AI Worker worker.md

AI Worker Registry (Prototype)

This is a prototype marketplace layer for worker.md. It indexes public projects and normalizes metadata so teams can compare projects quickly.

Each entry includes source attribution, update signals, and a compatibility note for worker-style bounded execution.

Market snapshot#

Entries50
Total stars231,605
Last verified2026-03-01
Data sourceGitHub seed

Top categories: Tool registry (20), Agent framework (18), Automation platform (9), Agent platform (3).

Entries#

  • BettaFish

    微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

    Agent framework 40,156 stars Python Worker-compatible

  • activepieces

    AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

    Tool registry 21,574 stars TypeScript Worker-compatible

  • openfang

    Open-source Agent Operating System

    Tool registry 16,251 stars Rust Worker-compatible

  • pydantic-ai

    AI Agent Framework, the Pydantic way

    Agent framework 16,100 stars Python Worker-compatible

  • eigent

    Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity. Local and Free Alternative to Claude Cowork.

    Automation platform 13,422 stars TypeScript Worker-compatible

  • waoowaoo

    首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.

    Automation platform 10,817 stars TypeScript Needs adapters

  • hive

    Outcome driven agent development framework and runtime harness

    Automation platform 10,041 stars Python Worker-compatible

  • agent-framework

    A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

    Automation platform 8,772 stars Python Worker-compatible

  • MiroThinker

    MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.

    Agent framework 8,193 stars Python Worker-compatible

  • Upsonic

    Agent Framework For Fintech and Banks

    Tool registry 7,820 stars Python Worker-compatible

  • intentkit

    IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

    Agent framework 6,499 stars Python Worker-compatible

  • rllm

    Democratizing Reinforcement Learning for LLMs

    Automation platform 5,376 stars Python Worker-compatible

  • Integuru

    The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

    Automation platform 4,565 stars Python Needs adapters

  • youtu-agent

    A simple yet powerful agent framework that delivers with open-source models

    Agent framework 4,497 stars Python Worker-compatible

  • ag2

    AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

    Tool registry 4,359 stars Python Worker-compatible

  • open-multi-agent

    TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js runs.

    Agent framework 4,285 stars TypeScript Worker-compatible

  • wanwu

    China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, an...

    Tool registry 4,243 stars Go Worker-compatible

  • FedML

    FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o...

    Agent platform 4,029 stars Python Needs adapters

  • fast-agent

    Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support

    Tool registry 3,737 stars Python Worker-compatible

  • ii-agent

    II-Agent: a new open-source framework to build and deploy intelligent agents

    Agent framework 3,283 stars Python Worker-compatible

  • Acontext

    Agent Skills as a Memory Layer

    Agent platform 3,265 stars TypeScript Needs adapters

  • BotSharp

    AI Multi-Agent Framework in .NET

    Agent framework 3,039 stars C# Worker-compatible

  • gitagent

    A framework-agnostic, git-native standard for defining AI agents

    Agent framework 2,525 stars TypeScript Worker-compatible

  • ouroboros

    Stop prompting. Start specifying.

    Tool registry 2,032 stars Python Worker-compatible

  • agentic_security

    Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

    Agent framework 1,839 stars Python Worker-compatible

  • Agently

    [GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven F...

    Agent framework 1,548 stars Python Worker-compatible

  • better-agents

    Standards for building agents, better

    Tool registry 1,506 stars TypeScript Worker-compatible

  • paperdebugger

    A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

    Tool registry 1,434 stars TypeScript Worker-compatible

  • zeroshot

    Your autonomous engineering team in a CLI. Point Zeroshot at an issue, walk away, and return to production-grade code. Supports Claude Code, OpenAI Codex, OpenCode, and Gemini CLI.

    Automation platform 1,393 stars JavaScript Worker-compatible

  • Director

    AI video agents framework for next-gen video interactions and workflows.

    Automation platform 1,345 stars Python Worker-compatible

  • AgentsMesh

    AgentsMesh — AI Agent Fleet Command Center. Orchestrate Claude Code, Codex CLI, Gemini CLI, Aider and more from a single platform.

    Agent platform 1,266 stars Go Worker-compatible

  • sre

    The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents acr...

    Tool registry 1,248 stars TypeScript Worker-compatible

  • AWorld

    Search, understand, reproduce, and improve an idea with ease

    Tool registry 1,171 stars Python Worker-compatible

  • agents

    Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

    Tool registry 1,052 stars TypeScript Worker-compatible

  • openops

    The batteries-included, No-Code FinOps automation platform, with the AI you trust.

    Tool registry 1,011 stars TypeScript Worker-compatible

  • tabularis

    A lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.

    Tool registry 945 stars TypeScript Worker-compatible

  • golf

    Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

    Tool registry 821 stars Python Worker-compatible

  • context-space

    Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

    Tool registry 810 stars Go Worker-compatible

  • ArcReel

    AI Agent 驱动的开源视频生成工作台 — 小说→角色/场景/道具设计→剧本→分镜图→视频，跨镜头角色与场景一致 | Open-source AI video workspace powered by AI Agents, Nano Banana 2 & Veo 3.1 / Grok / Seedance / OpenAI

    Agent framework 783 stars Python Worker-compatible

  • blades

    Blades is a Go-based multimodal AI Agent framework.

    Automation platform 749 stars Go Worker-compatible

  • voice-ai

    Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state m...

    Agent framework 708 stars Go Worker-compatible

  • agent-governance-toolkit

    AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

    Agent framework 672 stars Python Worker-compatible

  • LLMTornado

    The .NET library to build AI agents with 30+ built-in connectors.

    Tool registry 590 stars C# Worker-compatible

  • cordum

    The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.

    Tool registry 457 stars Go Worker-compatible

  • crabtalk

    Agents daemon that hides nothing

    Agent framework 433 stars Rust Worker-compatible

  • dat

    Asking yours data in a natural language way through pre-modeling (data models and semantic models).

    Tool registry 245 stars Java Worker-compatible

  • DashClaw

    🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.

    Agent framework 196 stars JavaScript Worker-compatible

  • AutoHarness

    AutoHarness: Automated Harness Engineering for AI Agents

    Agent framework 181 stars Python Worker-compatible

  • PolyMCP

    Polymcp provides a simple and efficient way to interact with MCP servers using custom agents

    Tool registry 165 stars TypeScript Worker-compatible

  • agent-skill-bus

    The missing runtime for Agent Skills — health monitoring, self-improvement, and dependency management for any AI agent framework. Zero dependencies.

    Agent framework 157 stars JavaScript Worker-compatible

See also#

FAQ#

Is this an endorsement list?

No. This registry is a discovery index. Treat entries as references and validate security, quality, and licensing before adoption.

How fresh is this metadata?

This prototype uses a seed dataset verified on 2026-03-01 and can be upgraded to scheduled GitHub sync.

Can this include standalone worker specs too?

Yes. The next step is ingesting AGENTS.md and SKILL.md manifests into the same normalized schema.