Eric Charles

An AI agent shouldn't be twelve YAML keys you hold in your head. Our visual editor draws it: the agent in the middle, its model, MCP servers, rules, skills around it. Canvas, spec and Python are one definition. Try it, no sign-in → datalayer.ai #AIAgents #MCP

📐 Agent specs are getting nicer: Oracle's Open Agent Spec, Pydantic AI, runtime-enforced AgentSpec. Datalayer Agentspecs now makes protocols specs too: MCP, A2A, PAP, PACT… declared per agent, checked, compiled to Python + TypeScript 🧩 github.com/datalayer/agentspecs about:blank#blocked #AIAgents

🎉 Personal Agent Protocol 0.11.0: the first complete Python 🐍 + TypeScript 🟦 SDKs, both roles, an example for every feature 🧭 personal-agent-protocol.datalayer.tech/examples/ Now integrating it in Datalayer 🚀 personal-agent-protocol.datalayer.tech/blog/persona...

🎉 Datalayer's Poppy SDKs (Python 🐍 + TypeScript 🟦) are listed on poppy.md! 📚 Must-read: Poppy vs MCP, A2A, UCP, ACP, TAP, PACT. Poppy answers the consent question 🔐 Kudos Fabricio Telles 👏 poppy.md/compare

🎉 Our Personal Agent Protocol SDKs (Python 🐍 + TypeScript 🟦) are on awesome-poppy! Draft 0.1 today; sign-in, conversations and Operations next 🚀 Thanks Javier Chulvi Bernad for the list 🙌 github.com/JaviChulvi/a...

🚀 PAP SDK v0.3.2 is live for Python + TypeScript! PAP is an open protocol for every company and every personal agent. We ❤️ protocols and want to build with the community. 🌸 personalagentprotocol.org// ✨ Listed on github.com/JaviChulvi/a... #Poppy

Connect with me for feedback on this announce. MCP is the enabler, we are now providing way more features for your AI data-driven cases. #Expand #Growth #Data #AI

One more time, amazingly powered by the community. Plenty of great contributions here 💪⚡💚

Early queue at Odoo Experience

Follow the datalayer-ai feed bsky.app/profile/did:... to learn more about data analysis

The "women and children first" protocol was clearly followed Socioeconomic status (class/fare) significantly impacted survival chances. Family size (siblings/spouses and parents/children) shows varying effects on survival. #titanic #survival

Pyramid and the Golden Ratio The Golden Ratio (Φ ≈ 1.618) is closely approximated in the dimensions of the Great Pyramid of Giza, where the ratio of the pyramid's slant height (apothem) to half of its base length remarkably yields approximately 1.61804.

✨ An agent that answers with an interface, not a wall of text. 📅 A form that sends your input back to the agent; 📊 Jupyter output as an A2UI surface, buttons that send your click to the code. 🎬 90 s, 🔓 open source → github.com/datalayer/agent-runtimesabout:blank#blocked #A2UI #Jupyter

Jupyter MCP Server 2.2 can now be extended the way your editor is: about:blank#blocked • extensions add tools — install one and its tools are served • extensions extend tools — wrap, narrow or re-describe a tool another extension offers, by name No fork. No load-order race. 🧵

Excellent country blues by Paul Crowley, an Englishman in France, and folk/country by The Rusty Zippers from north of Belgium. Add to leave before The Recidivists

#folk and #blues this evening at Wihéries (Elouges), BE

Sunday morning exercise with Claude Code launching Subagents to reformat docs. Nice view of the hierarchy and details of each Subagent system prompt.

🛑 𝙎𝙩𝙤𝙥 𝙥𝙖𝙨𝙨𝙞𝙣𝙜 𝙅𝙪𝙥𝙮𝙩𝙚𝙧 𝙣𝙤𝙩𝙚𝙗𝙤𝙤𝙠𝙨 𝙖𝙧𝙤𝙪𝙣𝙙. Handoffs lose state, files, outputs and context. 🪐 Datalayer gives teams and AI agents one live Jupyter notebook. Same cells. Same state. Same results. datalayer.ai #Jupyter #Collaboration

I really like the support of webm upload on Bluesky, way better than on X - Bluesky allow large files upload and eats them like a boss.

🚀 𝗝𝘂𝗽𝘆𝘁𝗲𝗿 𝗳𝗼𝗿 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 Our new Datalayer homepage is live. Give your agent persistent notebooks, scalable compute & connected data—or try an Agent built for Jupyter directly. The work keeps running when you disconnect. 👉 datalayer.aiabout:blank#blocked

🧩 I was missing a plugin framework spanning Python + React, so I built one. Reactor is now OSS: github.com/datalayer/re... Extension points, dependencies, Python packaging + React plugins via Module Federation. Feedback welcome 👀

Version 2 lays the foundation for 𝗲𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲-𝗴𝗿𝗮𝗱𝗲 Jupyter MCP.

🚀 𝗧𝗵𝗲 𝗵𝗼𝘀𝘁𝗲𝗱 𝗝𝘂𝗽𝘆𝘁𝗲𝗿 𝗠𝗖𝗣 𝗦𝗲𝗿𝘃𝗲𝗿 𝗶𝘀 𝗹𝗶𝘃𝗲. 🔌 One MCP endpoint gives your AI agent: 📓 Persistent notebooks ⏳ Durable execution ⚡ CPU/GPU compute 🗄️ Direct data access 🤝 Human + agent collaboration No server to operate. 👉 datalayer.ai/docs/mcp

⚡ 𝗝𝘂𝗽𝘆𝘁𝗲𝗿 𝗠𝗖𝗣 𝗦𝗲𝗿𝘃𝗲𝗿 — 𝗛𝗼𝘁 𝗙𝗶𝘅 `code-sandboxes` renamed: 🔄 `jupyter` → `jupyter-server` Use: ✅ `jupyter-mcp-server >=1.5.0` → `code-sandboxes >=1.1.1` ⏪ Older server → `code-sandboxes <=1.0.9` Otherwise: 💥 `Unknown sandbox variant: jupyter` jupyter-mcp-server.datalayer.tech/releases/#ho...

🧭 Vibe coding → document-first → spec-driven. Now live: Datalayer Code Sandboxes support CPU + GPU environments from Modal and Kaggle. 🚀 📚 datalayer.ai/docs/jupyter... 💬 github.com/datalayer/ag...

More is coming #next

#GPU #Jupyter #MCP

🌊 Sea, sun & art. 💻 Shipping community feature requests for our Jupyter projects. 🤝 A reminder that a great open-source community is a privilege worth caring for. 🎭 Open-air theatre to finish Sunday. A pretty good weekend. 😊 #OpenSource #Jupyter #MCP

📚 Better docs for Jupyter MCP Server! The MCP tools reference is now automatically generated from source with @sourcey. 👉 jupyter-mcp-server.datalayer.tech/mcp/ Big thanks to @antheducation for the contribution! 🙏 #Jupyter #MCP #OpenSource

Enterprise AI needs more than token metrics. It needs traceability. Know what your agents executed, which tools they called, what data they used, and how they reached a result. That's how AI becomes trustworthy. datalayer.ai/guide #AI #AIAgents #Jupyter

🥈 We just open-sourced our **AI for Earthquake Response** solution. 2nd place at the ESA Φ-lab challenge. 📖 Blog: datalayer.blog/2025/09/12/a... 💻 Code: github.com/datalayer-ch... Next: reproduce it on Datalayer. #AI #OpenSource

**The cheapest token is the one you never send.** Most AI agents keep sending the same context back to the LLM. CodeMode keeps execution inside a **Code Sandbox**, sending only what's needed for the next decision. Fewer tokens. Lower cost. Faster agents. datalayer.ai/guide #AI #AIAgents #LLM

🚀 Jupyter MCP Server v1.2.0 is out. ⚠️ Breaking change: **Runtime** → **Code Sandbox**. This better reflects support for multiple execution backends. It's **not** the MCP v2 migration—that comes later. Migration guide: jupyter-mcp-server.datalayer.tech/releases/#mi... #MCP #Jupyter #OpenSource

AI agents need AI runtimes. Without a runtime, agents repeatedly rebuild context and redo work. Persistent execution makes agents faster, cheaper, and ready for production. datalayer.ai/guide #AI #AIAgents #Jupyter

🎨 One theme doesn't fit everyone. Datalayer now has 5 themes: 🟢 Datalayer (classic) 🌌 Spatial (cosmic) 🌹 Lovely (warm) 💚 Matrix (terminal) 🌍 Earth (nature) Plus Light, Dark & Auto modes. 🎥 www.loom.com/share/4977d2... Which theme would you pick?

🤝 Jupyter MCP Server keeps reaching new users! A recent request is to publish the project on **conda-forge**. If you have conda-forge experience, we'd love your help: github.com/datalayer/ju... New contributors? Start here: github.com/datalayer/ju... #Jupyter #OpenSource #Python #MCP

🪐 Jupyter MCP Server v1.1.3 is out! More reliability, better compatibility, and a smoother experience for AI agents working with Jupyter Notebooks. Release notes: github.com/datalayer/ju... #Jupyter #MCP #AI

A small but important milestone for @datalayer.ai team: Jupyter MCP Server + Code Sandboxes now moves toward a multi-sandbox provider model. Keep one MCP while giving teams freedom to choose the runtime backend that fits each workload. #Jupyter #AI #MCP #Freedom #LockOut

For large source coding features, I use Opus 4.8, then fall back to GPT-5.3-Codex to polish, all that from VS Code Copilot.

🧠 Context engineering > prompt engineering. We compare CodeMode vs no CodeMode with reproducible GitHub Actions workflows. Less context → fewer tokens → lower cost. 🎥 Demo: www.loom.com/share/1edbbe... Report deep dive next.

Should the mcp server open the #jupyterlab tab on "use notebook" mcp tool invocation? Join the discussion on the github issue github.com/datalayer/ju...

📊 First agent in the Datalayer Agent Gallery! We prepared the classic Titanic dataset as an Excel workbook and let the agent analyze it: answering questions, generating chart by executing Python. datalayer.ai/gallery/agen... #AI #Agents www.loom.com/share/60c6c4...

curing cancer by adding a checksum nucleotide to the end of dna

This new release is possible thanks to the amazing opensource community of developers and users. Thank you so much for being part of the journey 🙏❤️ ⋆.˚✮𝕋𝕙𝕒𝕟𝕜 𝕪𝕠𝕦✮˚.⋆

🔓 We built Datalayer around one principle. You should own your AI. 🤖 Models. 🔧 Tools. 🧩 Workflows. Not the other way around. #AI #OpenSource #EnterpriseAI www.loom.com/share/45d1e0...

now reading an article at the intersection of AI Agent harness, loop and meta agents huggingface.co/spaces/joeln...

💡 AI vendor lock-in isn't just about models. It's your workflows. 🛢️Your Data 🧩 Your tools. 📚 Your business knowledge. Those should belong to you. #AI #EnterpriseAI #OpenSource