Highlights
- Pro
Stars
An enterprise friendly way of detecting and preventing secrets in code.
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model thro…
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
Framework for evaluating and improving agents
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
AI agents running research on single-GPU nanochat training automatically
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
FlashInfer: Kernel Library for LLM Serving
An Open-Source Asynchronous Coding Agent
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
InternVL-U is a 4B-parameter unified multimodal model (UMM) that brings multimodal understanding, reasoning, image generation, image editing into a single framework.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Agent harness to publish your agent chat history as Huggingface datasets.
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
ZeroGUI: Automating Online GUI Learning at Zero Human Cost
Implementation for "The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"