v2.0.0

enricoros/big-AGIv2.0.0Oct 28, 2025by enricoros

AI Summary

Major 2.0 release with Beam 2 multi-modal intelligence, professional features including reasoning models and web search, local-first redesign, and introduction of three-tier model (Open, Free, Pro) with cloud sync.

Key Highlights

  • Beam 2: Multi-modal reasoning across multiple models simultaneously
  • Professional reasoning models (Claude Opus 4.1, Gemini 2.5 Pro, GPT-5/o3/o1, Grok 4)
  • Native web search with citations
  • Image generation with Nano Banana and gpt-image-1
  • Local FileSystem integration with drag/drop and diff support

New Features

  • Beam 2 multi-modal intelligence
  • Web search with citations
  • Image generation and editing
  • Local FileSystem integration
  • Cloud Sync for Pro users (1GB storage, unlimited devices)
  • UI completely overhauled for desktop and mobile
  • Local-first redesign with zero latency
  • Three-tier model: Open, Free, and Pro

Full Release Notes

# 🚀 Big-AGI 2.0.0 - **Open**, **Free** and **Pro**

### A year in the making, redesigned for professionals.

**Big-AGI 2.0** is here. More than an update; we've rebuilt core components, massively improved the UI, and are officially launching the three-tier model to support the project's next phase.

Built for **Engineers** architecting systems, **Founders** making decisions, **Researchers** validating hypotheses, and IT departments deploying the top value to their company, and after **thousands of hours of engineering**, we're delivering what you asked for: a professional-grade AI workspace that's local-first, vendor-neutral, and madly optimized for zero latency.

<img width="1792" height="1024" alt="release-cover-v2 0 0" src="https://github.com/user-attachments/assets/35ea95cf-896e-403f-bfe4-3aca59fd11a1" />

## What's New

### **Beam 2: Multi-Modal Intelligence**
Program-based reasoning across multiple models simultaneously, with **images**, **follow-ups**, and **saved presets**.

### **Professional Features**
- **Reasoning Models**: Anthropic Claude Opus 4.1, Gemini 2.5 Pro, OpenAI GPT-5/o3/o1, xAI Grok 4, etc.
- **Web Search** native and with citations for supported models
- **Image Generation** with Nano Banana and gpt-image-1, including edits
- **Local FileSystem** integration: drag/drop files to add context, diff them, and save them back, automatically
- UI completely overhauled for desktop and mobile

### **Cloud Sync (Pro Only)**
10 months of solo engineering. Real-time sync across unlimited devices, 1GB storage. Your data, your control.

### **Technical Improvements**
- **Local-first redesign**: Everything runs in your browser when possible. Zero latency. No vendor lock-in.
- **Multi-part/multi-modal** almost every subsystem has been redesigned and drastically improved
- And plenty more - see the latest on [big-agi.com/changes](https://big-agi.com/changes)

### Three Tiers
- **Big-AGI Open** (self-host): First to get new models. Maximum control. IT departments love it.
- **Big-AGI Free** (big-agi.com): Full core experience with Beam, Personas, and the best UX
- **Big-AGI Pro** (from $10.99/mo): Everything + **Cloud Sync** across unlimited devices with 1GB storage

As an independent, non-VC-funded project, Pro subscriptions fund all development including the free and open-source tiers.

<a href="https://big-agi.com">
  <img width="210" height="68" alt="image" src="https://github.com/user-attachments/assets/b2f8a7b8-415f-4c92-b228-4f5a54fe2bdd" />
</a>  

### Inception Screenshot
<img width="2116" height="1274" alt="image" src="https://github.com/user-attachments/assets/dcd3811d-8993-4827-8e25-f7c47929dbb9" />


## New Contributors
Welcome and thank you to our 12 new contributors who made their first contributions to Big-AGI! Your code is now part of something professionals worldwide rely on daily.

* @powyncify made their first contribution (UI improvements) in https://github.com/enricoros/big-AGI/pull/830
* @sam0jones0 made their first contribution (Claude thinking models) in https://github.com/enricoros/big-AGI/pull/811
* @darthalex2014 made their first contribution (multi-key support) in https://github.com/enricoros/big-AGI/pull/777
* @Jonathan523 made their first contribution (Gemini custom endpoints) in https://github.com/enricoros/big-AGI/pull/716
* @jayrepo made their first contribution (Docker SSL fixes) in https://github.com/enricoros/big-AGI/pull/706
* @matrix303 made their first contribution (Docker Node 22) in https://github.com/enricoros/big-AGI/pull/695
* @darshmashru made their first contribution (documentation fix) in https://github.com/enricoros/big-AGI/pull/629
* @mapringg made their first contribution (DeepSeek vendor + Mac shortcuts) in https://github.com/enricoros/big-AGI/pull/580
* @therippa made their first contribution (Personas panel fix) in https://github.com/enricoros/big-AGI/pull/575
* @JeremiLorenti made their first contribution (DALL-E settings) in https://github.com/enricoros/big-AGI/pull/572
* @blakkd made their first contribution (LocalAI URL fix) in https://github.com/enricoros/big-AGI/pull/570
* @pichuang made their first contribution (Kubernetes support) in https://github.com/enricoros/big-AGI/pull/152

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v1.16.8...v2.0.0

## For Institutions
Need shared prompts, SSO, or managed deployments? Contact enrico@big-agi.com - we're actively building enterprise features based on research group requirements.

## In Summary
Big-AGI 2.0 represents our commitment to building the AI workspace that experts deserve. No compromises on speed, no vendor lock-in, no BS. Just a powerful tool that works exactly how you need it to.

As an independent, non-VC-funded project, Pro subscriptions directly fund all development. Early subscribers shape the roadmap.

**Upgrade today** via [big-agi.com](https://big-agi.com), Docker, or self-host from source.