Marketplace Agen

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

Agentic RAG for any scenario. Customize sources, depth, and width

A Multi-Agent framework that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

Build, test, and deploy intelligent AI agents the Laravel way

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

A Text-Based Environment for Interactive Debugging

The specification for the Universal Tool Calling Protocol

📱 Terminal in Your Pocket — Control Claude Code, Codex, Gemini CLI & your Mac/Linux/Windows from any phone or browser. Vibe coding from anywhere. Alternative to MobileCLI, Claude Remote, vibe-remote, MuxAgent.

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

Design notes, architecture, and trade-offs for MyInvestPilot — an AI-native investment OS built with agent-driven development, DSL engine, and solo company tech stack.

Agent Framework Samples - showcasing ways in which agent framework can be utilized.

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

Mantis Hack

Deep Reinforcement Learning in C#

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

Give you decision-ready references for the most common AI engineering problems

Multi-Agent Collaboration Platform✨

ADE( Agentic Development Environment) The spec-driven environment for AI coding agents, where your planning becomes lasting, shared project context.

165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, learning science, curriculum, assessment and regeneration. Claude, Codex and Hermes.

ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to query data, fill out forms, and execute business tasks directly within OA, ERP, CRM, and other business applications.

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.