#UMAP in VR for #3DThursday! In this zebrafish embryogenesis dataset, RNA-seq + ATAC-seq across 94k+ cells reveal changing regulatory programs over time.
🥼 Yang-Joon Kim, Loic Royer @loicaroyer.bsky.social , Matthias Haury
📝 www.biorxiv.org/content/10.1...
🏛️ Biohub @biohub.org
🎬 #syGlass v2.6.0
10/ Here is the latest thread about Omega:
bsky.app/profile/loic...
That 'loop' is already there. Just combine an autoreserach skill + MCP-agent + napari. I do this routinely now.
9/ Thanks for all the beta-testers!
8/ We are aware of other efforts developed independently, such as the project by Haichao Miao at LLNL: github.com/llnl/bioimag.... Try it too!
8/ Here is a presentation and demo by Ilan!
www.youtube.com/watch?v=SG91...
7/ Power + safety: napari-mcp can expose code execution + package installation tools, so treat it like a local instrument (not a public toy).
Docs: royerlab.github.io/napari-mcp/
Contributions welcome: issues/PRs on GitHub.
6/ Already in napari? Use plugin mode.
Plugins → napari-mcp: MCP Server Control → Start Server.
Your MCP client now controls the *current* session (no new viewer), so it slots into real workflows.
royerlab.github.io/napari-mcp/g...
5/ Quick start:
1) pip install napari-mcp
2) napari-mcp-install <app> (claude-desktop / cursor / cline-vscode / gemini / codex)royerlab.github.io/napari-mcp/getting-start...
4/ The fun part: your assistant can *see* what is on the napari canvas and use that to reason and decide what to do next! With visual feedback, the agent can observe, reason, and iterate rather than guess.
royerlab.github.io/napari-mcp/a...
3/ napari-mcp exposes tools for layer management, viewer control (2D/3D, camera, dims), widgets, screenshots, and more! You get the best of both worlds: first-class agentic interfaces + napari viewer!
API: royerlab.github.io/napari-mcp/a...
2/ Context: Omega (napari-chatgpt) showed that LLM agents can do real work inside napari (processing + widgets + self-repair). napari-mcp is the next step: any MCP-enabled app can now drive napari!
github.com/royerlab/nap...
1/ 🚀 Excited to release: napari-mcp - agentic control of napari from any MCP-capable AI assistant!
Use it for interactive image processing, analysis, and visualisation! Really cool project from @ilan-theodoro.bsky.social from my team!
#napari #bioimageanalysis #MCP @biohub
Congrats Christian!
Good to be back home!
Excited to share our new paper (CVPR 2026 🚀): "MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy" which enables local predictions to use global context.
Great work led by @albertdm.bsky.social & another fun collab w @gioelelamanno.bsky.social! @scadsai.bsky.social
Our symposium on ‘AI applications in Biology’ is about to start in 30 minutes! Great lineup of speakers for what promises to be a fantastic meeting! 🧪
There was an issue with version 2026.2.8.2, I deleted it and created a new one: 026.2.9
Thanks, Zebrafish Rocks! It is not new, but it has been massively improved with new features and many bug fixes! 😀
12/ I would like to thank @anthropic.com for making Claude Code. CC did most of the maintenance work to 'fix' Omega. It even addressed the issues directly, fixing the code, adding comments, closing issues, reviewing image.sc, and further fixing issues and implementing new requested features! nuts!
11/ 🔬🧪 Try it today! pip install napari-chatgpt — GitHub: github.com/royerlab/napari-chatgpt — Paper: doi.org/10.1038/s41592-024-02310-w #Omega #napari #AI #BioImageAnalysis
10/ And remember! An often overlooked feature of Omega is its integrated code editor! All code generated by Omega is saved for you to edit, improve, and reuse later!
9/ 🛡️ 30+ bug fixes & security hardening: Qt thread safety segfaults, Windows Unicode errors, macOS shutdown hangs, shell injection prevention, and infinite loop guards. #Omega is now much more robust across all platforms!/home/royer/workspace/python/napari-chatgpt/screenshots/card_bug_fixes.png
8/ 🧰 More tools & better napari integration: FileDownload, PipInstall (with user permission!), web search, exception catcher. Plus sample data in the napari File menu so you can start experimenting with #Omega immediately.
7/ ✨ Modernized chat UI: dark theme, message bubbles, thinking animations, collapsible tool output, responsive layout, and a live session token counter. Removed 176K lines of vendored CSS for a clean, fast experience.
6/ 🤖 Agentic widget maker! #Omega now uses a sub-agent to generate napari/magicgui widgets. If the code fails, it reads the error and self-corrects — up to 3 attempts. Smarter code generation, fewer failures!
5/ ⚡ New: Layer Actions! Ask #Omega to create custom right-click context menu items & keyboard shortcuts for napari layers. Say 'make an action that applies a Gaussian blur' and it appears in your context menu, ready to use on any layer!
4/ 🧩 New: NapariPluginTool! #Omega can now discover & use ANY installed napari plugin. Plus, 3rd-party devs can extend Omega with custom tools via Python entry points — just add an entry in your pyproject.toml!
3/ 🔧 Bring your own LLMs! Connect Ollama, Azure, vLLM, or any OpenAI-compatible endpoint via ~/.omega/config.yaml. Got a GitHub token? #Omega auto-detects it and unlocks free GitHub Models. Frontier to local — your choice!
2/ 🔗 Multi-provider LLM support for the very latest frontier models! #Omega now works with OpenAI, Anthropic (Claude), & Google Gemini via the LiteMind library. No more vendor lock-in. You can even set separate models for conversation & coding tasks!
