Search

AI-powered design assistant using Claude's multi-agent architecture. 7 specialized agents for UI/UX reviews, accessibility audits, and design system guidance.

An AI Agent tool to automate Android devices reliably

AI agent governance framework with audit trails, safety checks, and replayable decision making for autonomous systems

🌐 An open, standardized three-layer enterprise ontology framework for knowledge graphs, semantic layers, master data management, and AI Agent knowledge bases.

Full-stack AI chat platform with streaming SSE, multi-turn sessions, and PostgreSQL persistence including pgvector. Backend: FastAPI, SQLModel, Alembic, and MCP tools for Context7, weather, web search, and code execution. Frontend: React 19, TypeScript, Ant Design, Redux Toolkit, and Vite+. SMS or WeChat login with JWT. Docker Compose supports loca

Nebula-Copilot 是一个面向值班与排障场景的智能 CLI 工具，支持 Trace 诊断、瓶颈定位、异常归因与可执行建议输出，并结合了 Agent Tool Calling 与知识库增强排障。

一个面向学习与个人实战的本地优先 Coding Agent 框架：内置 Flow 编排、MCP、Skill、RAG、CLI/RPC/Web UI，帮你从 0 到 1 搭建自己的 AI 编码助手。Local-first coding agent framework for learning and personal use. Build your own AI coding assistant with Flow nodes, MCP, Skills, RAG, CLI, RPC, and Web UI.

A Model Context Protocol (MCP) server for Mount & Blade II: Bannerlord. Gives AI agents access to decompiled source search, XML data browsing, gameplay queries, local mod source indexing, and patch generation tools.为《骑马与砍杀2：霸主》打造的 MCP 服务器，支持源码检索、XML 数据查询、玩法数据浏览、本地 Mod 源码索引与补丁辅助生成。

An Agent Harness crafting around your project. From Desktop, CLI, editors, chatbots, APIs — everywhere you work.

An open-source agent harness framework for building, hosting, and orchestrating tool-using AI agents.

A governance-first multi-agent framework that treats agents as an organization, not just a router.

Governance-first, agent-based AI framework that models how real software teams think, decide, and ship.

No description available

NIYOJAN is an end-to-end AI-powered planning platform that transforms demand forecasts into actionable business decisions. It combines machine learning–based forecasting, agentic AI workflows, and retrieval-augmented reasoning to generate intelligent insights and automated reports, powered by a FastAPI backend and a React-based frontend.

从零实现四种 LLM Agent 范式：ReAct / Plan-and-Solve / Reflection + 综合案例：电商客服智能体

✊ Let your agent grind 24x7 fully autonomously

Multi-agent AI debate engine. 4 LLMs debate any topic via OpenRouter. Structured rounds, adversarial scoring, final report with confidence rating.

Intelligent LLM agent cost optimization runtime — semantic caching + graduated budget enforcement

Autonomous debugging engine — trace-to-code correlation via AST analysis and LLM synthesis

CLI tool for AI agents to manage tasks on BotBoard