agent-tasks

by keshrath · AI Agent Frameworks · ★ 22

agent-tasks is an MCP server by keshrath. Pipeline-driven task management for AI coding agents — stages, dependencies, artifacts, and multi-agent collaboration. It has 22 GitHub stars and ranks #409 of 604 in AI Agent Frameworks by stars.

Category: AI Agent Frameworks
Author: keshrath
GitHub stars: 22
This week: Tracking since 19 Oct 2026
Weekly downloads: 110
Language: TypeScript
License: MIT (open source)
Last update: 2026-10-01 (23 days ago)
Links: Source Website npm

ai-agents
claude-code
collaboration
kanban
mcp
mcp-server
pipeline
real-time
sqlite
task-management
typescript
websocket
+1 more

How to install agent-tasks

agent-tasks is published on npm as agent-tasks, and it is listed in the official MCP Registry. These steps assume it runs as a local stdio server, which is the usual setup.

Check the README. Confirm the start command and note any API keys or environment variables it needs (pass them with -e KEY=value or an env block). You need Node.js for npx.

Add it to Claude Code from a terminal:

claude mcp add agent-tasks -- npx -y agent-tasks

Or add it to Cursor or Claude Desktop in .cursor/mcp.json or claude_desktop_config.json:

{
  "mcpServers": {
    "agent-tasks": {
      "command": "npx",
      "args": [
        "-y",
        "agent-tasks"
      ]
    }
  }
}

Restart the client and check it. Run claude mcp list, or open the client's MCP settings, and confirm agent-tasks and its tools are listed. The install guide covers VS Code and Codex.

Also listed in

Maintain this project? Get it featured ($99/mo, pinned at the top of AI Agent Frameworks) or see what featuring includes.

Report a problem with this listing

Frequently asked questions

What is agent-tasks?

agent-tasks is an MCP server by keshrath in the AI Agent Frameworks category. Pipeline-driven task management for AI coding agents — stages, dependencies, artifacts, and multi-agent collaboration. It has 22 GitHub stars and ranks #409 of 604 in AI Agent Frameworks by stars. It is written in TypeScript. It is licensed under MIT. It was last updated 23 days ago.

Is agent-tasks free and open source?

Yes. agent-tasks is published under the MIT license, so you can run, modify and self-host it at no cost. If it connects to a paid service, that service's own pricing and API terms still apply. Check the repository for the exact license text before using it commercially.

What are the alternatives to agent-tasks?

Other AI Agent Frameworks projects on MCP Harbor include paperclip, ruflo, oh-my-openagent. Each alternative links to its own page with stars, license and recent activity. The AI Agent Frameworks category ranks all 604 by stars, and you can re-sort it by growth this week.

Alternatives to agent-tasks

paperclipTrending★ 106,693

paperclipai · TypeScript+3,234 stars this week (+3.1%)

The open-source app everyone uses to manage agents at work

rufloTrending★ 78,856

ruvnet · TypeScript+2,953 stars this week (+3.9%)

🌊 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

oh-my-openagent★ 70,301

code-yeongyu · TypeScript+168 stars this week (+0.2%)

OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.

nanobot★ 49,318

HKUDS · Python+192 stars this week (+0.4%)

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

oh-my-claudecode★ 40,218

Yeachan-Heo · TypeScript+220 stars this week (+0.6%)

Teams-first Multi-agent orchestration for Claude Code

composio★ 30,714

ComposioHQ · TypeScript+106 stars this week (+0.3%)

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

All 604 AI Agent Frameworks MCP servers →

Data last updated 25 October 2026. Stars and downloads are refreshed every day from GitHub and npm.