# langroid/langroid

Harness LLMs with Multi-Agent Programming

Repository: https://github.com/langroid/langroid
Canonical: https://ross.abutalabs.com/products/langroid
Homepage: https://langroid.github.io/langroid/
Language: Python
License: MIT
License Family: permissive
Topics: agents, chatgpt, gpt, gpt-4, gpt4, language-model, llm, llm-agent, multi-agent-systems, openai-api, ai, llm-framework, llama, local-llm, function-calling, information-retrieval, rag, retrieval-augmented-generation
Last push: 2026-08-23T23:24:57+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 88
- inputs: {"age_days": 1235, "days_push": 10, "days_rel": 10, "gap_med": 0.0, "n_releases_24m": 283}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4102, forks 397 (observed 2026-08-28T04:08:35.563370+00:00)

## What it is
Langroid is a Python framework for building LLM-powered applications using multi-agent programming, where agents encapsulate LLM conversations, vector stores, and tools and collaborate by exchanging messages. It is inspired by the Actor model, works with practically any LLM, and does not depend on LangChain.

## Use cases
- build multi-agent LLM applications in python
- orchestrate llm agents that collaborate on tasks
- build a rag chatbot over my documents
- add function calling and tools to an llm app
- run agents with local llms like llama
- delegate tasks between multiple llm agents
- query a vector store with an llm agent

## When to choose
- you want agents as first-class citizens with principled multi-agent orchestration
- you need a lightweight, LangChain-free LLM framework
- you want to mix OpenAI, local, and other LLMs in one app
- you need built-in vector-store and tool/function-calling support

## When to avoid
- you only need a single LLM call with no agent structure
- you are already invested in LangChain or another ecosystem
- you need a no-code or non-Python solution

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, llm-inference, prompt-engineering, chatbot
- domain: large-language-models, developer-tools
- platform: python, cross-platform
- tags: multi-agent, llm-framework, actor-model, function-calling, vector-store, openai, ai-agents, retrieval-augmented-generation, natural-language-processing, docker

## Member repositories
- langroid/langroid (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.563370+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:15.977928+00:00, confidence not recorded.
  - readme: https://github.com/langroid/langroid (fetched 2026-08-28T04:08:35.563370+00:00, sha a860ca292c7a)
  - homepage: https://langroid.github.io/langroid/ (fetched 2026-08-29T09:14:48.786748+00:00, sha c797bfc21b2c)
- Data as of 2026-08-30T08:39:29.467469+00:00.