big-AGI

A multi-model AI chat suite for power users, known for Beam, which runs one prompt through several models and merges the best answers.

7.2k stars, 1.6k forks TypeScript On GitHub since March 2023

Visit website View on GitHub How to run it

What is big-AGI?

big-AGI is a web app for working with many models at once. Its Beam feature sends a prompt to several models in parallel and helps you compare and merge the results, which reduces hallucinations. It also has AI personas, voice input and output, text-to-image, code highlighting and execution, PDF import and developer presets. Chats are stored locally in your browser, and you can self-host it or use the hosted version.

Good fit if

  • You regularly compare answers from different models before trusting one.
  • You want a fast personal interface that keeps data in the browser.

Look elsewhere if

  • You need multi-user accounts and permissions: LibreChat.
  • You want an assistant that lives in your chat apps: OpenClaw.

Before you adopt it

big-AGI is MIT-licensed. Its author, Enrico Ros, funds development with a Pro subscription for the hosted service, and he writes nearly all of the code.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

big-AGI health: is it still maintained?

71 of 100, actively developed

  • Activity
    653 commits in the last 90 days, the latest on 31 October 2026.
    30 / 30
  • Contributors
    2 people wrote the latest 100 commits; the most active wrote 99% of them.
    4 / 20
  • Releases
    8 releases in the last 12 months; the latest, v2.1.3, on 27 October 2026.
    17 / 20
  • Replies to issues
    Maintainers answered 72% of recent issues, with a median first reply after 3 days.
    15 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

big-AGI license: is it open source?

big-AGI uses MIT, an open-source license approved by the OSI.

  1. March 2023First published on GitHub.
  2. TodayMIT.

How to run big-AGI yourself

Docker
Dockerfile or compose file in the repository
Compose file
docker-compose.yaml: 1 service
Setup effort
1 of 5, judged from the compose file
Kubernetes
No Helm chart in the repository
Desktop and mobile
No app builds in GitHub releases
Interface languages
English only

Install instructions: big-agi.com or the README on GitHub.

Alternatives to big-AGI

  • LibreChatEnhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API,… 74 health · MIT · 46.6k stars
  • Cherry StudioYour AI workspace for models, agents, and productivity. 81 health · AGPL-3.0 · 53.2k stars
  • ChatboxPowerful AI Client 79 health · GPL-3.0 · 42.2k stars
  • AnythingLLMStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first… 94 health · MIT · 67.8k stars
  • RAGFlowRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG… 93 health · Apache-2.0 · 93.3k stars

All 36 projects in AI chat & local LLMs

Questions about big-AGI

Is big-AGI open source?

Yes. big-AGI is published under MIT, an OSI-approved open-source license.

Is big-AGI still maintained?

Its health score is 71 of 100 (actively developed). It had 653 commits in the last 90 days, the latest on 31 October 2026, and its latest release came out on 27 October 2026.

How do I run big-AGI?

You can run it with Docker. The README on GitHub has the exact steps.

What are the alternatives to big-AGI?

Close alternatives in the AI chat & local LLMs category include LibreChat, Cherry Studio, Chatbox.