Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- 1.5k
Harvey LAB
Benchmark tasks and harness for testing AI agents on legal work
- 1.9k
Jido
Elixir framework for building supervised, multi-agent systems on OTP
- 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
- 3.4k
SIE
Self-hosted inference server running many open models behind one API
AI models and runtimesAgent frameworks and toolsServers and infrastructure
3.7k
- 4.5k
Embabel Agent Framework
JVM framework for building goal-driven AI agents with typed domain models
- 3.4k
Switchyard
Per-request model routing for AI agents across cheap and capable LLMs
- rUv4.6k
RuVector
Rust vector database with graph memory and local embeddings for agents
Agent frameworks and toolsAI models and runtimesData and spreadsheets
- az5.7k
RLM
Inference library letting language models recursively call themselves via a REPL
- 5.7k
UltraRAG
MCP-based framework for building and evaluating RAG pipelines in YAML
- 5.9k
Cloudflare Agents
TypeScript SDK for stateful AI agents running on Cloudflare Durable Objects
- 5.9k
AReaL
Asynchronous reinforcement learning system for training LLM agents
- 6.4k
AutoHedge
Multi-agent LLM pipeline that analyzes markets and trades on Solana
- 8.2k
Vision Agents
Python framework for real-time voice and video AI agents
- 8.3k
FinRobot
Multi-agent LLM framework and desktop app for equity research
8.5k
- 8.7k
Monty
Python interpreter in Rust for safely running LLM-generated code
- 8.9k
Strands Agents
Open-source Python and TypeScript toolkit for writing AI agents
- 5.5k
AI Data Science Team
Python agents that load, clean, chart, and model data for analysts
- 8.4k
MiroThinker
Open-weight deep research agent models with a tool-using search framework
- 9.7k
Cloudflare Computer
Durable virtual filesystem and execution sandbox for AI agents on Workers
- 11.2k
Tambo
React toolkit for agents that render your own components as replies
- 11.5k
e2e
End-to-end test framework where an AI agent drives web and mobile apps
