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.
Open source. Open possibilities.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
A personal marketplace of agentic coding skills for AI assistants, offering plugins for terminal UI design, DevOps automation, security management, and game development workflows.
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.
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.
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.
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.
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.
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。
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.
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.
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 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.
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.
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.
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.
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.
SkyClass Distill is a pipeline tool that transforms teaching videos into structured Teaching Skills, supporting video collection, transcription, evidence extraction, and LLM distillation.
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.
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.
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.
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.
An open, git-based standard for organizing agent knowledge and instructions in portable Markdown folders, with a TypeScript reference library and conformance kit.
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.
An interactive storytelling framework that uses LLMs to generate dynamic narratives based on predefined, graph-based story paths.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
MCP Arcade is a command-line testing tool that runs a small catalog of experiments, called atoms, against MCP servers, judging results by the JSON-RPC wire and sandbox file changes rather than by tool descriptions or model prose.
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.
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.
An unofficial Codex Skill for repository delivery: it routes work between the current task, internal agents and optional App tasks, with explicit ownership, isolated Git worktrees, independent review, an installer with check/dry-run modes, and deterministic tests.
Shatterfish is an open-source engine for Shattered Pixel Dungeon, inspired by Stockfish. It enables headless gameplay, symbolic AI bots, statistical testing, and in-game overlays — all while enforcing fair information parity with human players.
HarnessDesk is an MIT-licensed macOS developer preview that acts as a vendor-neutral control plane for coding agents such as Codex, Claude Code, Cursor, Gemini CLI and other ACP agents, adding shared history, permissions, handoffs, audit logs, worktrees and usage views.
GTM Agent is an open-source tool that connects Slack to a Git-backed GTM workspace and Vercel workflows, allowing teams to build and run GTM processes like ICP definition, persona creation, and prospect qualification directly from chat.
Runewake is an AI-backed fantasy TCG featuring a node-based map, rune system, and archaeology progression, built with Godot and .NET.
wicked-garden is a curated skill catalog for coding agents (Claude Code, Codex, etc.) that fills gaps in verification, memory, and multi-model review. It re-derives 'done' from evidence, tracks injected edges, and enforces rigorous gates without forcing a specific workflow.
Agent skill for OpenClaw and DeepSeek Harness enabling intelligent A-share stock selection, quantitative analysis, and stock pool management.
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.
Malleus is a protocol and Python reference implementation for typed, fail-closed semantic change, enabling explainable and replayable knowledge graph population through ontology-driven contracts.
Commitarium is a local-first workspace where AI coding agents collaborate to plan, build, and review software. It uses a coordinator to manage workflows, SQLite for state, and optional real Codex/Claude agents integrated with Forgejo for version control and audit trails.
A framework for establishing bootstrap instruction conventions and safety guardrails for AI coding agents and human collaborators across software projects.
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.
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.
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.
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.
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。
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.
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.
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.
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.
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.
OpsNest is an open-source workspace for managing servers, routers, NAS devices, and endpoints from one place. It combines a dashboard, service discovery, and an AI-assisted SSH terminal, allowing operators to inspect systems and handle routine tasks without losing control. Built for homelabs, self-hosted deployments, and small teams, OpsNest keeps infrastructure context close at hand. It supports Linux servers, OpenWrt routers, and NAS devices, helping users organize services and tools. Its goal is to make infrastructure work easier to understand, faster to operate, and simpler to maintain.
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.
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.
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.
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.
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.
A self-updating calendar for AI conferences, meetups, and hackathons in Berlin, utilizing iCal feeds and GitHub Actions for automated updates.
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.
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.
Deskmate provides open-source, self-hostable AI coworkers for Slack that integrate with your data via MCP and require human approval for write operations.
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.
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.
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.
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.
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.
An embedded micro-VM sandbox built on libkrun for safely running AI agents, supporting Linux (KVM) and macOS (Hypervisor.framework).
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.