Stars
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
A PyTorch native library for training speculative decoding models
The simplest, fastest repository for training/finetuning medium-sized GPTs.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Hierarchical Reasoning Model Official Release
Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get interview prep and an appli…
Slow-Fast Inference: Training-free Inference Acceleration via Within-sentence Support Stability
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
OpenClaw-RL: Train any agent simply by talking
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.
中文自然语言处理工具包 Toolkit for Chinese natural language processing
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Apache Beam is a unified programming model for Batch and Streaming data processing.
🙌 OpenHands: AI-Driven Development
AI companions with memory: a lightweight stack to create and host your own AI companions
🚀 Efficient implementations for emerging model architectures
MiniMax-M2, a model built for Max coding & agentic workflows.