enricoros/big-AGI
AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud. observed · 2026-08-28
Health v2 · maintenance only
93/100
- Activity 99
- Release rhythm 86
- Longevity 90
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: 49.5
- age_days: 1263
- days_rel: 12
- days_push: 7
- n_releases_24m: 7
Adoption not part of the score
7102 stars · 1595 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Big-AGI is an open-source AI workspace web application that lets users chat with many state-of-the-art LLM providers (OpenAI, Anthropic, Gemini, xAI, local models via Ollama, and more) using their own API keys. It offers advanced features like Beam multi-model parallel chats, AI personas, text-to-image, voice, PDF import, and can be self-hosted via Docker or Vercel.
Use cases
- chat with multiple LLMs side by side and compare answers
- self-host a private ChatGPT alternative with my own API keys
- run one prompt across several models in parallel to catch hallucinations
- chat with local models through Ollama or LM Studio
- generate images and use voice within an AI chat workspace
- import PDFs and ask questions about them
- avoid vendor lock-in with a multi-provider AI interface
- deploy an AI chat UI for my team on-prem or in the cloud
When to choose
- you want a polished, self-hosted AI chat workspace with BYO API keys
- you need to compare or fuse responses from multiple models (Beam)
- you want broad provider support including local models like Ollama
- you need extras like personas, voice, image generation, and PDF import in one app
When to avoid
- you need a headless API or library to embed LLM calls in your own code
- you want a fully managed hosted service without managing keys or deployments
- you need fine-grained multi-user team administration and billing out of the box
Facets
application · maturity active
chatbot agent-framework llm-inference rag chat-interface image-processing speech-recognition tts pdf web-framework artificial-intelligence large-language-models chatbots self-hosted web-development self-hosted cross-platform cloud multi-model ai-workspace beam byo-api-keys openai anthropic gemini ollama text-to-image voice-chat personas vercel-deploy ai-agents web-server docker nodejs
4 sources
- readme: https://github.com/enricoros/big-AGI · fetched 2026-08-28 · f810af0f0230
- homepage: https://big-agi.com · fetched 2026-08-29 · 05e6f4bb3fd4
- site_page: https://big-agi.com/docs · fetched 2026-08-29 · 4f12a84b9f7f
- site_page: https://app.big-agi.com · fetched 2026-08-29 · 27a610ff71c8
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| enricoros/big-AGI | main | 93 |
For agents
markdown · JSON · MCP: product_card(name="enricoros/big-AGI")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem