工具说明为英文。
技术工具雷达: Agents, skills and MCP
雷达筛选条件
工具排名
按实测增长排序,并在不同来源间归一化。 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。
- 1活跃
Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
github实测增长打开来源 ↗
2 791GitHub 星标+659 (+30.9 %) - 2活跃
OpenBot
智能体Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
github实测增长打开来源 ↗
3 622GitHub 星标+699 (+23.9 %) - 3活跃
genoffice
智能体Free, open-source AI office suite for macOS, Windows & Linux — Word (.docx), Excel (.xlsx), PowerPoint (.pptx), PDF and Markdown editing with built-in AI agents.
github实测增长打开来源 ↗
4 110GitHub 星标+406 (+11.0 %) - 4活跃
OmniRoute
智能体Never stop coding. Free MIT AI gateway: one endpoint, 350 providers (90+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback,…
github实测增长打开来源 ↗
58 715GitHub 星标+3 424 (+6.2 %) - 5活跃
img2threejs
智能体Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
github实测增长打开来源 ↗
14 598GitHub 星标+789 (+5.7 %) - 6204 990GitHub 星标+9 289 (+4.7 %)
- 79 444GitHub 星标+388 (+4.3 %)
- 8100 079GitHub 星标+2 746 (+2.8 %)
- 9活跃
KiroCrew
智能体A persistent workspace for development work that self-improves and continues beyond one session.
github实测增长打开来源 ↗
3 499GitHub 星标+238 (+7.3 %) - 10活跃
firecrawl
智能体The context API to search, scrape, and interact with the web at scale. 🔥
github实测增长打开来源 ↗
174 906GitHub 星标+2 497 (+1.4 %) - 11活跃
browser-use
智能体🌐 Make websites accessible for AI agents. Automate tasks online with ease.
github实测增长打开来源 ↗
111 878GitHub 星标+1 349 (+1.2 %) - 12活跃
omnigent
智能体Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
github实测增长打开来源 ↗
9 566GitHub 星标+285 (+3.1 %) - 13239 083GitHub 星标+2 588 (+1.1 %)
- 14活跃
ECC
智能体The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
github实测增长打开来源 ↗
245 322GitHub 星标+2 085 (+0.86 %) - 15活跃
ragflow
智能体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
github实测增长打开来源 ↗
89 772GitHub 星标+519 (+0.58 %) - 16活跃
crm
智能体Comp AI CRM is an open source, CRM designed for AI agents. Agentic-first CRM.
github实测增长打开来源 ↗
9 167GitHub 星标+231 (+2.6 %) - 1765 400GitHub 星标+338 (+0.52 %)
- 18145 386GitHub 星标+389 (+0.27 %)
- 19活跃
dsh-routing-suite — injector + router-standard kit: install the runtime injector first, then the task-aware reasoning-mode router preset (measured P1-P23).
github实测增长打开来源 ↗
6 977GitHub 星标+158 (+2.3 %) - 20活跃
Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent:每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐,由你自己的 Agent 驱动投资研究。基于开源的 Codex Harness 打造。
github实测增长打开来源 ↗
2 280GitHub 星标+99 (+4.5 %) - 21活跃
deer-flow
智能体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.
github实测增长打开来源 ↗
81 191GitHub 星标+297 (+0.37 %) - 22活跃
langflow
智能体Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
github实测增长打开来源 ↗
153 998GitHub 星标+314 (+0.20 %)
学习与参考资源
按实测增长排序,并在不同来源间归一化。 这些资源可单独访问,不参与主要排名。
- 151 638GitHub 星标+2 509 (+5.1 %)
- 2活跃打开来源 ↗
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
github资源实测增长75 687GitHub 星标+384 (+0.51 %) - 3活跃打开来源 ↗
Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS.
github资源实测增长128GitHub 星标+24 (+23.1 %)