JS Wei (Jack) Sun

Datasette moves execution off the server: local LLMs and browser plugins

Every URL the pipeline pulled into ranking for this issue — primary sources plus the supporting and contradicting findings each Researcher returned. Inline citations in the issue point back here.

← Back to the issue

Sources

datasette-llm 0.1a11 simonwillison.net

Release: datasette-llm 0.1a11 datasette-llm is the intermediate plugin for Datasette that supports configuring LLMs for use with other Datasette plugins. This release adds support for OpenAI-compatible endpoints, so you can configure Datasette to use an LLM hosted anywhere that talks the OpenAI pseudo-standard web protocol. This means that if you’re running local models with LM Studio or Ollama or llama.cpp (which just hit v1.0.0 ) you can run Datasette via uvx like this: wget https://datasette…

datasette-vega 0.7 simonwillison.net

Release: datasette-vega 0.7 A new release of Datasette’s longest untouched plugin, for rendering charts (using Vega-Lite ) against data in a table or custom query. The last release was in July 2018! I finally bumped it for compatibility with the latest Datasette alphas, plus some cosmetic tweaks to make it work better with Datasette Lite . (Datasette Lite just gained the ability to run JavaScript plugins like this! I’ll write more about that soon.) Since it works with Datasette Lite, the live d…

References

mlq.ai on llama.cpp v1.0.0 mlq.ai

The v1.0.0 server implements new protections against Server-Side Request Forgery (SSRF), Cross-Origin Resource Sharing (CORS) misconfigurations, and DNS-rebinding attacks… defaults to port 9931 (moving away from the common 8080).

Medium (Data Science in Your Pocket) — llama.cpp v1.0.0 medium.com

It adds support for FP8 (E4M3) key-value caches, which significantly reduces the VRAM required for long-context windows… For Mixture of Experts (MoE) models, a new expert cache allows weights to spill into system RAM.

MotherDuck — Agentic SQL with Qwen3.8-27B motherduck.com

In the DABstep SQL benchmark, it surpassed models like GPT-5.6 Luna in accuracy while operating at a fraction of the cost—roughly 50 cents in electricity per task.

cloudaitradingagent.com — datasette-llm allowlist bypass watch.cloudaitradingagent.com

On the agent.datasette.io demo environment, this allowed users to select and invoke LLMs that were not explicitly included in the restricted allowlist… patched on November 4, 2026, with the release of datasette-llm version 0.1a10.

datasette.io blog — Datasette Agent datasette.io

A recursive ‘agentic loop’ to inspect schemas, generate SQL queries, and provide human-readable summaries… the agent must request explicit user permission before executing ‘write’ queries or creating new applications.

MotherDuck — LangChain SQL agent + DuckDB motherduck.com

LangChain faced significant scrutiny in early 2026 due to several high-profile CVEs involving SQL injection and remote code execution in its stateful checkpointing layer… many enterprise teams moved toward DuckDB’s local-first architecture.

Observable — Plot vs Vega-Lite comparison observablehq.com

Vega-Lite uses a high-level JSON schema while Observable Plot uses idiomatic JavaScript functions… Vega-Lite’s declarative JSON makes it highly portable across polyglot environments, but Plot is often praised for ‘sane defaults’ that make it faster for exploratory work.

Observable — Plot library docs observablehq.com

Observable Plot encourages a JS-first approach, often pairing with data-wrangling libraries like Arquero or Apache Arrow to process data before it hits the charting layer — more efficient for large datasets because it avoids the overhead of a proprietary expression parser.

Hacker News discussion news.ycombinator.com

An ideal implementation would ‘take an informed guess’ based on the data types present in a table… the plugin only supports a fixed set of visualizations (bar, line, and scatter) and does not allow custom Vega specifications, which has driven more advanced users toward alternative tools.

datasette.io news datasette.io

datasette-plot, released as a ‘spiritual successor’ to the older Vega plugin, is the recommended standard… the Datasette Agent utilizes the datasette-agent-charts plugin, which is powered specifically by Observable Plot.

BEAVER text-to-SQL benchmark (arXiv) arxiv.org

2026 Text-to-SQL benchmarks like BEAVER highlight that while agentic frameworks are improving, they still struggle with complex private schemas, achieving only about 10% accuracy without human intervention.

Jack Sun

Jack Sun, writing.

Engineer · Bay Area

Hands-on with agentic AI all day — building frameworks, reading what industry ships, occasionally writing them down.

Digest
All · AI Tech · AI Research · AI News
Writing
Essays
Elsewhere
Subscribe
All · AI Tech · AI Research · AI News · Essays

© 2026 Wei (Jack) Sun · jacksunwei.me Built on Astro · hosted on Cloudflare