of its own.

A comprehensive kit that transforms a Claude Code subscription into a team-oriented assistant accessible via Telegram, featuring tools for agent monitoring, skill management, and client communication.

Zara is an experimental local-first AI assistant and Linux desktop copilot that combines symbolic logic (Prolog) with LLMs for intent handling and reasoning.

Web of Flaws is a structured, markdown-first catalog of web security vulnerabilities and secure code replacements designed for developers, security engineers, and AI coding agents.

lore is a Bun-based command line tool that mirrors Claude Code's local transcripts into an archive, indexes them with SQLite FTS5, and serves a local web explorer for searching sessions and profiling token usage.

TerraSecure is an ML-powered security scanner for Terraform and HCL Infrastructure as Code across AWS, Azure, and GCP. It detects cloud misconfigurations at build time using a multi-cloud rule engine, an XGBoost ML model for AWS, and AI analysis for contextual remediation, integrating with CI/CD workflows.

Meshify is a real-time face mesh detection application that identifies and tracks facial landmarks using OpenCV, MediaPipe, and CVZone.

ferrite is a Rust-native inference engine for GLM-5.3-Flash, featuring PDAF disaggregation, composable TP/CP/DCP parallelism, and exact MHC. It supports GatedDeltaNet and DSA sparse attention with CUDA kernels for sm_100a.

A tiny GPT language model (~540M parameters) designed to be trained from scratch on consumer laptop hardware, with pretraining on Fineweb-edu and chat finetuning capabilities.

An open-source, multi-provider LLM chat platform featuring organization management, model routing, RAG integration, sandboxed code execution, and OpenAI-compatible APIs.

A hands-on Elixir lab for learning distributed systems by building them from first principles using raw process primitives, OTP concepts, and standalone runnable examples.

A local multimodal LLM plugin for Unreal Engine 5 providing offline inference for text, speech-to-text, and text-to-speech.

Python SDK for the AskNews API that injects real-time news context into any LLM with a single line of code, offering endpoints for news search, event tracking, forecasting, analytics, deep research, knowledge graphs, and web search.

MOZAK gives a research topic or code repository a Git-native memory: six modules record goals, evidence, decisions, progress and reusable concepts so people and coding agents share the same project state across sessions.

Calor is a programming language designed for AI coding agents, compiling to .NET via C#. It makes code semantics explicit—effects, contracts, and stable IDs—so agents can reason, verify, and edit precisely without inferring hidden logic.

PromiseLink is an AI-driven personal business relationship management assistant focused on ensuring data sovereignty through local storage and implementing closed-loop management from event entry to promise tracking.

An educational machine learning project that classifies online payment transactions as legitimate or fraudulent. It preprocesses a transaction dataset, encodes and scales features, then trains and evaluates Logistic Regression, Decision Tree, and Random Forest models with Python, pandas, NumPy, and scikit-learn.

Read-only-by-default Model Context Protocol (MCP) server for Microsoft SQL Server, providing metadata discovery, parameterized SELECT-only queries, execution plan analysis for slow query diagnosis, profile-based multi-connection configuration, and optional per-profile write access, shipped as a .NET NuGet tool.

TawkType is a local voice typing tool for Windows that converts speech to text directly into the active application. It uses NVIDIA Parakeet or OpenAI Whisper engines locally, ensuring privacy with no telemetry or accounts. Features include multiple text modes, smart cursor fitting, history management, and optional AI cleanup.

A GenAI connector designed for integration with the ExFace business web application platform.

SkyClass Distill is a pipeline tool that transforms teaching videos into structured Teaching Skills, supporting video collection, transcription, evidence extraction, and LLM distillation.

A curated collection of 107 foundational generative AI research papers with comprehensive summaries, learning roadmaps, glossaries, and decision guides—making cutting-edge AI research accessible to everyone.

RouteTok is a local-first LLM inference router with OpenAI and Anthropic compatible APIs, health-aware failover, multi-provider catalogs, an operations dashboard, and a model sandbox.

TianGong LCA MCP Server exposes life-cycle assessment data tools over the Model Context Protocol via STDIO and Streamable HTTP, with OAuth 2.1 protection, Supabase-backed auth, and GLAD dataset search.

An AI-powered mixing and mastering tool providing both a desktop application and an MCP server for Ableton Live integration.

Ashlar is a local-first .NET runtime for auditable AI workflows you can embed. It offers task audit trails, a CI-proven certification gate, local model routing, and self-hosted deployment via CLI, HTTP API, containers, or NuGet.

UnrealAgentPlayer allows AI coding agents to drive the Unreal Editor for closed-loop self-testing via a C++ plugin and a Python MCP server.

artefacto bridges coding agents and humans with interactive artifacts. It renders agent-generated plans as browser pages for live review, comments, and approvals, feeding data back to the agent.

An AI agent designed for the creation of social media content.

MCP server for VictoriaMetrics Anomaly Detection (vmanomaly), enabling AI assistants to perform health checks, model management, configuration generation, alert rule creation, and documentation search via the Model Context Protocol.

LinkeGringo is a LinkedIn profile optimizer for Brazilian engineers seeking remote US jobs. It runs 100% in the browser (SPA, no backend), uses a personal Google Gemini key (BYOK), and rewrites profiles from exported PDFs.

MyCut is an AI video editing Agent that provides a complete creative closed-loop, from trending topic selection and copywriting generation to automatic video slicing.

FamilyBot is a WhatsApp-native AI assistant that monitors group chats to extract events and tasks, syncs them to Google Calendar, and provides daily digests to a coordination group.

An open, git-based standard for organizing agent knowledge and instructions in portable Markdown folders, with a TypeScript reference library and conformance kit.

Batchalign3 is a TalkBank audio and ML pipeline for producing and enriching CHAT transcripts, covering ASR, forced alignment, neural morphotagging, translation and utterance segmentation. It ships a CLI, Python package, PyO3 bridge, React dashboard and an experimental Tauri desktop shell.

A3S Cloud is a self-hosted, Agent-first developer platform that turns tenant-authorized product intent into durable AaaS, WaaS, FaaS, Durable Cell, model-inference and Static Web services on operator-owned CPU/GPU infrastructure.

PASO is a production-grade, real-time communication platform featuring AI moderation, voice/video calling, and scalable Socket.IO infrastructure. It combines messaging, AI features, and administrative controls.

An interactive storytelling framework that uses LLMs to generate dynamic narratives based on predefined, graph-based story paths.

GramGuidedURA provides code for semi-blind channel estimation in Unsourced Random Access (URA) using Gram-guided diffusion models.

OpenCosmos is a creative platform and ecosystem consisting of multiple applications built using a unified, human-centered design system.

Finite state and Constraint Grammar based morphological analysers, proofing tools, and language resources for the Komi-Zyrian language, part of the GiellaLT project.

Slopcamera is a local visual studio for coding agents: a Bun CLI, TypeScript SDK and Agent Skill that let agents author scenes, combine generated and recorded media, and export images, diagrams, animation and video while keeping editable sources.

An MCP server for South Korean listed companies' ESG data, created by a securities analyst. It allows AI agents like Claude and ChatGPT to query ratings from 5 agencies, governance indicators, and GHG emissions from KRX, KIND, and GIR via 12 tools without requiring API keys.

SYNAPSE is an AI-powered intelligence aggregation and automation platform featuring a multi-agent system and RAG capabilities for research and document generation.

nexus-vscode is an MCP proxy extension for VSCode and Cursor that forwards AI tool calls to Unreal Engine (UE) instances.

CoalLedger is a docs-health checking suite for AI coding agents — the documentation counterpart to CoalMine's code canaries. Seven canaries flag wrong, incomplete, stale, contradictory, broken, unreadable and (optionally) leaked documentation, with a bundled zero-dependency CommonMark+GFM AST engine, context-judged severity and choice-gated fixes.

OpenSelf is a local-first, open-source context layer for AI agents. It stores source-attributed, time-aware memories in SQLite and exposes them via MCP or JavaScript API, with optional encryption and privacy controls.

A group chat protocol hub based on AG-UI Group Chat Extension Protocol v1.0, implemented in C#/.NET 10, featuring agent gateways, RAG semantic memory, HITL approval, and dual WebSocket/SSE transport.

Open-source Finnish language resources and tools built on finite state transducers and Constraint Grammar, providing morphological analysers, spell checkers, and proofing tools for desktop and mobile platforms.

A fully offline, deterministic MCP server that gives AI agents local tools for exact math, date and timezone handling, unit and base conversion, subnet math, text distance and token counting — no network calls, telemetry or API keys.

AAMF is an AI-agent framework that migrates legacy codebases to other languages by deriving a deterministic task graph, running phased agents, and verifying build/test parity with resumable checkpoints.

cc-grass reads Claude Code session logs under ~/.claude/projects (and optionally Codex CLI sessions) and renders a GitHub-style orange contribution-graph SVG you can commit to a profile README. Zero dependencies, Node 18+, incremental cache, optional HTML with tooltips.

Helio is a data visualization tool that transforms raw data from CSVs, SQL databases, or REST APIs into personalized dashboards using visual pipelines and AI-assisted editing.

Lociant is a local AI runtime for edge devices like Android phones and Rockchip boards. It enables local model inference via GGUF/llama.cpp, exposes device capabilities as MCP tools, and provides an OpenAI-compatible control API for external orchestration.

A local, read‑only dashboard that visualizes Claude Code usage—token counts, cost estimates, sessions, tools, skills, projects, and activity patterns—by scanning ~/.claude/projects/ and serving a FastAPI‑based UI.

aiueos is a capability-secure operating system designed for AI agents, featuring a C-free bare-metal kernel profile and Wasm component execution.

A community-maintained catalog of Bangla (Bengali) NLP resources — 712 papers, 63 datasets, 20 models, and 9 tools across 13 tasks — built as a static Astro site with strict data verification and shareable filters.

Ghostget is an open-source CLI and SDK that provides AI agents with precise, bounded web capabilities. It enables secure page capture, media archiving, and encrypted reads from connected services like social platforms and email, ensuring local custody and explicit trust boundaries without granting unrestricted browser or API access.

ALPURIS OS is a Python-based open-source engine that simulates a metropolis of 100 autonomous AI citizens using PIANO dual-speed cognition, an ECS event bus, a 3D WebGL voxel city and procedural Web Audio.

UE5 asset workbench plugin enables scripts and AI agents to read, edit, import, migrate, and audit Unreal Engine 5 uasset files by exporting structured JSON and applying changes via commandlets, supporting Blueprints, animations, widgets, materials, Niagara, levels, etc.

RepoScout is a fast, local-first Rust CLI for repository intelligence, providing code metrics, complexity analysis, and duplication detection for humans and coding agents.

LuoxueAPI is an AI API gateway platform designed for distributing and managing API quotas from AI product subscriptions.

Stateless LLM API gateway routing OpenAI, Anthropic, and Gemini requests across multiple providers with cross-dialect translation, usage metering, and single-binary deployment.

A local OpenAI-compatible API gateway supporting multi-provider routing, circuit breaking, Chinese error prompts, a visual management panel, and native desktop application delivery.

Open LLM hallucination benchmark regarding the BNCC (Brazil's National Common Curricular Base). It measures how much models invent official codes and texts using an auditable methodology with raw data and CI.

AI Engineering is an open-source e-book providing a systematic guide to building production-grade AI systems, from LLM fundamentals to advanced agent architectures. Maintained by the community and Hermes Agent, it features daily updates, traceable sources, and advanced search capabilities.

Profer is a local-first AI Agent desktop app built on the Claude Agent SDK and Pi dual runtime, supporting multi-model integration, collaborative sub-agents, scheduled automation, mobile remote access, and team workspaces.

Open-source, production-oriented platform for crypto futures research and execution on Binance USD-M Futures and OKX, combining advisory AI agents, a Decision/Judge pipeline, a deterministic risk engine, adaptive TP/SL and position management.

ChatMonteur is an agent-orchestrated AI video editor for talking-head footage. It transcribes, cuts by meaning, adds captions, motion graphics, sound, and color — driven by Claude Code or Codex. Two tested quality gates reject weak plans and broken files. Free and local by default.

comma-lab is a community and historical-record research workspace for the comma.ai video compression challenge. It provides the Task-Aware Compression library tac, lab operations tooling, exact replay custody, evidence grades, and OSS release hygiene.

Starbase is a web-based database and toolkit for exploring Starship transposable elements in fungi, offering sequence browsing, BLAST/HMMER search, submission, and visualization features.

SparkLang is an MIT-licensed language and runtime for plain .spark files: dry-run-first CLI, compile/bytecode dumps, IDE language ops, playbooks, model lab ops, and optional live gateway, voice, browser and CUDA surfaces.

Self-hosted security operations stack combining SIEM log collection, endpoint detection with Sigma rules and cross-event correlation, SOAR playbooks, OSV vulnerability scanning and a local Ollama model for AI triage, deployed with a single docker compose up.

Overflow is a cooperative credit ledger for open-source work: sponsors offer issues, contributors close them via GitHub, and the service records settled transfers with labels, comments, API tokens and MCP tools.

Frags is an advanced AI/LLM agent CLI tool and Go library for complex data workflows including retrieval, transformation, extraction, and aggregation. Designed for engineers with a focus on precision, structured output, and extensibility.

vtmate is a terminal-based voice AI toolkit featuring ultra-low latency, 41 language support, and integrated TTS/STT. It enables live voice conversations, debates, voice cloning, session exports, and background daemon mode with global shortcuts for seamless AI interaction.

Vtx is a minimalist coding agent harness featuring a Textual TUI and headless CLI. It offers a lean ~2,600-token system prompt, supports 50+ LLM providers, and includes modular skills, session trees, and safe permission controls.

Downcity offers AI builders a reusable agent runtime layer: a CLI-hosted local City manages, coordinates and operates many agents, with shared models, tools, memory, tasks, plugins, permissions, usage, billing and Federation services.

pkcs11rs is a Rust PKCS #11 provider for YubiKey, YubiHSM, FIDO2, and software tokens, implementing standards up to version 3.2 with cross-platform support.

Strata is a native machine learning and linear algebra library written in Mojo, offering scikit-learn-compatible estimators, dense/sparse matrix containers, zero-copy serialization, and composable pipelines with SIMD and LAPACK acceleration.

npm/PyPI packages and an MCP server for querying the Brazilian BNCC curriculum. Bundled data with 1,721 verified learnings from MEC/CNE, zero runtime dependencies. Integrates BNCC into TypeScript, Python, or AI agents via MCP.

A local-first web UI for running Claude Code and Codex sessions in browser tabs with real PTY terminals, persistent history, and agent coordination via MCP. Sessions run in tmux for durability, with token-authenticated localhost security.

Cloudx is a local-first mobile and desktop workbench for running and supervising Codex CLI sessions on your own Linux machine: pane layouts, file tools, diffs, worktrees, plugin tabs, a local documentation archive, Jira views and constrained voice control.

AgentRecall is a local-first .NET CLI and MCP server that captures coding feedback, failures, and preferences into structured, ranked rules for AI coding agents like Claude Code, with conflict resolution and deterministic context injection.

A local-first review surface for writing with AI coding agents, allowing users to annotate and edit documents while routing feedback back to the agent session.

NEAT-AI is a Deno/TypeScript neuroevolution library that evolves neural networks using WASM-accelerated activation, memetic evolution, error-guided structural discovery, and optional GPU-accelerated analysis via a Rust FFI extension.

Fermix is a self-hosted, Elixir-native multi-agent AI platform that runs as a local daemon and connects to your existing chat apps (Telegram, WhatsApp, Slack, Discord, Signal) plus a CLI. It supports multiple LLM providers, scheduled jobs, voice companion, and sandboxed tool execution.

An unofficial MCP server that gives AI assistants seven read-only tools to search, list and read any Fumadocs documentation site, working against a deployed URL or a local docs repo via a single npx command.

CWSP-document is a tool for working with Markdown documents, supporting viewing, editing, printing, and exporting to DOCX format.

An MCP server providing LLM agents with lean tools to look up, read, and cross-reference academic papers across seven providers including OpenAlex, arXiv, bioRxiv, ACL Anthology, Crossref, OpenCitations, and Wikipedia.

Research repository for an AI-assisted mod authoring agent for Skyrim SE/AE. It proposes a hybrid orchestrator architecture prioritizing headless, deterministic operations over direct Creation Kit automation. Includes validated synthetic proof-of-concept (POC-002) with strict safety policies, typed plans, and human approval gates.

Self-hosted Telegram bot that turns an Obsidian vault into a personal AI agent: capture text, voice, photos and links, then file them as markdown, kanban tasks and a finance ledger. Modules (planning, knowledge, finance) are fail-closed and can be disabled entirely.

Python and MCP example for an Apify actor that returns US House and Senate congressional stock trades and financial disclosures as structured JSON, with filters for member, ticker, and date range.

Restage is a server-driven UI toolkit for Flutter that allows developers to ship UI updates over the air using their own widgets and themes.

LAMINARIA is a research-stage unified toolchain that models Rust and Nim builds as one explainable action graph, spanning dependency resolution, compiler pipelines, backend routes, caching and resource-aware execution.

FlashLoanArbitrage is a DeFi bot that scans ETH/USDC prices across Chainlink, Uniswap V2, SushiSwap, Curve, and Balancer, then executes flash loan arbitrage through Aave, dYdX, Uniswap V3, or Balancer when price spreads reach 0.9% or more.

An OpenAI-compatible AI gateway written in Rust that provides intelligent routing, automatic failover, and multi-provider support in a single binary.