Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

The Comprehensive Toolkit for Embodied AI Models

Memory control plane for AI Agents in 6 lines of code

Build Real-Time Knowledge Graphs for AI Agents

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.

Universal memory layer for AI Agents

OpenClaw-RL: Train any agent simply by talking

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

UI-Venus is a native UI agent designed to perform precise GUI element grounding and effective navigation using only screenshots as input.

[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

[COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents

🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

Causal depthwise conv1d in CUDA, with a PyTorch interface

🚀 Efficient implementations for emerging model architectures

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

Awesome-Low-Rank-Adaptation

This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding code links.

Supercharge Your LLM with the Fastest KV Cache Layer

Dynamic Memory Management for Serving LLMs without PagedAttention

A Datacenter Scale Distributed Inference Serving Framework

Code for data-aware compression of DeepSeek models

Code repo for efficient quantized MoE inference with mixture of low-rank compensators

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

[ICLR 2025, IEEE TPAMI 2026] Mixture Compressor & MC#

Official implementation of Half-Quadratic Quantization (HQQ)

🔥🔥Android上将bilibili缓存视频合并导出为mp4，支持安卓5.0 ~ 13，视频挂载弹幕播放(Android consolidates and exports the bilibilibili cache video to mp4, supports Android 5.0~13, and plays the video on the screen)

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

A command-line installer for Windows.