Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
39 projects
Remove filter Agent frameworks and toolsRemove filter PythonRemove filter CLIClear filters- 1.5k
Harvey LAB
Benchmark tasks and harness for testing AI agents on legal work
- 2.2k
SIA
Self-improvement loop that rewrites an AI agent to score higher on a benchmark
- Antoine2.3k
forge
Reliability layer that makes local LLM tool calls succeed more often
3.7k
- Vitali Avagyan5.3k
Code-Graph-RAG
Maps a codebase into a knowledge graph to query and edit in plain English
- 6.4k
LoopX
Local-first control plane for long-running coding and research agents
- 6.4k
AutoHedge
Multi-agent LLM pipeline that analyzes markets and trades on Solana
- 10.4k
Octop
Self-hosted multi-user AI assistant with teams of specialist agents
- 12.3k
OpenSRE
Framework and CLI for building AI agents that investigate incidents
- 12.7k
ViMax
Multi-agent pipeline that turns ideas, scripts, or novels into videos
- 13k
LEANN
Compact local vector index for private RAG over personal data
- 2.1k
ADR
Detection, telemetry, and benchmarking for securing enterprise AI agents
Privacy and securityAgent frameworks and toolsSecurity testing and OSINT
- LJQ14.3k
GenericAgent
Minimal agent that controls your computer and saves solved tasks as skills
- 13.5k
Speech To Speech
Local voice agent pipeline chaining VAD, speech recognition, LLM and TTS
- 16k
OpenSandbox
Isolated sandbox runtime for AI agents on Docker or Kubernetes
- 3.2k
Computer Use Preview
Reference browser agent driven by Gemini's computer use models
- 6.1k
agents-cli
Command-line tool and skills to build and ship ADK agents to Google Cloud
Agent frameworks and toolsAgent skills and pluginsDeveloper tools
- 6.9k
A.I.G
AI red teaming platform for scanning agents, MCP servers, and model infra
- 6.5k
Agent Governance Toolkit
Policy enforcement, identity, and audit trails for AI agent actions
- 30.4k
Deep Agents
Opinionated Python agent harness with sub-agents, files, and memory
- 30.5k
iFixAi
Command-line auditor that checks whether an AI agent does its intended job
- 32.6k
Cognee
Knowledge-graph memory layer that gives AI agents long-term recall
- 36k
Vibe-Trading
AI trading agent for market research, backtesting, and strategy work
- 40.4k
OpenViking
Filesystem-style context store for agent memory, knowledge, and skills
