Autonomous AI agents that perform tasks independently
mutton-dev
Autonomous Agent Development Orchestrator - Multi-agent TDD pipeline powered by Claude
luismdev
Official TypeScript SDK for Stackbone — the marketplace and managed runtime for containerized AI agents.
Portable reproducibility seed bundle for AI-agent steps (Python port of @p-vbordei/agent-rerun)
Byte-deterministic transcript format for AI-agent conversations (Python port of @p-vbordei/agent-scroll)
trustaldo
Web GUI for Context Expert (ctx)
GitHub Actions
A Payload CMS plugin that adds an AI chat agent for reading, creating, and updating content
Rave
A local-first cognitive agent with a learned router (Caudate) and Claude-SDK-shaped tool palette.
A local-first cognitive agent with a learned router (Caudate) and Claude-SDK-shaped tool palette.
MayAI <[email protected]>
Command-line client for Italian PEC (Posta Elettronica Certificata) — built for AI agents and developers.
DocAgent contributors
Whole-repo documentation generator (README, AGENTS.md, CLAUDE.md, how-to guides, API reference, llms.txt) with deterministic verifier and citation grounding. Not affiliated with facebookresearch/DocAgent (Meta AI, arXiv 2504.08725).
...moreStandalone agentic framework for local LLMs via Ollama — reliable tool calling, session persistence, and loop guards
Ilya Kamen
Autonomous multi-agent coding orchestrator.
wachawo
Modular, independent tool kits (filesystem, SQL, pandas, memory, RAG, ...) for pydantic-ai agents.
RAG layer for pydantic-ai agents. Part of pydantic-ai-toolkits.
mico contributors
Terminal-first coding agent CLI for local and OpenAI-compatible models
GEPA adapter for LangChain v1 — optimize prompts for chat models, agents, and LangGraph pipelines
memoryforensics1
C# MCP server for kernel & user-mode Windows debugging — DbgEng COM, KDNET, Frida, dbgsrv, TTD, and integrated VM control. 29 tools for LLM agents.
...moreGloomsen-SD
Gemini Roleplay Core systemprompt, a framework for highly immersive, psychologically profound Simulation\role-playing.
beltromatti
LunarLander-v3 game played by an AI agent trained with the DQN algorithm with Prioritized Experience Replay using deep-reinforcement-learning python framework.
...morewachawo
Toolkits for pydantic-ai agents: FS, SQL, pandas, memory, RAG.
BrettMGoughWork
An skills-based LLM runtime, using lessons learned from previous attempts
jcartu
Self-hostable agent platform with live computer view, parallel research, voice, and a Tauri desktop app. CodeAct loop, Docker-sandboxed Chromium, server-enforced cost ceiling, MCP host.
...moreszqjl
Hermes Agent memory awareness pipeline — perception, injection, and retrieval for LLM agents
frontier-infra
Layered behavioral configuration for Claude Code: universal discipline + role overlays (Forge/Quill/Scout/Warden) + project overlays + verifiable /goal contracts with Warden sign-off.
...more