Stars
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.
📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.
An alignment auditing agent capable of quickly exploring alignment hypothesis
External storage tool for Letta agents to manage persistent notes
SkyRL: A Modular Full-stack RL Library for LLMs
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
Our library for RL environments + evals
Post-training with Tinker
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Open-source, self-hosted note-taking tool built for quick capture. Markdown-native, lightweight, and fully yours.
A benchmark for LLMs on complicated tasks in the terminal
An LLM leaderboard for stateful agents
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
DeepGEMM: clean and efficient BLAS kernel library on GPU
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Curso…
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Demo app for Groq plugins in LiveKit Agents
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework