Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
atlas-agent-control-plane
Agents & frameworksAtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI
git clone https://github.com/malevrigns/atlas-agent-control-plane.git -
agent-systems-handbook
PromptsA practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.
git clone https://github.com/Prompthon-IO/agent-systems-handbook.git -
curie
SkillsOpen-source, self-hostable platform that turns agents into co-workers. Start with Software Factory: delegate GitHub issues and review pull requests, with model, approval, and cost controls in your infrastructure.
git clone https://github.com/curie-eng/curie.git -
TraderHarness
Datasets & benchmarks面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成,支持 A 股研究|Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data
git clone https://github.com/HephaestLab/TraderHarness.git -
trace-to-practice
SkillsEvidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.
git clone https://github.com/wssfk12138/trace-to-practice.git -
autogen-studio
Agents & frameworksAutogen studio docker
git clone https://github.com/lludlow/autogen-studio.git -
Holix
SkillsHelix is a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creates reusable skills for the future.
git clone https://github.com/javded-itres/Holix.git -
veriflow-cc
SkillsVeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.
git clone https://github.com/bjwanneng/veriflow-cc.git -
model-compose
AI repositoriesDeclarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.
git clone https://github.com/hanyeol/model-compose.git -
my-codex
MCP serversAll-in-one agent harness for OpenAI Codex CLI — Boss meta-orchestrator, 17 curated agents (+17 opt-in AI specialists), 123 curated skills, 3 MCP servers. Install once, curated specialists ready.
git clone https://github.com/sehoon787/my-codex.git -
tyran
Agents & frameworksA task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
git clone https://github.com/jjanczur/tyran.git -
developer-agent-skills
Skills61 Agent Skills for developers: frontend, backend, databases, DevOps, security and AI engineering. Plain Markdown, works in Claude Code, Cursor, Codex, Copilot and Gemini CLI.
git clone https://github.com/reddygopalkrishna/developer-agent-skills.git -
openPASO
MCP serversopenPASO (formerly OASiS): an MCP server that lets an AI model run nine finite-element and multiphysics codes, with curated knowledge, verified execution and cross-code coupling. Under active development; contributions welcome.
git clone https://github.com/open-PASO/openPASO.git -
OpenART
SkillsOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
git clone https://github.com/AI45Lab/OpenART.git -
Xenon
Agents & frameworksVerifiable AI coding agent harness / 可验证的 AI 编码代理:evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP · multi-model · Windows/CJK · listed in awesome-opensource-ai & Collabnix awesome-mcp-lists
git clone https://github.com/xianyu-sheng/Xenon.git -
root-agent-skill-framework
PromptsRoot Agent for Grok Bot: sizes the team a request needs, creates the Bots, and delegates day-to-day management to Leads. Description, skills and templates.
git clone https://github.com/MrBekoX/root-agent-skill-framework.git -
octomind-tap
SkillsCommunity registry of AI agent manifests, capabilities, skills, and workflows for Octomind — run a fully-configured specialist with one command.
git clone https://github.com/Muvon/octomind-tap.git -
Hypha
Agents & frameworksHarness-oriented agent system framework for production-grade LLM agent applications
git clone https://github.com/CodeSoul-co/Hypha.git -
bg3-agent-harness
MCP serversAn AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark and a playthrough app.
git clone https://github.com/Bogzx/bg3-agent-harness.git -
agent-assh
MCP serversSSH workflow helper for LLM agents
git clone https://github.com/izzzzzi/agent-assh.git -
Pepper
Agents & frameworksiOS dynamic library MCP for agents
git clone https://github.com/skwallace36/Pepper.git -
Warden-AI
SkillsThe structurally-verified context layer for AI coding agents. Cut 50-90% of your agent's token spend.
git clone https://github.com/rynald0cst0ltziam/Warden-AI.git -
sno-station-skills
SkillsSno Station Skills: 39 tested skills that turn Claude Code and Codex into one working team. Review by a different agent, automatic handoff when an agent hits its usage limit, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.
git clone https://github.com/sno-ai/sno-station-skills.git -
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.