The best agent harness.

AI Agent Memory System inspired by Neuroscience

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

Agent skills for Obsidian. Teach your agent to use Markdown, Bases, JSON Canvas, and use the CLI.

An open-source alternative to Claude Cowork built for teams, powered by opencode

Chrome DevTools for coding agents

EvoCUA: Evolving Computer Use Agent

omo; the best agent harness - previously oh-my-opencode

Programs for producing static call graphs for Java programs.

Unified Policy as Code

LLM-Check: Investigating Detection of Hallucinations in Large Language Models (NeurIPS 2024)

🚀 PR Agent - The Original Open-Source PR Reviewer. This repo is not the Qodo free tier! Try the free version on our website.

Declarative Continuous Deployment for Kubernetes

Test Kitchen is an integration tool for developing and testing infrastructure code and software on isolated target platforms

The AI Browser Automation Framework

集成midscene.js的playwright项目，AI 带来愉悦的 UI 自动化体验。

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

A library for evaluating Retrieval-Augmented Generation (RAG) systems (The traditional ways).

Automated Evaluation of RAG Systems

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Enable network mocks and more in UI Tests