Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONLess than 10 stars, 5+ commits in the last 30 days — projects made with care.
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.
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.
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.
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.
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.
UnrealAgentPlayer allows AI coding agents to drive the Unreal Editor for closed-loop self-testing via a C++ plugin and a Python MCP server.
An open, git-based standard for organizing agent knowledge and instructions in portable Markdown folders, with a TypeScript reference library and conformance kit.
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.
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.
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.
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.
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.
RepoScout is a fast, local-first Rust CLI for repository intelligence, providing code metrics, complexity analysis, and duplication detection for humans and coding agents.
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.
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.
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 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.
CheckMyData.ai is an AI-powered database query agent that enables natural language data analysis across PostgreSQL, MySQL, ClickHouse, and MongoDB. It features multi-agent orchestration, rich visualizations, and code-database synchronization.
Adeorq is a Windows/Linux desktop panel that runs AI coding agents in real terminals, using your existing subscriptions and CLIs. It features a multi-terminal cockpit, session management, canvas, and more, with a source-visible proprietary license.
SUNGLASSES is a local, open-source input inspection layer for AI agents. It scans text, images, audio, video, PDFs and QR codes for prompt injection, credential exfiltration and command injection, and provides a CLI, Python API, MCP server and Claude Code firewall hook.
A curated library of machine-readable task prompts and Agent Skills for coding agents, focusing on common agent failures like broken setup scripts, vague issues, and tests requiring unavailable services. Includes fixtures with planted defects for validation.
A Strands-powered agent for small embroidery and decorated-apparel shops: it reads a customer email, inspects orders, inventory and machine capacity, analyses blockers, proposes a hash-addressed schedule, and stops at a human-approval interrupt before any write.
MCP Hub is the largest open-source directory of Model Context Protocol (MCP) servers, aggregating 8,000+ servers from multiple sources with full-text search, validation, and GitHub integration.
Specrails Core is an MIT-licensed CLI that installs specification-driven, chain-of-agents workflows into a software project, connecting Claude Code, Codex CLI, Gemini CLI or Kimi Code with architect, developer and reviewer roles, OpenSpec artifacts and local configuration.
Open Kioku is a local repository intelligence tool for AI coding agents. It indexes codebases locally to provide context, generate bounded edit plans, and verify actual diffs against those plans.
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.
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.
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.
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.
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 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.
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.
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.
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.
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 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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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 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.
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.
An AI-first engineering toolkit that provides specialized knowledge, workflows, and standards to turn AI coding agents into senior mobile engineers.
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.
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 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.
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.
An OpenAI-compatible failover proxy that automatically switches between LLM providers to ensure uninterrupted service and reduced latency.
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.
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。
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.
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.
