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
- 2.2k
SIA
Self-improvement loop that rewrites an AI agent to score higher on a benchmark
AL3k
- Antoine2.3k
forge
Reliability layer that makes local LLM tool calls succeed more often
- hope3.5k
Oh My Hermes
Plugin that adds workflows, memory, and model routing to Hermes Agent
- 3.7k
Letta Code
Terminal agent harness with persistent memory that learns over time
- 3.8k
VulnClaw
AI agent that runs authorized penetration tests from plain language
- Jordan Gibbs3.9k
Hyperresearch
Deep research pipeline that runs inside Claude Code or Codex
- 3.4k
Switchyard
Per-request model routing for AI agents across cheap and capable LLMs
- Nico Bailon4k
pi-subagents
Subagent delegation extension for the Pi coding agent
- 5.3k
AIPOCH Open-Science
Local-first AI workbench for running reproducible research projects
- 6.4k
LoopX
Local-first control plane for long-running coding and research agents
- 5.9k
Apache Maka
Local-first agent workspace that logs every model call and tool action
- 7.1k
Talk to Figma MCP
MCP server and Figma plugin that let AI agents read and edit designs
- Craig7.5k
SEO Machine
Claude Code workspace for researching and writing SEO blog posts
- Mike Schwarz8k
OpenRig
Run persistent teams of Claude Code and Codex agents from YAML
8k
- 6.4k
AutoHedge
Multi-agent LLM pipeline that analyzes markets and trades on Solana
8.5k
7.3k
- 8.7k
Evolver
CLI engine that turns agent run logs into auditable, reusable prompt assets
- 8.9k
Strands Agents
Open-source Python and TypeScript toolkit for writing AI agents
- Alex Yang7.5k
Pi Web
Local browser interface for the pi coding agent's sessions and settings
- 9.8k
Mobile Next
MCP server that lets AI agents drive iOS and Android apps and devices