RhythmicWave
★ 1,196NovelForge
AI辅助长篇小说创作，卡片式创作，支持基于 JSON Schema的结构化 AI 生成与上下文引用，可扩展性强。
AI 频道AI 智能体 
开源 AI 智能体
AI 智能体是一种用大模型决定下一步做什么的程序：它会调用浏览器、代码解释器或 API 等工具，反复执行，直到任务完成。这里的项目既有用来搭建自己智能体的框架，也有能写代码、浏览网页或运行业务流程的现成智能体。
怎么选
比较时看三点：能用哪些模型——只支持一家服务商，还是任何兼容 OpenAI 接口的端点（包括本地模型）；怎么限制智能体能做的事——沙箱、审批步骤、权限清单；以及它能否在步骤之间、会话之间保留记忆。会执行代码或命令行的智能体应该在沙箱里运行，给它访问你电脑的权限之前先确认这一点。
Star 最多的项目
第 409–426 个，共 426 个polterguy
★ 1,193magic
Instant SECURE Full Stack Apps and AI Agents
NVIDIA-NeMo
★ 1,189Gym
Evaluate and improve models and agents using environments
FunnyWolf
★ 1,181agentic-soc-platform
Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)
rudrankriyam
★ 1,181Foundation-Models-Framework-Lab
A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
AI-QL
★ 1,154tuui
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
zjunlp
★ 1,149LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
Rath-Team
★ 1,136OpenRath
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
massgen
★ 1,130MassGen
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
withkynam
★ 1,130vibecode-pro-max-kit
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
mrwadams
★ 1,123stride-gpt
An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.
vamplabAI
★ 1,118sgr-agent-core
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
agentlas-ai
★ 1,111Agentlas-OS
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Onelevenvy
★ 1,109flock
A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.
EmbeddedLLM
★ 1,103JamAIBase
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
tigicion
★ 1,084dao-code
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
raindrop-ai
★ 1,076workshop
Give your coding agent the power to write and run agent evals.
Deuz-AI
★ 988Deuz-SDK
Zero-dependency TypeScript framework for production AI agents: durable execution, long-term memory, hybrid RAG, MCP tool calling, human-in-the-loop approval, planning and CodeAct sandboxes. One streaming API for Claude, GPT, Gemini, Grok, Mistral and DeepSeek — Node, Bun, Deno, serverless and edge.