ai-manus

AI Manus is a general-purpose AI agent system that runs tools and operations in a sandbox.

github.com/Simpleyyt/ai-manus
ai-manus homepage screenshot

About ai-manus

AI Manus is an open-source, general-purpose AI agent system that runs tools and operations inside a sandbox environment, distributed as a repository on GitHub. Each task is allocated a separate sandbox that runs in a local Docker environment; a plan-and-execute agent loop submits plans and step results through native structured output tool calls rather than a JSON-in-prompt protocol, and supports terminal, browser, file, web search and messaging tools with real-time viewing and takeover, plus external MCP tool integration. Session history is managed through MongoDB/Redis and supports background tasks, and a sidebar Library aggregates attachments and artifacts across sessions with filters, search and preview. Deployment primarily relies on Docker, and the project states that minimal deployment requires only an LLM service, with no dependency on other external services.

Key features

  • Per-task sandbox running in a local Docker environment
  • Plan-and-execute agent loop using native structured output tool calls
  • Terminal, browser, file, web search and messaging tools with live takeover
  • Supports external MCP tool integration
  • Reusable skill packages from catalog, upload or GitHub, invoked by command
  • Session history in MongoDB/Redis with background task support
Best for: Developers and technical teams who want to self-host a general-purpose AI agent that executes tools inside an isolated local Docker sandbox.
Good for
  • Open source with Docker Compose files for development and deployment
  • Minimal deployment needs only an LLM service, with no dependency on other external services
  • Includes user login and authentication, plus Chinese and English support
Watch out for
  • Requires a relatively new Docker (20.10+) and Docker Compose
  • Requires a chat model provider with native tool or function calling; DeepSeek and GPT models with reliable tool calling are recommended
  • Mobile and Windows sandbox access, plus K8s and Docker Swarm deployment, are listed as roadmap items rather than finished features

ai-manus at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

ai-manus alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Agents & Automation

Well-known listings from the same topic.

All 313

ai-manus FAQ

What is required to run AI Manus?
The project relies on Docker for development and deployment and calls for Docker 20.10+ and Docker Compose. Model requirements include support for LangChain chat model providers (default OpenAI) and native tool or function calling, with DeepSeek and GPT models with reliable tool calling recommended.
Does AI Manus depend on external services?
The repository states that minimal deployment requires only an LLM service, with no dependency on other external services. Session history is managed through MongoDB/Redis and each task sandbox runs in a local Docker environment.
Which languages does the interface support?
AI Manus supports both Chinese and English.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing