Starred repositories
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
from vibe coding to agentic engineering - practice makes claude perfect
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
The agent that grows with you
AI agents running research on single-GPU nanochat training automatically
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
slime is an LLM post-training framework for RL Scaling.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
A community collection of OpenClaw use cases for making life easier.
The open agent skills tool - npx skills
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
IronClaw is an Agent OS focused on privacy, security and extensibility
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
GRID: Generative Recommendation with Semantic IDs
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
We write your reusable computer vision tools. 💜
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
Implementation for FP8/INT8 Rollout for RL training without performence drop.