# Daneel AI — News & Updates

Daneel AI is a private-AI Chrome extension for enterprise. Zero cloud exposure.
All inference stays on your infrastructure.

## Articles
- [More one-click MCP servers for your AI](https://daneel.injen.io/news/mcp-presets-expansion.md): Twenty new preset MCP servers join the Featured list. Daneel connects to any HTTP/SSE MCP server you paste by URL, these are just one-click ready.
- [Daneel now speaks, and listens — three voices, one of them fully local](https://daneel.injen.io/news/daneel-speaks.md): Pick the voice that suits the moment: system voices for zero-install, Kokoro 82M for fully on-device synthesis on WebGPU, or Google Cloud voices when you want that extra polish. And hold Alt+Space to dictate.
- [Wikidata next to Wikipedia — facts you can scan, not just read](https://daneel.injen.io/news/wikidata-fact-box.md): Click an entity in your knowledge graph and you now get two panels side by side: Wikipedia for the story, Wikidata for the structured facts. Birth dates, awards, employers, external IDs, all in one scannable card.
- [Reclaim disk space from your local models](https://daneel.injen.io/news/models-storage.md): A new Settings section shows how much disk every downloaded model is using, grouped by role, with per-model trash and a delete-all.
- [Your LLM at 37,000 feet](https://daneel.injen.io/news/offline-mode.md): Cache your vault and a local model before boarding. Work with your own AI for the whole flight. The other first-class passengers are still waiting on satellite internet.
- [Hide the Widget in Fullscreen, or Per Site](https://daneel.injen.io/news/widget-visibility.md): The launcher now hides itself when a page goes fullscreen, and a new per-site toggle in the popup gives you explicit control anywhere else.
- [Math Formulas Render Cleanly](https://daneel.injen.io/news/math-rendering.md): Ask an LLM for a derivation, and you now get typeset math across every chat surface, not raw LaTeX.
- [Mermaid Diagrams, Now in Every Chat](https://daneel.injen.io/news/mermaid-diagrams.md): Ask for a flowchart, sequence, or mindmap, and the chat renders the diagram instead of the source.
- [How we build Daneel: full spec-driven development with a coding agent](https://daneel.injen.io/news/agentic-development-workflow.md): 8,000 lines of specs, 82,000 lines of code, 1,331 tests, 27 releases, and 25 articles in 26 days. Not a team of ten. One developer and a coding agent, working from 8,000 lines of specification.
- [Bonsai by PrismML: A 1.7B one bit model in 291 megabytes, running in your browser](https://daneel.injen.io/news/bonsai-1bit-webgpu.md): Bonsai 1.7B brings native 1-bit quantization to Daneel's WebGPU engine, delivering a thinking-capable model at a fraction of the usual download size.
- [Claude Opus 4.7 is now available in Daneel](https://daneel.injen.io/news/claude-opus-4-7.md): Anthropic's newest flagship model brings stronger coding, sharper vision, and better instruction following, available today in the Claude settings.
- [Index any site, even without a sitemap](https://daneel.injen.io/news/web-crawl-link-discovery.md): Daneel can now discover pages by following links, so sites without a sitemap.xml are no longer invisible to site search.
- [PDF is now a first-class citizen in Daneel](https://daneel.injen.io/news/pdf-first-class.md): Open any PDF in Chrome and start chatting, no upload required. Extract text, ask questions, copy as Markdown, or save to a vault, all from the same widget you already know.
- [Documentation, where you need it](https://daneel.injen.io/news/embedded-docs.md): Every settings panel now opens its own help column — the right doc, beside the right setting, one click away.
- [From pretty graph to research workbench — analytics, paths, and Wikipedia for your knowledge graph](https://daneel.injen.io/news/knowledge-graph-analytics.md): The 3D knowledge graph now has an insights panel that ranks key entities, detects topic clusters, surfaces bridges, and lets you trace connections between any two entities — plus one-click Wikipedia lookup that opens articles right next to the graph.
- [Click any link, stay in the vault — the document viewer is now a markdown mini-browser](https://daneel.injen.io/news/vault-mini-browser.md): Web pages saved to your vault are now navigable: click any link inside them to fetch, convert, and display the next page right in the viewer, with a back button and no new tab in sight.
- [Start it and forget it — background tasks that survive everything](https://daneel.injen.io/news/background-tasks.md): Site crawls, vault indexing, and knowledge graph builds now run in the background — close panels, switch tabs, even restart Chrome, and your work picks up where it left off.
- [Gemma 4 lands in Daneel — Google's latest open model, running locally](https://daneel.injen.io/news/gemma-4-support.md): Google's Gemma 4 family brings 128K context, built-in reasoning, and 35+ language support to Daneel's WebGPU and Ollama backends — running entirely on your device.
- [Chat with any YouTube video](https://daneel.injen.io/news/youtube-transcript-chat.md): Daneel now extracts YouTube transcripts automatically — ask questions, get summaries, and find key moments without leaving the page.
- [The Vault, part 2: your knowledge graph](https://daneel.injen.io/news/vault-part-2.md): Daneel extracts entities from your documents, resolves duplicates, builds a relationship graph, and renders it as an interactive 3D visualization you can filter and explore.
- [Docker Companion — local MCP servers, Ollama, and health monitoring from your browser](https://daneel.injen.io/news/docker-companion.md): A built-in Docker Compose generator that spins up local MCP servers, Ollama, and a health sidecar — all from your browser settings. Power user preview.
- [Your data, your way — backup anywhere](https://daneel.injen.io/news/data-portability.md): Export everything to a local file, Azure Blob Storage, or any S3-compatible service. Your settings, conversations, and indexed sites travel with you — your secrets don't.
- [The Vault, part 1: your private document knowledge base](https://daneel.injen.io/news/vault-part-1.md): Import your own documents, embed them locally, and chat with your personal knowledge base. PDF, DOCX, Markdown, HTML, plain text — all searchable, all private.
- [Azure AI Foundry support: frontier models, your private cloud](https://daneel.injen.io/news/azure-foundry-support.md): Deploy GPT-4.1, GPT-4o, or Phi-4 on your own Azure subscription — frontier model power with your organization's data governance. The privacy sweet spot between local and third-party cloud.
- [Meet Agents — your AI, your rules](https://daneel.injen.io/news/agents-feature.md): Create specialized AI personas with structured prompts and bound tool access — then attach them to any conversation or document vault.
- [Find your best model — the AI registry that knows your hardware](https://daneel.injen.io/news/model-registry.md): A unified model registry across five providers, hardware-aware scoring, and a guided wizard that recommends the right model for your GPU, your priorities, and your privacy preferences.
- [Connect your AI to the tools you already use](https://daneel.injen.io/news/mcp-connectors.md): Daneel now speaks MCP — connect Stripe, Notion, Vercel, Supabase, and dozens more services directly to your browser AI, with full OAuth support and multi-turn tool calling.
- [How Daneel's licensing works — one payment, no account, full control](https://daneel.injen.io/news/licensing-explained.md): A one-time payment, a portable license key, no account required. Here's how Daneel keeps premium features simple, private, and permanent.
- [When you need the full power — Claude on Daneel](https://daneel.injen.io/news/claude-support.md): Bring your own Claude API key for tasks that demand frontier intelligence — complex reasoning, multi-step tool chains, and long documents — while keeping local inference as your default.
- [Privacy in Daneel: how your data stays yours across every feature](https://daneel.injen.io/news/privacy-architecture.md): From on-device inference to encrypted API keys, from MCP credential isolation to opt-in analytics — a complete look at how Daneel protects your data at every layer.
- [Search by meaning, not just keywords](https://daneel.injen.io/news/semantic-search.md): Daneel crawls and indexes entire websites, then lets you search them with natural language — matching concepts, not strings, with results in under 5 milliseconds.
- [Zero-install AI — Gemini Nano runs inside your browser](https://daneel.injen.io/news/gemini-nano-support.md): Chrome ships an AI model built into the browser itself. Daneel now supports it — no downloads, no API keys, no server. Here's how to activate it and what you can do with it.
- [Run AI on your own machine — Ollama meets Daneel](https://daneel.injen.io/news/ollama-support.md): Connect your local Ollama server to Daneel and run models like Llama, Mistral, and Qwen entirely on your hardware — with streaming, tool calling, and full model management from your browser.
- [Daneel AI 1.0 is here](https://daneel.injen.io/news/daneel-1-0-release.md): The first stable release of Daneel AI — private, local-first AI for your browser. Chat with any page, search entire sites, and build your own document vault, all without leaving your data.

## Feeds
- RSS: https://daneel.injen.io/rss.xml
- Atom: https://daneel.injen.io/atom.xml
- JSON Feed: https://daneel.injen.io/feed.json

## Research papers
- [From community ports to first-party releases: small-to-medium browser LLMs in March 2026](https://daneel.injen.io/research/state-of-browser-small-medium-llms-march-2026.md): The in-browser open LLM catalog grew up in 2025-2026: from three community ports to two dozen first-party releases in eighteen months.
- [The three walls of in-browser LLM inference: the state of affairs in April 2026](https://daneel.injen.io/research/three-walls-browser-llm-inference-2026.md): In April 2026 browser LLM inference passed an inflection point: runtime architecture is solved, and per-tab VRAM is the new ceiling.

## Research feeds
- RSS: https://daneel.injen.io/research/rss.xml
- Atom: https://daneel.injen.io/research/atom.xml
- JSON: https://daneel.injen.io/research.json