智能体市场

为所有人准备的AI搞钱团队，帮你把经验和方法跑成一门生意。

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Browser Harness | Self-healing harness that enables LLMs to complete any task.

🖥️ Run AI Agent in your browser.

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

Make Any Website into CLI & Use your logged-in browser by AI agent.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Vane is an AI-powered answering engine.

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

18 Lessons to Get Started Building AI Agents

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

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

Agents that use the browser.

The context API to search, scrape, and interact with the web at scale. 🔥

The agent engineering platform.

The agent that grows with you

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.