← AUTOMATER NEWSROOM

Datasette's Local-Model Agent Path: Streaming Renderers, SQL-Capable Apps and an Access-Control Fix on the 0.65 Line

Datasette's November 2026 releases add OpenAI-compatible local-model support, a sandboxed SQL app layer, streaming renderers, and an access-control fix for the 0.65 line: what operators can actually do with them.

Diagram of the November 2026 Datasette release stack: a SQLite file feeds Datasette core 1.0a43 with its streaming renderers; the core serves a homepage agent prompt and sandboxed SQL apps; the agent or an app calls a local model over an OpenAI-compatible endpoint; and a separate banner notes the 0.65 access-control fix.Diagram of the November 2026 Datasette release stack: a SQLite file feeds Datasette core 1.0a43 with its streaming renderers; the core serves a homepage agent prompt and sandboxed SQL apps; the agent or an app calls a local model over an OpenAI-compatible endpoint; and a separate banner notes the 0.65 access-control fix.
How the November 2026 Datasette releases fit together: your SQLite file stays in place while the homepage agent prompt, sandboxed apps and a local model connect through an OpenAI-compatible endpoint, with the 0.65 line carrying the route-based access-control fix. Drawn from Simon Willison's release notes of 14 and 15 November 2026.

Datasette, Simon Willison’s open-source tool for exploring and publishing SQLite data, shipped seven releases across two days in mid-November 2026. Read one at a time they look like a changelog: a renderer API, a homepage prompt, a sandbox for apps, a geospatial plugin, a compatibility bump. Read together they add up to one thing operators have wanted for a while: a question-answering agent over your own database that can run on a local model, next to apps that query that database with SQL, and one access-control fix that needs attention now.

Vertical flow diagram with five steps: a question typed into the Datasette homepage agent prompt, the agent hash-mentioning a table or saved query and planning SQL, datasette-llm routing to an OpenAI-compatible endpoint such as localhost:1234/v1, a local model on LM Studio, Ollama or llama.cpp returning the answer, and SQL running against the operator's own SQLite file.Vertical flow diagram with five steps: a question typed into the Datasette homepage agent prompt, the agent hash-mentioning a table or saved query and planning SQL, datasette-llm routing to an OpenAI-compatible endpoint such as localhost:1234/v1, a local model on LM Studio, Ollama or llama.cpp returning the answer, and SQL running against the operator's own SQLite file.
The request path enabled by datasette-llm 0.1a11: the model call leaves the process as an ordinary OpenAI-compatible API request, so it can terminate at a local server instead of a vendor endpoint. Steps and endpoint naming come from Simon Willison's datasette-llm 0.1a11 release notes of 14 November 2026.

The local-model path is the real headline

The piece that changes the deployment story is datasette-llm 0.1a11. datasette-llm is the intermediate plugin other Datasette plugins use to reach a model, and this release adds support for OpenAI-compatible endpoints, so the model can be hosted anywhere that speaks that pseudo-standard protocol. The maintainer’s worked example points a Datasette Agent instance at a local model server:

wget https://datasette.io/content.db

uvx --with datasette-agent datasette \
  --root --secret 1 \
  -s plugins.datasette-llm.default_model '{
    "model": "lmstudio-qwen",
    "model_name": "qwen/qwen3.8-27b",
    "api_base": "http://localhost:1234/v1"
  }' content.db

Simon Willison's Weblog post announcing datasette-llm 0.1a11, showing the release notes, the uvx command block that points Datasette Agent at a local OpenAI-compatible model endpoint, and, lower on the page, an embedded Datasette Agent chat demo.
Source: Simon Willison's Weblog, post 'Release: datasette-llm 0.1a11', 14 November 2026. The capture shows the post title, the posting date, the worked uvx command that runs datasette-agent against a local model endpoint at http://localhost:1234/v1, and, in the lower portion of the image, an embedded Datasette Agent chat screenshot showing the question 'how many repos and how many releases are there?' with a sql_query request and its response. · Original source

Lower on the same page, an embedded Datasette Agent chat demo answers “how many repos and how many releases are there?” with a sql_query against the database.

Run that and you have a private agent over a local database: rows never leave the machine, prompts never leave the machine, and the model can be LM Studio, Ollama or llama.cpp, which just hit v1.0.0. That is the practical consequence worth naming: the agent over a private dataset no longer needs a vendor key, an account or an egress rule. For teams already running local models, the LM Studio setup guide and the Ollama local-only lane turn the Datasette agent into a local reader instead of a network call.

Two sharp edges in that snippet are yours to fix. --root switches off the per-user permission model entirely, and --secret 1 is a guessable password. Use them on a scratch database, not on the instance holding anything you care about. The plugin adds no access control of its own; it only changes which endpoint answers.

The agent surface and the app layer

datasette-agent 0.6a0 is, by the maintainer’s description, mostly accumulated small fixes. The one that changes a session: Datasette Agent now puts its prompt directly on the Datasette homepage, with support for hash-mentions of tables and queries. You point the agent at the specific table or saved query you mean instead of describing it, which removes a round of “which table did you mean” from every question.

datasette-apps 0.4a0 is the more interesting half of the pair. Datasette Apps are sandboxed HTML and JavaScript applications that live inside Datasette; the maintainer’s comparison is to Claude Artifacts, except these can run SQL queries against your data. Version 0.4a0 adds linking: an app can be linked to with #fragments in the URL and can read those fragments, and the supported URL schemes are reported back to Datasette Agent.

Diagram of the Datasette Apps 0.4a0 linking model: Datasette Agent writes two separate sandboxed apps over the same data, a search app that lists matching rows and a detail app that renders one record, with the search app linking to the detail app through URL fragments.Diagram of the Datasette Apps 0.4a0 linking model: Datasette Agent writes two separate sandboxed apps over the same data, a search app that lists matching rows and a detail app that renders one record, with the search app linking to the detail app through URL fragments.
The app-linking model added in datasette-apps 0.4a0: an app can be addressed with #fragments in the URL, and the supported URL schemes are reported back to Datasette Agent so it can write apps that link to each other. Drawn from the 15 November 2026 release notes.

Read that as one capability: a search app can hand a row to a detail app, and the agent knows which URL schemes it may use because Datasette tells it. Apps become a composable layer over the same SQLite file instead of one-off embeds.

The core release: streaming renderers and two security fixes

datasette 1.0a43 carries the biggest 1.0 item so far: streaming support for output renderers. The built-in TSV and CSV export mechanisms now use it, and plugins can register themselves as capable of streaming every row of a table in one go through the new Response.stream() method. For operators exporting large tables, that is a memory-profile change, not a cosmetic one.

Simon Willison's Weblog post announcing datasette 1.0a43, showing the post date and the release notes text about streaming support for output renderers and the GitHub advisory for exposed private stored queries.
Source: Simon Willison's Weblog, post 'Release: datasette 1.0a43', 15 November 2026. The capture shows the post title, the posting date, and the release notes describing streaming support for output renderers, the built-in TSV and CSV export using it, and the security fix for private stored queries. · Original source

The release also has two security fixes, one of which the maintainer says deserved a GitHub advisory: private stored queries could be exposed, granting access to the title and SQL of the query, though not allowing that query to be executed. The title and SQL of a saved query can still be the sensitive part of a dataset, so treat it as a disclosure issue.

The 0.65 stable line got the backport that matters most for existing deployments. datasette 0.65.6 fixes a case where a database registered with add_database(db, name=..., route=...), using a route that differs from its name, could be downloaded from /<route>.db by users denied access to it. If you register databases under custom routes, a common way to hide internal names behind friendly ones, that is your configuration. Upgrade the 0.65 line.

The ecosystem signal

datasette-maplibre 0.1a0 is the first new Datasette geospatial plugin in years, combining MapLibre GL with the free OpenFreeMap vector server. The maintainer says he built most of it from a single prompt to Claude Fable 5.2, and that asking the model to “be creative and think outside the box” produced his favorite feature: SVG previews of GeoJSON shapes that load a WebGL preview only when they scroll into view. It also runs in Datasette Lite through Pyodide and WebAssembly.

datasette-vega 0.7 is the quieter release with a related theme: a plugin last touched in July 2018, finally compatible with the current alphas and with Datasette Lite, which can now run JavaScript plugins.

What to do on Monday

Release What changed Practical consequence
datasette-llm 0.1a11 OpenAI-compatible endpoint support Run the agent on LM Studio, Ollama or llama.cpp with no vendor key
datasette-agent 0.6a0 Prompt on the homepage, table and query mentions Fewer clarification round trips, question grounded in one mention
datasette-apps 0.4a0 Fragment linking, URL schemes reported to the agent Apps that link to each other over the same SQLite file
datasette 1.0a43 Streaming renderers and streaming TSV and CSV export Lower memory on large exports, plus a plugin streaming API
datasette 0.65.6 Access-control fix for databases under a custom route Upgrade if you pass a route to add_database()

So: try the local-model path on a copy of a database, with a real secret and without --root; upgrade the 0.65 line if you register databases under custom routes; treat the agent as a reader you point at a specific table rather than a component to hand a production endpoint.

None of this is finished. The 1.0 milestone is 53% complete, these are alphas, and datasette-agent 0.6a0 is a fix release rather than a redesign. Pin your versions, read the release notes before upgrading an instance other people depend on, and treat the app sandbox as a sandbox. The notable part is not the version numbers. It is that the agent, the apps and the data can now live on one machine, in one process, with the model inside your perimeter.

Sources

  1. Release: datasette 1.0a43
  2. Release: datasette-apps 0.4a0
  3. Release: datasette-agent 0.6a0
  4. Release: datasette-maplibre 0.1a0
  5. Release: datasette 0.65.6
  6. Release: datasette-llm 0.1a11
  7. Release: datasette-vega 0.7