Eric Charles @echarles.net · 26/09/2026Connect 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 000
Eric Charles @echarles.net · 26/09/2026One more time, amazingly powered by the community. Plenty of great contributions here 💪⚡💚 002
Reposted by Eric CharlesDatalayer @datalayer.ai · 23/09/2026Follow the datalayer-ai feed bsky.app/profile/did:... to learn more about data analysis 011
Eric Charles @echarles.net · 23/09/2026The "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 000
Eric Charles @echarles.net · 23/09/2026Pyramid 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. 000
Reposted by Eric CharlesDatalayer @datalayer.ai · 23/09/2026✨ 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 011
Reposted by Eric CharlesDatalayer @datalayer.ai · 21/09/2026Jupyter 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. 🧵 111
Eric Charles @echarles.net · 20/09/2026Excellent 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 000
Eric Charles @echarles.net · 13/09/2026Sunday morning exercise with Claude Code launching Subagents to reformat docs. Nice view of the hierarchy and details of each Subagent system prompt. 001
Reposted by Eric CharlesDatalayer @datalayer.ai · 05/09/2026🛑 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 011
Eric Charles @echarles.net · 31/08/2026I 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. 000
Reposted by Eric CharlesDatalayer @datalayer.ai · 31/08/2026🚀 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 011
Eric Charles @echarles.net · 31/08/2026🧩 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 👀 000
Eric Charles @echarles.net · 26/08/2026Version 2 lays the foundation for 𝗲𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲-𝗴𝗿𝗮𝗱𝗲 Jupyter MCP. 000
Reposted by Eric CharlesDatalayer @datalayer.ai · 24/08/2026🚀 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 011
Reposted by Eric CharlesDatalayer @datalayer.ai · 21/08/2026⚡ 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...jupyter-mcp-server.datalayer.techReleases | 🪐 🔧 Jupyter MCP Server documentationLatest Release 011
Eric Charles @echarles.net · 20/08/2026🧭 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...datalayer.aiDatalayer ☰ Managed Agent WorkersDatalayer ☰ Managed Agent Workers 000
Eric Charles @echarles.net · 10/08/2026🌊 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 030
Reposted by Eric CharlesDatalayer @datalayer.ai · 07/08/2026📚 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 031
Reposted by Eric CharlesDatalayer @datalayer.ai · 04/08/2026Enterprise 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 011
Reposted by Eric CharlesDatalayer @datalayer.ai · 04/08/2026🥈 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 031
Reposted by Eric CharlesDatalayer @datalayer.ai · 31/07/2026**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 #LLMdatalayer.aiDatalayer ☰ AI Agents for Data AnalysisDatalayer ☰ AI Agents for Data Analysis 021
Reposted by Eric CharlesDatalayer @datalayer.ai · 31/07/2026🚀 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 #OpenSourcejupyter-mcp-server.datalayer.techReleases | 🪐 🔧 Jupyter MCP Server documentationMigration Guide to 1.2.0 141
Reposted by Eric CharlesDatalayer @datalayer.ai · 30/07/2026AI 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 021
Reposted by Eric CharlesDatalayer @datalayer.ai · 29/07/2026🎨 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?loom.comDatalayer ☰ AI Agents for Data Analysis - 29 July 2026Use Loom to record quick videos of your screen and cam. Explain anything clearly and easily – and skip the meeting. An essential tool for hybrid workplaces. 021
Reposted by Eric CharlesDatalayer @datalayer.ai · 29/07/2026🤝 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 042
Reposted by Eric CharlesDatalayer @datalayer.ai · 28/07/2026🪐 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 #AIgithub.comRelease Release 1.1.3 · datalayer/jupyter-mcp-server🚀 Release 1.1.3 🔗 Links PyPI Docker Hub What's Changed fix(execute): track a timed-out execute_code's background task so is_kernel_busy sees it by @AmirF194 in #318 refactor: rename sandbox kern... 032
Eric Charles @echarles.net · 24/07/2026A 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 011
Eric Charles @echarles.net · 23/07/2026For 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. 010
Reposted by Eric CharlesDatalayer @datalayer.ai · 17/07/2026🧠 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.loom.comDatalayer ☰ AI Agents for Data Analysis - 17 July 2026Use Loom to record quick videos of your screen and cam. Explain anything clearly and easily – and skip the meeting. An essential tool for hybrid workplaces. 011
Eric Charles @echarles.net · 14/07/2026Should the mcp server open the #jupyterlab tab on "use notebook" mcp tool invocation? Join the discussion on the github issue github.com/datalayer/ju...github.comuse_notebook opens notebook in JupyterLab UI - unexpected side effect · Issue #218 · datalayer/jupyter-mcp-serverProblem When calling use_notebook, the tool currently triggers docmanager_open to open the notebook in the JupyterLab UI. This feels like an unexpected side effect - use_notebook is conceptually a ... 000
Reposted by Eric CharlesDatalayer @datalayer.ai · 13/07/2026📊 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...datalayer.ai 021
Reposted by Eric CharlesDahlia @robotranny.soy · 12/07/2026curing cancer by adding a checksum nucleotide to the end of dna 530636
Eric Charles @echarles.net · 11/07/2026This 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✮˚.⋆ 000
Eric Charles @echarles.net · 07/07/2026🔓 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...loom.comDatalayer ☰ AI Agents for Data Analysis - 7 July 2026Use Loom to record quick videos of your screen and cam. Explain anything clearly and easily – and skip the meeting. An essential tool for hybrid workplaces. 020
Eric Charles @echarles.net · 04/07/2026now reading an article at the intersection of AI Agent harness, loop and meta agents huggingface.co/spaces/joeln...huggingface.coDon't Train the Model, Evolve the Harness - a Hugging Face Space by joelniklausEvolving an agent's harness, not its model, on Harvey's LAB 000
Eric Charles @echarles.net · 03/07/2026💡 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 120
Eric Charles @echarles.net · 02/07/2026🤖 Managed Agents are becoming the next platform for enterprise AI. The question isn't whether you'll use them. It's whether you'll own them. #AI #AIAgents #EnterpriseAI 100
Reposted by Eric CharlesNikos Vaggalis @nikosvg.bsky.social · 18/05/2026The #Jupyter Notebooks MCP Server by @datalayer.ai is a MCP server implementation designed to act as a bridge between Large Language Models, AI assistants and a user's live Jupyter environment.What does it enable? On IProgrammer: dub.sh/mNFIOeIdub.sh 022
Reposted by Eric CharlesDatalayer @datalayer.ai · 04/05/2026☁️ Clouder is now open source! Create, manage & share Kubernetes clusters across clouds with a simple CLI & Python package. Includes Helm, autoscaling, backups, and even alpha features like container checkpoint (CRIU). Supports AWS, Azure & OVHcloud. 👉 clouder.shclouder.shClouder | ☁️ ClouderClouder is the infrastructure and operations layer for running Datalayer services on Kubernetes. 011
Reposted by Eric CharlesDatalayer @datalayer.ai · 29/04/2026This example highlights the power of Agent Runtimes: a single agent can support multiple output formats seamlessly. From plain text and Markdown to structured JSON and UI-ready payloads, responses can adapt dynamically. ➡️ Build once, deploy everywhere. #AI #Agents #DeveloperTools 121
Eric Charles @echarles.net · 29/04/2026Advancing the integration of Datalayer AI Agents into VS Code 000
Reposted by Eric CharlesDatalayer @datalayer.ai · 28/04/2026🛡️ AgentToolApprovalsExample: human-in-the-loop, in 4 lines. id: demo-tool-approvals tools: - runtime-echo:0.0.1 # auto - runtime-sensitive-echo:0.0.1 # manual approval One agentspec, two tools — runtime-echo ships, runtime-sensitive-echo waits for your 👍. #AIAgents #Datalayer 011
Eric Charles @echarles.net · 27/04/2026Should your AI agent need approval before running a skill—even for something as simple as telling a joke? What do you think? Personally, I believe it should be configurable 🙂 011
Reposted by Eric CharlesDatalayer @datalayer.ai · 27/04/2026Jupyter MCP Server 1.0.2 is out! 🎉 Now supports the default Jupyter stack—no more pinning older collaboration versions. Use the version you want. 👉 github.com/datalayer/ju... 031
