# Big-AGI 2.1.0 - Weights Dust

### Six new vendors.

Cerebras, NVIDIA NIM, Sakana AI, Cohere, Modular and Nous Research, each with a setup guide. Plus model updates across Anthropic, OpenAI, Gemini, xAI, Moonshot and Z.ai, a multi-vendor transcription framework, explicit reasoning-effort and mode controls, and code sandboxes that persist across turns. 628 commits since 2.0.5.

<img width="1536" height="1024" alt="210-d4" src="https://github.com/enricoros/big-AGI/releases/download/v2.1.0/210-d4-FINAL.png">


### New Vendors
- **Cerebras** first-class vendor support, with live catalog and CSF (#1146) - [setup](https://big-agi.com/docs/connect-cerebras)
- **NVIDIA NIM** with a curated catalog and sync tooling - [setup](https://big-agi.com/docs/connect-nvidia-nim)
- **Sakana AI** on the Responses API: Fugu Cyber, Fugu Ultra 1.1, Namazu (#1142) - [setup](https://big-agi.com/docs/connect-sakana)
- **Cohere** model family, including Aya - [setup](https://big-agi.com/docs/connect-cohere)
- **Modular** with MiniMax M3, Kimi K2.7 Code and Gemma 4 - [setup](https://big-agi.com/docs/connect-modular)
- **Nous Research** Hermes models and the Portal subscription gateway, and **EmpirioLabs** (#1129), both via [custom endpoints](https://big-agi.com/docs/connect-custom-endpoints)

### Models
- Anthropic **Opus 5**, **Sonnet 5**, **Opus 4.8**, plus **Fable 5** and **Mythos 5**
- OpenAI **GPT-5.6** Sol/Terra/Luna, with Reasoning Mode (#1158) and Max effort (#1159)
- Google **Gemini 3.5 / 3.6 / 3.7 Flash**, **Nano Banana 2 Lite**, Robotics-ER 2, and 3.7 video understanding
- xAI **Grok 4.5**, **4.6** and **Grok Build 0.1**, with none/x-high efforts (#1104)
- Moonshot **Kimi K3**, and Kimi Code subscription keys (#1161)
- Z.ai **GLM-5.2 / 5.3**, Alibaba **Qwen 3.7 Flash**, **DeepSeek V4** Flash and Pro, **MiniMax M3**

### Transcription (New)
- Multi-vendor speech-to-text framework, with its own Settings section - [voice docs](https://big-agi.com/docs/feature-voice)
- **Deepgram** diarization, dictionaries, topic and sentiment detection, word-level spans
- **OpenAI** gpt-transcribe with keyword and language hints, and diarization
- Per-engine instances and profiles, sharing the config layout with Speech and Draw

### Sandboxes & Containers
- Anthropic: standalone **Code Sandbox** toggle, container re-attached across dynamic-web turns (#1087)
- OpenAI: **container files** as hosted resources - download, embed, sandbox-link interception; code execution downgrades to function calls when a container expires
- Gemini: **Omni**, video output, Antigravity agent events, and the Interactions protocol rewrite with usage metrics (#1143)

### Reasoning & Caching
- OpenAI Responses: reasoning phase (commentary vs final) and client-controlled policy, defaulting to all-turns on GPT-5.4+
- OpenRouter: reasoning on/off/default (#1138), Anthropic-style prompt caching via ephemeral breakpoints, session affinity
- Anthropic: reasoning token accounting, x-high auto-probing, cache breakpoints capped at the API limit (#623)
- Vertex AI redirect links resolved automatically or on demand (#1114)

### Reliability
- Multi-tab rewritten on Web Locks; demote-by-wipe replaces the old heuristic (#802)
- Warning that chats live in the browser and are lost on cache clear (#672)
- Auto-reload once on stale-deploy chunk load errors, and denoised error reporting
- Browser support floor enforced in lint, Intl.Segmenter fallback, tiktoken preload failures tolerated

### Also New
- **Draw**: OpenRouter image generation on the dedicated Image API, engine-instance settings
- Settings redesign, Diagnostics section, model assignments with per-domain Auto picks
- Token stats during generation, not just at the end (#1125)
- Markdown preview for .md fenced code (#1126), rendered ```svg blocks, Live-SVG
- Mobile wake lock, model-select search that keeps focus, attachment rename
- Removed: Helicone (maintenance mode), OpenPipe (discontinued), react-player

### Developers
- **AIX Protocol Lab**: protocol microscope and differential tester for the decode layer, alongside the [AI Inspector](https://big-agi.com/docs/feature-ai-inspector)
- Anthropic and Claude Code protocol eviscerators, standalone storage and diagnostics tools
- Per-vendor model-defs manifest with selective boot refresh: model updates no longer need an AIX roll
- Tests wired into CI, type-checking extended over tools/

## New Contributors
* @Adam-Dalloul made their first contribution in https://github.com/enricoros/big-AGI/pull/1130
* @mahirhir made their first contribution in https://github.com/enricoros/big-AGI/pull/1145
* @Robinnnnn made their first contribution in https://github.com/enricoros/big-AGI/pull/1156

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.5...v2.1.0

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.


Big-AGI 2.1.0: Weights Dust

# Big-AGI 2.0.5 - Roberto

> Named after my father, on his birthday.

### Resilience, persistence, excellence.

Long-running AI sessions get a serious upgrade. Anthropic Containers give you persistent files, Skills, and bash sessions that span turns. Gemini Deep Research is now fully resumable - reconnect after pauses, recover from server cuts, cancel cleanly. Add to that Opus 4.7 with 1M tokens, GPT-5.5, DeepSeek V4, and two new vendors.


<img width="1536" height="1024" alt="205-b" src="https://github.com/user-attachments/assets/11e6052a-6dc9-4ca4-9a65-aa7f6846790a" />


### Models
- **Anthropic Opus 4.7** with 1M token context, X-High effort, auto-detect features and 0-day models
- **OpenAI GPT-5.5** family with 1M context, plus **gpt-image-2** for image generation
- **DeepSeek V4** Flash and Pro with native thinking/reasoning_effort
- **Gemini 3.1 Flash**, 3.1 Flash Lite, 3.1 Flash TTS, Robotics-ER 1.6, and Gemma 4
- **xAI Grok 4.3** with encrypted reasoning and reasoning summaries
- **Moonshot Kimi K2.6**
- New vendors: **MiniMax** and **Arcee AI**

### Anthropic
- **Containers** (1h): persistent files, bash sessions, Skills, dynamic filtering, temp files across turns
- **Skills**: enabled by default with improved selector
- **File API**: download, embed, delete - text and image inlining via Container -> File pipeline
- Server-side recovered errors ignored, refusal details surfaced, code execution failures traced

### Gemini Deep Research
- Full SSE migration (no more POST + GET-loop)
- Resumable across pauses with full recovery mode (#1088)
- Cancel and delete controls, multiple reattaches
- Audio + thoughts support, image-as-figure handling
- Option to disable visualizations (#1095)

### Beam
- Auto-title beam chats when done (#1078)
- No accidental wipe with Ctrl+Shift+B (#1079); no re-beam while open
- No ghost columns in 2-beam mode (#1073); title edit fix (#1085)

### UX
- Inline message timestamps with TimeAgo (#1065)
- New chat on startup option (#1002)
- Single-dollar inline LaTeX (#795)
- Model pub dates, "new" badges on models under 30 days
- Sort LLM categories by name, filter chat drawer by open beams

### Also New
- AIX Resume framework with stop/cancel/recovery across providers
- xAI: encrypted reasoning by default, reasoning summaries always (#1091)
- OpenAI Responses: encrypted reasoning, tool re-parsing fixes
- New Global AI Settings store
- Performance: throttled code highlighting, memoized reasoning chips, lazy per-chat stores

### Fixes
- Voice features hidden in browsers without Speech Recognition (#1061)
- OpenRouter models refresh (#804)
- Zod 4 type strictness (#1072)

## New Contributors
* @alexdenton123 made their first contribution in https://github.com/enricoros/big-AGI/pull/1062
* @tredondo made their first contribution in https://github.com/enricoros/big-AGI/pull/1074

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.4...v2.0.5

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.

Big-AGI 2.0.5: Roberto

# Big-AGI 2.0.4 - Hyper Params

### Precision matters.

This release is about getting models right: accurate parameter ranges for reasoning effort, verbosity, and temperature across providers and through 3rd parties such as OpenRouter and AWS. Plus the latest frontier models, a new cloud platform, and Anthropic going deeper.

A huge shout-out goes to @Slava-256, for making Big-AGI's model support the best-in-class with this release. From filing detailed issues for accurate reasoning effort ranges ([#940](https://github.com/enricoros/big-AGI/issues/940), [#944](https://github.com/enricoros/big-AGI/issues/944)), verbosity accuracy ([#947](https://github.com/enricoros/big-AGI/issues/947), [#948](https://github.com/enricoros/big-AGI/issues/948)), temperature support ([#953](https://github.com/enricoros/big-AGI/issues/953)), to pushing for Opus 4.6 support ([#962](https://github.com/enricoros/big-AGI/issues/962)), and [many more (31 closed tickets!)](https://github.com/enricoros/big-AGI/issues?q=state%3Aclosed%20author%3ASlava-256). Slava's thorough testing, precise reports, findings, and reference code are the reason why 2.0.4 was focused on precise parameters support.

<img width="1792" height="1024" alt="0 - A2 - High-key_white_scene_with_impeccable_cleanliness__employing_heroic_framing _A_detailed_close-up_view_of_a_capybara__compellingly_crafted_from_crystal_glass _The_capybara_poses_with_flair__sporting_sleek_black_sunglasses_and_securely_positio" src="https://github.com/user-attachments/assets/257df06f-d365-4bf6-a81a-a9e74f97c0fe" />
 
### Models & Parameters
- Anthropic **Opus 4.6** with adaptive thinking and 1M tokens, **Sonnet 4.6** and new features
- Google **Gemini 3.1 Pro**, **Nano Banana 2**
- OpenAI **GPT-5.4** family with 1M context and reasoning controls
- xAI **Grok 4.20**
- New **Z.ai** GLM models support, with configurable thinking
- **API-validated parameters**: reasoning effort, budget, verbosity, temperature, tools, are tested on live APIs
- **Model-specific controls**: each model exposes only the parameter values it actually supports
- **Automated sweep testing** across native APIs keeps parameter definitions current

### Anthropic API mastery
- Configurable web search and web fetch depth, and dynamic search
- API controls such as **US-based inference** and **Fast mode for Opus** (2.5x speed, at 6x cost)
- Continuation for long outputs (pause_turn support)

### AWS Bedrock support (New)
- Authentication via both IAM credentials, or using a single AWS Bedrock token
- Native support for 3 native AWS Bedrock protocols: Anthropic models via Invoke, Amazon Nova models via Converse, and other models via OpenAI-compatible ChatCompletions

### Also New
- Attachments on any message, lossless images option (warning: can be very large on Gemini models)
- Rich text copy, reasoning trace controls
- System theme mode follow
- [Mobile focus mode](https://github.com/enricoros/big-AGI/issues/894)

## New Contributors
* @Blacksuan19 made their first contribution (SSR guard, system theme mode) in https://github.com/enricoros/big-AGI/pull/1011
* @dLo999 made their first contribution (local time for backup exports) in https://github.com/enricoros/big-AGI/pull/1041
* **Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.3...v2.0.4

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.

Big-AGI 2.0.4: Hyper Params

# Big-AGI 2.0.3 - Red Carpet

## What's New

### **Models updates**
This release embraces models precision: improved parameter configuration to match the model vendors, a new native xAI-flavored responses API, a new model vendor, and all the newest models including the already legendary Kimi 2.5, great for code.
- **Kimi K2.5** with image understanding and reasoning
- **Gemini 3 Flash** with 4-level thinking (high, medium, low, minimal)
- **GPT 5.2** with x-high reasoning and native search
- **GPT Image 1.5** for image generation
- **Novita.ai** full provider support with automatic capability detection
- **LMStudio** model capability support and images
- **xAI Responses** native protocol support with X post search and code execution

### **Also New**
- **Google Drive** integration - attach docs, sheets, images with optimal LLM conversion
- **Inworld** speech synthesis with streaming playback
- Model duplication for custom configurations
- AI Injector, collapsible model groups, PDF auto-OCR
- Copy as-seen, reorder messages in cleanup mode
- Anthropic and OpenAI API fixes, security patches, CJK/IME input

<img width="1792" height="1024" alt="203-a" src="https://github.com/user-attachments/assets/07e959ed-8610-44f6-ba58-c3d18e24b0aa" />

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.2...v2.0.3

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.

Big-AGI 2.0.3: Red Carpet

# Big-AGI 2.0.2 - Speex

## What's New

### **Speex: Multi-Vendor Speech Synthesis**
A complete redesign of text-to-speech with support for multiple providers:
- **Web Speech API** - Zero-config browser-native voices (works offline)
- **LocalAI** - Self-hosted TTS with Kokoro, Bark, Piper backends
- **ElevenLabs** - High-quality voice synthesis and cloning
- **OpenAI TTS** - gpt-4o-mini-tts with voice instructions, plus tts-1 and tts-1-hd

Engines auto-detect from your configured LLM services—no duplicate API key entry. Priority-based fallback ensures speech always works.

### **Also New**
- **Claude Opus 4.5** full support
- Starred models for quick access
- Continued stability improvements

<img width="1792" height="1024" alt="release-cover-v2 0 0" src="https://github.com/user-attachments/assets/35ea95cf-896e-403f-bfe4-3aca59fd11a1" />

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.1...v2.0.2

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.


Big-AGI 2.0.2: Speex

# Big-AGI 2.0.1 - Heavy Critters

## What's New

### **Latest Models**
- **Gemini 3 Pro** with code execution support
- **Nano Banana Pro** for controllable image generation
- **Grok 4.1 Fast**, the **GPT-5.1** family, **Kimi K2 Thinking**
- Updated model definitions across all 17+ providers

### **Enhanced Features**
- **Image Generation** now supports Azure and LocalAI alongside OpenAI
- **OpenRouter** auto-detects model capabilities and reasoning
- Call transcripts saved automatically
- Generate **persona images**
- Search functionality in Beam

### **Improvements**
- Enhanced error resilience (85% reduction in connection issues)
- 280 commits of fixes and optimizations
- [AI-Automatic feature development](https://github.com/enricoros/big-agi/issues/new?template=ai-triage.yml) for community contributions

<img width="1792" height="1024" alt="release-cover-v2 0 0" src="https://github.com/user-attachments/assets/35ea95cf-896e-403f-bfe4-3aca59fd11a1" />

**Full Changelog**: https://github.com/enricoros/big-AGI/compare/v2.0.0...v2.0.1

## Get Started
Available now at [big-agi.com](https://big-agi.com), via Docker, or self-host from source.

Big-AGI 2.0.1: Heavy Critters

# 🚀 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.

Big-AGI 2.0.0: Open, Free and Pro

# 🚀 big-AGI 1.16.0 - Crystal Clear

### Clarity and transparency in your AI interactions.

**big-AGI 1.16.0** - **Crystal Clear** - brings enhancements and new features designed to ensure that every interaction with big-AGI is smoother, more intuitive, and simply better - as we always do. We hope you'll love the updated models across the board, and the new cost tracking (please refresh the models to load the latest prices, now supported on Anthropic, OpenAI, and OpenRouter), which will translate to saving money, as anything that can be measured can be optimized for.

![release-cover-v1.16.0](https://github.com/enricoros/big-AGI/assets/32999/02472393-96d5-47b8-96f4-15d16b193c14)

## What's Changed

- **Chat Cost Estimation**: display a cost estimation for supported networks*. hover price for token info
![feature-turn-cost-2](https://github.com/enricoros/big-AGI/assets/32999/a33c5190-a670-47d1-ba7b-93a0bd78b2cb)
- Enhanced [Beam](https://big-agi.com/blog/beam-multi-model-ai-reasoning) based on your feedback: auto-selection and remembering networks and UX simplifications #470 
- Major improvements to the **Auto-Diagrams Tool**
- **Save/Load Chat Files** with Ctrl+S and Ctrl+O #466 
- @joriskalz: **YouTube Transcriber** persona: transcribe and chat with YouTube videos (un-hide it from the selector) #500
- @mludvig: **3x faster on Apple silicon** with Docker multi-arch builds #507
- More: Perfect formulas/LaTeX rendering #508, soft-wrap code #517, chat text selection toolbar, dark mode fixes #520
- Doc corrections by @dandv and @PrivTEC and in #521 #522 #525 
- Updated Anthropic*, Groq, Ollama, OpenAI*, OpenRouter* and Perplexity models
- For Developers: updated LLM data structures
- [Full Changelog](https://github.com/enricoros/big-AGI/compare/v1.15.1...v1.16.0)

## New Contributors
* A warm welcome and thank you to @mludvig, @PrivTEC, and @dandv for their first contributions to big-AGI!

## In Summary
Transparency and user experience improvements, for an improved quality of life. We are thankful to be able to merge contributions for the community, including a new YouTube Transcriber persona and the faster multi-arch (ARM, x86) builds.

Upgrade today and experience the clearer, faster, and more intuitive big-AGI. Available via code, Docker, or on the free instance on [big-agi.com](https://big-agi.com). 🚀

Big-AGI 1.16.0: Crystal Clear

# 🚀 big-AGI 1.15.0 - Beam

### Introducing multi-model AI chats.

We're thrilled to announce **big-AGI 1.15.0 - Beam**. [Beam is a new chat modality in big-AGI](https://big-agi.com/blog/beam-multi-model-ai-reasoning) that empowers users to find better answers by leveraging the collective intelligence of multiple models. It's a game-changer for brainstorming, decision-making, and creativity.

The word "groundbreaking" gets tossed around a lot these days, but this is new technique really is, and this is a world exclusive for you big-AGI lovers. With over 400 commits and 10,000+ lines of code changed, big-AGI 1.15 sets a milestone in AI chats.

![release-cover-v1 15 0 r](https://github.com/enricoros/big-AGI/assets/32999/421ebefa-d0ce-4818-a380-ee3f03bf7d82)

- **Beam**: Unveiling the multi-model AI chat experience. #470
- **Managed Deployments Auto-Configuration**: Simplify your setup with auto-configuration for managed deployments: set env vars on the backend and the frontend will pick up all the models automatically - works well local models too, such as [LocalAI](https://localai.io). #436 
- **Message Starring ⭐ and Filtering**: Star important messages, and in the future you'll be able to attach and filter chats. It's already working, but we're still testing the UI patterns for it #476 
- **Persona Enhancements**: The default AI persona just got better
- **UI and Model Fixes**: Ironed out issues with Gemini models and SVGs and polished the UI and icons for a smoother experience

### For Developers:
- **Imperative LLM Models Discovery**: moved from React to imperative code, with reactive hooks. Enables #436 
- Full changelog: https://github.com/enricoros/big-AGI/compare/v1.14.1...v1.15.0

## In Summary

1.15.0 - Beam is the most impactful big-AGI release to date. By leveraging the power of multiple models, Beam enables users to explore diverse perspectives, synthesize optimal responses, and push the boundaries of what's possible with AI-assisted brainstorming, decision-making, and creativity.

Experience the future of AI chat _and upgrade to Beam today_, available via code, Docker, or directly on [big-agi.com](https://big-agi.com).

Join our vibrant AGI community on [Discord](https://discord.gg/MkH4qj2Jp9) and be part of the conversation! Your feedback and contributions are invaluable in shaping the future of big-AGI. Now, let's embark on this exciting journey together with `Beam` 🚀

Big-AGI 1.15.0: Beam

# 🚀 big-AGI 1.14.0 - Modelmorphic

### The new shape of intelligence and performance.

We're releasing big-AGI 1.14.0, "Modelmorphic." This update expands models support, focuses on improving performance, and delivers user experience enhancements. With over 230 commits and over 8,000 lines of code changed, it's designed to make big-AGI smarter, faster, more reliable.

![release-cover-v1 14 0 b](https://github.com/enricoros/big-AGI/assets/32999/0763d3c0-d165-4978-b45f-37c6e4b79b41)

- (1.14.1) Added support for **Anthropic Claude-3* models
- Added support for **Perplexity**, including Sonar Online models, and **Groq**, including models with up to 500 tok/s speeds. Contribution by @Penagwin.
- Added **Mistral** Large models, and Google **Gemini 1.5** models.
- Deeper **LocalAI** integration with support for model galleries and keys.  
- Performance **Optimizations**: comprehensive improvements for faster operation, lower power consumption, and better memory use  
- UI and Usability: updated navigation, search, scaling, shortcuts, and chat interactions for a smoother experience.
- Addressed issues with image warnings, standalone LaTeX blocks, hidden personas in the selector, and more.
  
### For Developers:
- Customizable PlantUML Server via an environment variable, thanks to @fredliubojin.
- New customization documentation and analytics support are now included.
- Added /info/debug for better diagnostics.
- Introduced a "controller-based" chat architecture to simplify per-chat data management, including ephemerals.
- Full changelog: https://github.com/enricoros/big-AGI/compare/v1.13.1...v1.14.0

### New Contributors

Special thanks to our new contributors @Penagwin and @jacksongoode. @Penagwin work has been instrumental for making this release a success.

## In Summary

Version 1.14.0 - **Modelmorphic** represents a leap forward in our commitment to providing advanced, reliable, and user-centric AI tools. We continue to eschew fluff in favor of substance, focusing on what truly matters to our users and developers.

Explore the new features and improvements _and upgrade to Modelmorphic today_, available via code, Docker, or directly on [big-agi.com](https://big-agi.com).

Join our AGI community on [Discord](https://discord.gg/MkH4qj2Jp9) and get involved with us! Your feedback and contributions are what drive us forward. Now enjoy `Modelmorphic` 🚀

Big-AGI 1.14.0: Modelmorphic

# 🚀 big-AGI 1.13.0 - Multi + Mind

### More AI in less time.

Today, we announce the release of big-AGI 1.13.0, marking another milestone in our journey to enhance AI interaction and productivity.
`Multi + Mind` focuses on multitasking capabilities and personal customization, ensuring that your experience with big-AGI is more efficient and tailored to your needs. Here's what's new:

![img-EvBk3F6tejzYJ81niD6eh5PY](https://github.com/enricoros/big-AGI/assets/32999/22938c52-4edf-4635-9a50-a89f2f6668a6)

- **Side-by-Side Split Windows**: multitask with parallel conversations - stop waiting for one assistant to finish #208  
- **Multi-Chat Mode**: send the same message in many chats at the same time #388 
- Export Tables as CSV: Thanks to @aj47 , you can export data gids to other software - a game-changer for data analysis and reporting #392 
- **Adjustable Text Size**: one size doesn't fit all, so now you can enjoy denser chats, especially on mobile phones #399 
- Dev2 Persona Technology Preview: we are starting to test out new and more capable personas
- UI: better-looking chats, improved spacing, fonts, and menus
- Extra: new integrated video player, an [LM Studio tutorial](https://www.youtube.com/watch?v=MqXzxVokMDk) by @aj47 , [MongoDB support](https://github.com/enricoros/big-AGI/blob/main/docs/config-database.md) (@ranfysvalle02), and large performance boost

### For Developers:
- This release includes over 150 commits, and focused on internal cleanups and quality, while delivering a few stunning new features
- Dive into the details: [v1.12.0...v1.13.0](https://github.com/enricoros/big-AGI/compare/v1.12.0...v1.13.0)

### New Contributors
We're thrilled to welcome @aj47 and @ranfysvalle02:
- @aj47 made their first contribution in [#392](https://github.com/enricoros/big-AGI/pull/392)
- @ranfysvalle02 made their first contribution in [#393](https://github.com/enricoros/big-AGI/pull/393)

---

https://github.com/enricoros/big-AGI/assets/32999/01732528-730e-41dc-adc7-511385686b13

---

### Upgrade Now
Don't wait to explore all these new features. Upgrade to big-AGI 1.13.0 today, available via code, Docker, or directly on the hosted site.

Join our AGI community on [Discord](https://discord.gg/MkH4qj2Jp9) and get involved with us! Your feedback and contributions are what drive us forward. And now enjoy `Multi + Mind` 🚀

Big-AGI 1.13.0: Multi + Mind

# 🚀 big-AGI 1.12.0 - AGI Hotline

Introducing big-AGI 1.12.0, a significant step in refining AGI interaction and management. Who can it be now? Your phone is ringing - it's your AGI. **Voice Call**, with **new OpenAI models**, flying on a snappier and **juicier** UI.

![release-cover-v1 12 0](https://github.com/enricoros/big-AGI/assets/32999/0cad8f75-5751-4471-9bfe-18f1d296811a)

Here's the essence of what's new:
- **Voice Calls**: real-time voice call your personas out of the blue or in relation to a chat #354 
- **Updated OpenAI 0125** Models. #364 
- Rename and **Auto-Rename** chats.  #222 
- **Link Sharing Revamped**, with more user control #356 
- **Accessibility** to screen readers #358
- Export chats to Markdown #337 
- Paste tables from Excel #286 
- Ollama model updates and context window detection fixes #309 

For Developers:
- Over 150 commits and 7,000+ lines changed, emphasizing performance optimizations and under-the-hood improvements for a smoother experience.
- Dive into the details: [v1.11.0...v1.12.0](https://github.com/enricoros/big-AGI/compare/v1.11.0...v1.12.0)

https://github.com/enricoros/big-AGI/assets/32999/95ceb03c-945d-4fdd-9a9f-3317beb54f3f

### Upgrade Now
Upgrade to big-AGI 1.12.0 today (code, docker, or the hosted site).

Join us on [Discord](https://discord.gg/MkH4qj2Jp9) and explore our [public roadmap](https://github.com/users/enricoros/projects/4/views/2). Together, we're shaping its future! 🚀

Big-AGI 1.12.0: AGI Hotline

# 🚀 big-AGI 1.11.0 - Singularity

Like a cosmic clockwork, today marks the release of big-AGI 1.11.0, and here's a constellation of enhancements that bring the universe of AI closer.

- **Search conversations**: find by keywords within titles and contents, with frequency ranking - thanks to @joriskalz's stellar work #329 
- **Command palette**: type "/" for command selection and auto-completion
- **[Together AI](https://together.ai) Integration**: connect with the recent and blazing-fast models provided by the Together AI inference platform #346 
- Persona Creator Enhancements: Deleteable history of creation, custom creation commands, and much more #301 #328 #199 #336 
- OpenAI-Compatible Endpoints: Multiply your AI potential by adding up to five custom OpenAI-compatible endpoints. Flexibility is the new frontier. [#323](https://github.com/enricoros/big-AGI/issues/323)

1.11.0 for Developers:
- New 'Actiles' framework for developers, to support commands auto-completion with abstract triggers and item sources.
- Full Changelog: [v1.10.0...v1.11.0](https://github.com/enricoros/big-AGI/compare/v1.10.0...v1.11.0)

https://github.com/enricoros/big-AGI/assets/1590910/a6b8e172-0726-4b03-a5e5-10cfcb110c68

### Acknowledgements
Thanks especially to @joriskalz for their impactful pull requests in this release.

### Upgrade Now
Upgrade to big-AGI 1.11.0 today (code, docker, or the hosted site).

Join the conversation on [Discord](https://discord.gg/MkH4qj2Jp9), explore our [public roadmap](https://github.com/users/enricoros/projects/4/views/2), and thank you for your continued support, and let's explore the possibilities of AGI, together! 🌌🚀

Big-AGI 1.11.0: Singularity

# 🚀 big-AGI 1.10.0 - The Year of AGI

Happy 2024! We're excited to give you Big-AGI 1.10.0, which brings good improvements and sets the stage a more powerful UX.

https://github.com/enricoros/big-AGI/assets/32999/fbb1be49-5c38-49c8-86fa-3705700f6c39

- **New UI**: Responsive, animated, and sleek interface for the best UX across desktop and mobile. #201 
- **Conversation Folders**: Keep your chats organized with the new folder system. #321 
- **LM Studio**: model support and improved token management.
- Resizable panes in split-screen chat mode
- Large performance optimizations making big-AGI even faster and more responsive

1.10.0 for Developers:
 - Introducing the new "OptimaLayout" UI framework to enable scale and support multiple top-level apps
 - Updated the documentation for proxy settings on browserless/docker environments. #318
 - Full Changelog: [v1.9.0...v1.10.0](https://github.com/enricoros/big-AGI/compare/v1.9.0...v1.10.0)

### New Contributors
We're excited to welcome @kursad-k to the big-AGI contributors! Thank you, @kursad-k! 🌟

### Acknowledgements
Thanks to @joriskalz for the masterful work on the conversation folders - _try that drag and drop to reorder!_. This community is what makes open source amazing!

### Support Big-AGI
Join the conversation on [Discord](https://discord.gg/MkH4qj2Jp9), explore our [public roadmap](https://github.com/users/enricoros/projects/4/views/2), and thank you for your continued support, and here's to a fantastic year ahead with big-AGI! 🎊✨

Big-AGI Notes