Highlights
- Pro
Starred repositories
Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)
Securely generate API tokens for third-party access to your Tesla.
A self-hosted data logger for your Tesla 🚘 [main maintainer=@JakobLichterfeld]
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
Turn your coding agents into research agents
A decompilation of Super Smash Bros Melee brought to you by a bunch of clever folks.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Companion code for the global workspace interpretability paper
Agent skills for product engineers: count the clicks on your happy path, test flows against a UX budget, plan adoption, instrument analytics, and design and read A/B tests. For Claude Code, Codex a…
A CLI tool to switch and manage Codex accounts
Open source app to control jailbroken 8 sleep pods on LAN
An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill
Make Any Website into CLI & Use your logged-in browser by AI agent.
Let Claude Code, Codex or Cursor use your real Chrome, logged in as you. One prompt to set up. Open source, MIT.
A Git-compatible VCS that is both simple and powerful
living document for Claude Code system prompt
why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.
A modern, browser-based viewer for your Tesla dashcam footage. Play all six camera angles (Front, Back, Left, Right, Left B-Pillar, Right B-Pillar) simultaneously with a sleek and intuitive interfa…
Python tool for converting files and office documents to Markdown.
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
AI agents running research on single-GPU nanochat training automatically
ATLAS by General Intelligence Capital — Self-improving AI trading agents using Karpathy-style autoresearch