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

Simpleyyt/ai-manus

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment. observed · 2026-08-28

github.com/Simpleyyt/ai-manus · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

86/100

  • Activity 99
  • Release rhythm 97
  • Longevity 35
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 12
  • age_days: 494
  • days_rel: 21
  • days_push: 10
  • n_releases_24m: 16

Full methodology

Adoption not part of the score

1618 stars · 406 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AI Manus is a self-hostable, general-purpose AI Agent system with a WebUI that plans and executes tasks using tools like Terminal, Browser, File, and Web Search inside isolated Docker sandboxes. It requires only an LLM service for minimal deployment and supports MCP tool integration, session management via MongoDB/Redis, and real-time tool viewing and takeover.

Use cases

  • run an AI agent that browses the web and summarizes news
  • let an AI write and execute Python code in a sandbox
  • automate file conversions like images to jpg via chat
  • self-host an open-source Manus alternative
  • integrate custom MCP tools into an AI agent
  • run long-running background agent tasks with session history

When to choose

  • you want a self-hosted general AI agent with sandboxed code execution and browser control
  • you need minimal deployment dependencies (just an LLM service)
  • you want real-time visibility and takeover of agent tool usage
  • you need MCP tool integration and multi-session task management

When to avoid

  • you only need a simple chatbot without tool execution
  • you cannot run Docker locally for sandbox isolation
  • you need managed cloud agent infrastructure rather than self-hosting
  • you require Windows or mobile computer-use sandboxes, which are still on the roadmap

Facets

application · maturity active

agent-framework mcp chat-interface web-scraping self-hosted artificial-intelligence large-language-models self-hosted self-hosted python ai-agent sandbox browser-use terminal-use plan-and-execute manus-clone webui task-automation ai-agents automation docker web-server

2 sources

Member repositories

RepositoryRoleHealth v2
Simpleyyt/ai-manusmain86

For agents

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

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem