Eric Charles

Disrupt or die @DatalayerIO

[Eric Charles @echarles]

Moved to https://t.co/SYeG32fBCy

[Datalayer @DatalayerIO]

Big news: @pydantic is donating the FastA2A repo to Datalayer. We'll take over maintenance and evolution of this MIT-licensed A2A framework, building on recent streaming collaboration. Focus: A2UI, Jupyter sandboxes, and agent-to-agent infra. 🚀

https://t.co/PlIMoiZMQx

[Datalayer @DatalayerIO]

☁️ 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.

👉 https://t.co/R5RoZrQvmN

[Datalayer @DatalayerIO]

This 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

[Eric Charles @echarles]

Advancing the integration of Datalayer AI Agents into VS Code

[Datalayer @DatalayerIO]

🛡️ AgentToolApprovalsExample: human-in-the-loop, in 4 lines.

id: 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

[Eric Charles @echarles]

Should 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 🙂

[Datalayer @DatalayerIO]

Jupyter MCP Server 1.0.2 is out! 🎉 Now supports the default Jupyter stack—no more pinning older collaboration versions. Use the version you want.

👉 https://t.co/SesMiGagtg

[Eric Charles @echarles]

Let's connect on the GitHub if you are a AI engineer or developer, or on https://t.co/ZIQw7vAmRM if you are a user looking for managed #AIAgents ready to be used.

[Datalayer @DatalayerIO]

Agent runtimes, by example.
Explore UX, guardrails, tooling, collaboration & more—each as deep, pluggable building blocks.

Try it, contribute, ⭐ your favorite:
https://t.co/LcsXJZbl21

[Eric Charles @echarles]

Thank you to all the amazing contributors and users for making this opensource project a success 🙏

[Datalayer @DatalayerIO]

Jupyter MCP Server 1.0.0 Reaches 1,000 GitHub ⭐

Right after the official 1.0.0 release, the Jupyter MCP Server repository crossed the 1K stars milestone. A huge thank you to the community building the future of notebook-native AI workflows.

https://t.co/SesMiGagtg

[Datalayer @DatalayerIO]

LLM apps in prod need more than accuracy—they need cost visibility.

Tokens drive spend, but most systems lack insight.

Datalayer’s open-source agent-runtimes adds runtime-level tracking, OTEL pluggability & React charts—works with any LLM.

PR: https://t.co/QZG6X2v9fB

[Datalayer @DatalayerIO]

📄🌍 Published in #IEEE GRS Magazine (2026): “Artificial Intelligence for Earthquake Response.”

Datalayer ranked 2nd overall 🥈 in ESA + International Charter challenge.

Paper: https://t.co/U93l5QvmnX
DOI: https://t.co/SfbS38Rozv

[Datalayer @DatalayerIO]

We just opened a Discord for builders working with Datalayer AI Agents 🧠⚡

No marketing fluff—just real workflows, early features, and direct access to our team.

If you’re building or exploring, come join us 👇
https://t.co/DXyX7mWwyt

[Datalayer @DatalayerIO]

🚀 Jupyter MCP Server v0.23.0 is out!

Better notebook interactions, improved tool consistency, and more reliable execution ⚡

Thanks to all contributors 🙌
🔗 https://t.co/h8vyN7HorY
#Jupyter #AI #MCP

[Datalayer @DatalayerIO]

Datalayer is writing a paper on cost-effective LLM agents (70–92% token reduction via codemode).

Seeking co-authors with real-world agent https://t.co/YvdMCZDx3O & apply → https://t.co/Iy93Oxhiaz

#LLMAgents #AIEngineering #OpenScience

[Eric Charles @echarles]

Going live in 30 minutes! 🚀
Join my online talk on Reducing LLM Costs Through Programmatic Tooling.

Save your spot: https://t.co/cj9LJcdRN9

[Eric Charles @echarles]

@openteamsinc Actually, not tomorrow, but on Thursday.

[Eric Charles @echarles]

🚀 Cut your LLM costs by up to 90%!

Join me tomorrow for a practical deep dive on programmatic tools that make AI faster, smarter, and cheaper.

Hosted by @openteamsinc . Don’t miss out!

🔗 Register here https://t.co/YUw5rGaF05

[Eric Charles @echarles]

#AgentBeats Phase 1 (Green Agents) judging is almost done.

A competition focused on standardized, reproducible AI agent evaluation.

Winners announced early next week — hoping to make the run into Phase 2 🤞

Organized by @BerkeleyRDI

https://t.co/gltSFBI4me

[Eric Charles @echarles]

Our new Datalayer variant is built for AI Agent workloads—cutting data costs by up to 90% without sacrificing performance.

Scale smarter, faster, and cheaper! 💡

🔗 https://t.co/ZIQw7vAUHk

#AI #DataInnovation #AIAgents #CostEfficiency

[Datalayer @DatalayerIO]

⚙️ Want to run Python notebooks instantly? With Datalayer VS Code Extension, you can use a Pyodide-powered browser kernel — no Python install, no Conda, no setup.

Open a notebook and start experimenting ✨

Read more 👉 https://t.co/bUXKYKcIGX

#VSCode #Python #Jupyter #Pyodide