Stars
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
把Openclaw 变成小红书运营助手，帮你分析、选题、创作、复盘、复刻，甚至全面托管
omo; the best agent harness - previously oh-my-opencode
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
On-device AI across mobile, embedded and edge for PyTorch
"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"
STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.
Extend the capabilities of your CrewAI agents with Tools
[arxiv: 2503.23895] Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Model Context Protocol Servers
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
VijayRagaAI / agentneo
Forked from raga-ai-hub/RagaAI-CatalystAgent AI Application Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced anal…
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
A simple screen parsing tool towards pure vision based GUI agent
Powerful Mindmap Editing Tool
Java code commit impact, java code change impact analysis，java代码改动影响范围分析工具，精准测试，回归测试范围划定
Mobile-Agent: The Powerful GUI Agent Family
The official PyTorch implementation of Google's Gemma models
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
🔥 ShadowHook is an Android inline hook library which supports thumb, arm32 and arm64.
🔥🔥 btrace (AKA RheaTrace) is a high-performance Android & iOS tracing tool built on Perfetto. It not only times your methods but also reveals why they’re slow.