Lists (1)
Starred repositories
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Learn it. Build it. Ship it for others.
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
Use your most capable model to audit your codebase and write plans for cheaper models to execute.
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…
An LLM post-training framework with vLLM for RL Scaling
Open-source local workbench for multi-agent software development.
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
Drop-in replacement for `claude -p` that drives the interactive Claude Code TUI inside an in-process zmux PTY session.
Drop-in replacement for claude -p that runs on your Claude Code subscription instead of metered API pricing.
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Low-level unprivileged sandboxing tool used by Flatpak and similar projects
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Scalable, cloud-native infrastructure for evaluating AI agents across any benchmark.
A protocol that recasts the primary research object from narrative document to machine-executable knowledge package — so AI agents can navigate, reproduce, and extend published research without re-…
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
Paperclip — search, read, and analyze 8M+ biomedical papers from the command line
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
For adapters paper experiments (correlation study, traj analysis, etc.) and harbor mix selection.