Langroid

github.com/langroid/langroid AI Agent Frameworks Open-source projectOpen source

Langroid supports programming multi-agent systems with large language models.

github.com/langroid/langroid
Langroid homepage screenshot

About Langroid

Langroid is an open source Python framework for building LLM-powered applications with multiple agents. Developers create agents, optionally equip them with a language model, vector store, and tools or functions, assign tasks, and have agents exchange messages to solve a problem.

It supports function calling, structured information extraction, retrieval-augmented generation with DocChatAgent, SQLChatAgent, and connections to MCP servers through a tool adapter. It works with OpenAI and non-OpenAI local and remote models and does not use LangChain or another LLM framework.

Key features

  • Build Python agents equipped with LLM, vector-store and tools
  • Assign tasks for agents to collaborate via message exchange
  • Extract structured information from documents using multi-agent workflows
  • Use DocChatAgent for retrieval-augmented generation over documents
  • Connect agents to MCP servers via ToolMessage adapter
  • Work with OpenAI and non-OpenAI local or remote LLMs
Best for: Python developers building LLM applications that use multiple collaborating agents.
Good for
  • Open source Python framework
  • Works with practically any LLM, including local and remote options
  • Operates without requiring LangChain or another LLM framework

Langroid 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

Langroid alternatives

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

All 24 alternatives

Popular in AI Agent Frameworks

Well-known listings from the same topic.

All 75

Langroid FAQ

Does Langroid depend on LangChain?
No. It does not use LangChain or any other LLM framework.
Which language models can it use?
It works with practically any LLM, including OpenAI models and non-OpenAI local or remote models.
How are multi-agent workflows structured?
You set up agents with optional LLM, vector-store and tools, assign tasks, and agents exchange messages to solve a problem.
Is something wrong or out of date?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