Stars
An Open Source template for a proactive AI agent that gets your work done and keeps you in the loop.
Open-source plugin for designing and reviewing software with agents
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
Open-source generative UI framework: agents stream layout data, and apps render it with native components in React, Angular, Lit, Flutter, SwiftUI and Jetpack Compose.
The official command-line interface for interacting with A2A (Agent2Agent) compatible agents.
Framework for evaluating and improving agents
Removes 20+ patterns of AI slop from any piece of writing.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…
Algorithm powering the For You feed on X
The World's First Virtual Terminal for AI Agents
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
An open-source database of AI models.
#1 Persistent memory for AI coding agents based on real-world benchmarks
Open-source construction ERP - BOQ, PDF/CAD/BIM takeoff, AI cost matching, 293 guided cases. 120,000+ priced positions, 44 languages, 190+ modules, cost data for 40+ markets. AGPL-3.0. pip install …
Ministack: Free, open-source local AWS emulator - 60+ services, Terraform compatible, real databases. Free forever. MIT licensed.
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Archived — ML Intern is no longer maintained. Continue with HuggingChat.
The open agent skills tool - npx skills
📝A simple and elegant markdown editor, available for Linux, macOS and Windows.
An interface library for RL post training with environments.
😎 A list of awesome Computer-Aided Design (CAD) papers
RL environments + evals for AI agents. Define once, train anything.
An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
Multi-tenant fine-tuning for LLMs with Tinker-compatible API
Textbook on reinforcement learning from human feedback
Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.