Ross ROSS = Recommend OSS · open-source software intelligence for agents

eigent-ai/eigent

Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex observed · 2026-10-13

github.com/eigent-ai/eigent · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-10-13

Health v2 · maintenance only

85/100

  • Activity 99
  • Release rhythm 96
  • Longevity 32
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: 7
  • age_days: 448
  • days_rel: 25
  • days_push: 8
  • n_releases_24m: 36

Full methodology

Adoption not part of the score

15506 stars · 1851 forks observed · 2026-10-13

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Eigent is an open-source desktop application for building and running AI agent workforces that automate complex multi-step workflows. Built on CAMEL-AI, it supports single-agent or multi-agent parallel execution, MCP and skill integration, browser and terminal toolkits, and local deployment with any model.

Use cases

  • automate multi-step research and report generation with AI agents
  • run a multi-agent workforce to parallelize complex tasks
  • open-source alternative to Claude Cowork for desktop AI agents
  • orchestrate browser automation and terminal tasks with agents
  • build custom AI workers with domain-specific skills and MCP tools
  • keep agent work local and private with my own API keys or local models
  • automate enterprise workflows like CRM and ERP tasks with agents

When to choose

  • you want a free, open-source desktop AI agent app you can self-host
  • you need multi-agent parallel execution with human-in-the-loop checkpoints
  • you want model-agnostic agents with MCP and skill/toolkit integration
  • you prefer local deployment for privacy over cloud-only agent products

When to avoid

  • you need a lightweight headless agent framework embedded in your own codebase
  • you require fully hands-off autonomous agents without human oversight
  • you only need a simple chatbot without tool use or workflow automation

Facets

application · maturity active

agent-framework workflow-automation chat-interface mcp web-scraping artificial-intelligence large-language-models developer-tools self-hosted cross-platform windows multi-agent cowork camel-ai desktop-agent human-in-the-loop model-agnostic local-deployment agentic-workflow open-source ai-agents automation desktop macos linux nodejs

5 sources

Member repositories

RepositoryRoleHealth v2
eigent-ai/eigentmain85

For agents

markdown · JSON · MCP: product_card(name="eigent-ai/eigent")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem