Datalayer is writing a paper on cost-effective LLM agents (70–92% token reduction via codemode).
Seeking co-authors with real-world agent data.Read & apply → datalayer.ai/research/con...
#LLMAgents #AIEngineering #OpenScience
Datalayer is writing a paper on cost-effective LLM agents (70–92% token reduction via codemode).
Seeking co-authors with real-world agent data.Read & apply → datalayer.ai/research/con...
#LLMAgents #AIEngineering #OpenScience
Going live in 30 minutes! 🚀
Join my online talk on Reducing LLM Costs Through Programmatic Tooling.
Save your spot: openteams.com/event/reduci...
Actually, not tomorrow, but on Thursday.
🚀 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 OpenTeams. Don’t miss out!
🔗 Register here openteams.com/event/reduci...
#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
rdi.berkeley.edu/agentx-agent...
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! 💡
🔗 datalayer.ai
#AI #DataInnovation #AIAgents #CostEfficiency
⚙️ Run Python notebooks instantly in VS Code with the Datalayer Pyodide kernel — no Python install, no Conda, no setup.
Open a notebook and start experimenting ✨
🎓 Beginners | ⚡ Quick tests | 🔒 Sandbox-safe
Read more 👉 medium.com/datalayer/st...
#VSCode #Python #Jupyter #Pyodide
🧵 1/6 What if your AI agent could actually DO things?
Not just chat. Actually search the web, access databases, read LinkedIn profiles, execute code.
That's what we built. Here's what you can do with Agent Runtimes 👇
We’ve enhanced agent runtimes with a built-in model selector, making it easier than ever to choose the right model for each use case. #AI #LLM
#Agent details now available - we will show the LLM context usage
Inline chat toolbar implemented in the Agent Runtimes repository (github.com/datalayer/ag...
). It provides an easy way to work with your text content.
1/ Jupyter UI documentation got a refresher
If this makes sense to you, you’re the target audience 👇
<JupyterReactTheme>
<Notebook path="analysis.ipynb" />
</JupyterReactTheme>
jupyter-ui.datalayer.tech
5/ Built on @datalayer's battle-tested Jupyter React library. Full Jupyter ecosystem compatibility.
Try it → jupyter-embed.datalayer.tech
#Jupyter #Python #OpenSource
4/ Use cases:
🎓 Education - students run code in course materials
📚 Docs - executable API examples
🔬 Research - reproducible analyses
🤝 Collaboration - code that works in any browser
3/ What you get:
🧪 Interactive code cells
📓 Full notebooks
💻 Terminal sessions
🖥️ REPL consoles
📊 Rich outputs
2/ Add interactive Python cells, notebooks, terminals & consoles to ANY website with just HTML.
No React. No build tools. Just:
```html
<div data-jupyter-embed="cell">
<code>print("Hello!")</code>
</div>
```
1/ 🪐 🌐 Just shipped: Jupyter Embed!
What if adding a live Python cell to your docs was as easy as adding an image?
Now it is. 🧵
🚀 Jupyter MCP Server docs just got a refresh!
Flattened TOC, new Reference & Providers sections, added JupyterHub + Google Colab providers (WIP), and more on security & multi-user use cases.
Docs: jupyter-mcp.datalayer.tech
Feedback welcome! 💬
🪐 Jupyter Embed is here!
Add interactive Python cells, notebooks & terminals to ANY website with a simple script tag.
🎯 Live demo: jupyter-embed.datalayer.tech
Built with ❤️ for educators, developers & data scientists.
#Jupyter #Python #OpenSource
The Jupyter UI docs just got a fresh revamp ✨
Now with embedded Storybook—take a look!
👉 jupyter-ui.datalayer.tech
this blog really nails a few things I’ve noticed about good architecture/coding practices for using agents, big recommend.
bits.logic.inc/p/ai-is-forc...
Year-end confettis are here 🎊 Explore them in the Jupyter UI Storybook 👉 jupyter-ui-storybook.datalayer.tech?path=/story/...
Jupyter React 2.0 is live! 🎉
Breaking changes: Notebook2 is now default, kernel setup moves to useJupyter(). See migration examples github.com/datalayer/ju...
I guess human review and test coverage help
I've added a tree view to pick files in Toad. 🐸
Fuzzy searching is great when you know what you're looking for. But a tree view is more natural when you want to look through your files.
Toad is a unified interface for agentic coding, and all things AI, in your terminal.
github.com/batrachianai...
1.5 days with #AI instead of maybe 1.5 weeks: Vite.js support and a revamped Jupyter React examples. AI is redefining software development timelines.
Devil’s in the details. This is why you’ll see a spinner in the VS Code runtime launcher while the remote runtime spins up.
Vercel AI SDK 6 is official released. The details are on vercel.com/blog/ai-sdk-6
The feature I prefer is the Tool Improvements and the needsApproval option that allows to force user approval on the first tool usage.
OAuth for MCP is also awesome feature.
The question you never asked yourself - sculptures that write sentences, by Fred Eerdekens.
www.fred-eerdekens.be/work/detail/...
Datalayer is joining the AgentX AgentBeats challenge! 🥊
To benchmark our data agent, we "agentified" DABench using the A2A protocol. The setup uses Pydantic AI and our Jupyter MCP Server.
We think A2A + MCP is the future of agent interoperability. 🤝
github.com/datalayer-ch...
#AgenticAI #MCP