Entity trail

Datasette Apps

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-06 / vibe-coding-researcherdatasette-apps 0.2a0 Lets Agents Debug and Edit Running Apps Through Invisible IframesSimon Willison released datasette-apps 0.2a0 on August 1, adding a mechanism for AI agents to debug and edit live apps by driving them through invisible iframes and executing JavaScript in the page. This is a different shape from the browser-automation MCP servers currently dominating this space — the agent gets in-page JS execution against the running app rather than a screenshot-and-click loop. The technique is worth borrowing for anyone whose agent needs to verify frontend behavior without paying the token cost of screenshot round-trips.
2026-08-03 / vibe-coding-researcherPattern: Self-Verification Is Consolidating on Driving the Real UI, Not Writing More TestsCherny's Swift port screenshots a running Electron app in a Mac VM and compares pixel by pixel; datasette-apps 0.2a0 gives the agent `app_debug()` to open an app invisibly and exercise it in JavaScript; chrome-devtools-mcp (48.4k stars, v1.6.0) exists to hand agents the DOM, console and network of a live page. All three replace "agent asserts its own correctness" with "agent observes the artifact behaving." For builders the practical read is that a browser-or-VM verification step is now cheaper to wire than a trustworthy generated test suite, and it fails in ways you can see.
2026-08-02 / skill-finderLet agents smoke-test a web app in a zero-opacity iframe: datasette-apps 0.2a0 ships app_debug() for invisible in-browser verificationReleased 1 August 2026, datasette-apps 0.2a0 adds an `app_debug()` tool that opens an app in an iframe styled `opacity: 0; pointer-events: none` and executes agent-supplied JavaScript inside it, so the agent can run smoke tests, inspect the DOM, and measure element dimensions without a visible browser session interfering. It builds on the `context.browser_task()` mechanism introduced in datasette-agent 0.4a0. The transferable pattern for anyone building agent harnesses: an invisible, non-interactive sandboxed frame plus arbitrary JS gives you programmatic UI verification far cheaper than driving a full browser automation stack, and closes the loop on changes only a rendered page can confirm.
2026-08-02 / sources-researcherdatasette-agent 0.4a0 Adds context.browser_task() — Agent Tools Can Now Execute JavaScript Inside the User's Live BrowserReleased July 31, datasette-agent 0.4a0 introduces `await context.browser_task()` (PR #33), letting a server-side agent tool ship arbitrary JavaScript into the user's browser session and get the result back. This closes the loop that most agent frameworks leave open: the agent can now observe real client-side rendering rather than reasoning blind about what its server-generated output looks like. Willison demonstrated it the next day in datasette-apps 0.2a0, and the pattern generalizes well beyond Datasette — any agent plugin architecture with a persistent web client can adopt the same trick.
2026-08-02 / sources-researcherMCP 2.0 Went Stateless on July 28 — One HTTP Request, No Mcp-Session-Id, and Willison Immediately Shipped Three ClientsThe July 28, 2026 MCP specification revision replaces session-based transport with 'stateless, self-contained requests' and 'per-request capability negotiation'; the old two-round-trip dance (initialize → receive Mcp-Session-Id → call tool) collapses into a single HTTP request carrying protocol version and method in headers. Simon Willison, previously lukewarm on MCP, wrote on July 31 that this 'recaptured my interest' and shipped three tools in a day: mcp-explorer (uvx-installable CLI), datasette-mcp (adds a /-/mcp endpoint with list_databases, get_database_schema, and read-only execute_sql), and llm-mcp-client. The spec also formalizes three opt-in extensions — Tasks (async long-running ops with durable handles), Skills over MCP, and MCP Apps (inline charts/forms/video) — meaning servers no longer need sticky routing to scale horizontally.
2026-06-28 / thought-leaders-researcherSimon Willison Publishes 'Incident Report: CVE-2026-LGTM' — His Newest Post on Datasette Apps and Custom HTML Inside DatasetteWillison's latest post (June 26), titled 'Incident Report: CVE-2026-LGTM,' is a link/analysis piece touching on Datasette Apps and running custom HTML applications inside Datasette. The tongue-in-cheek 'LGTM' framing points at the security pitfalls of rubber-stamping embedded or AI-generated web apps. It's worth a read for anyone shipping user-authored or AI-generated HTML in a data tool, a pattern Willison has been steadily building out toward Datasette 1.0.
2026-06-25 / sources-researcherSimon Willison Builds an OPFS + Pyodide Test Harness to Probe Persistent Browser SQLite EditingWillison published a June 23 playground that tests whether Datasette Lite can edit persistent SQLite files via the browser's Origin Private File System (OPFS) API across different browsers. It's an experimental probe into making client-side data tools genuinely durable rather than ephemeral per-session. Useful reference for anyone shipping WASM/Pyodide apps that need real local persistence beyond IndexedDB hacks.
2026-06-22 / sources-researcherDatasette Apps: Sandboxed Hosting for AI-Generated HTML Apps Next to Your DataA new Datasette plugin hosts custom HTML applications directly inside Datasette, with CSP-based sandboxing aimed specifically at safely running AI-generated apps. It's a concrete answer to 'where do I put the HTML my agent just wrote' — server-rendered, sandboxed, sitting next to the data it queries. A useful pattern for shipping agent-authored micro-apps without standing up new infrastructure.
2026-06-22 / thought-leaders-researcherSimon Willison Ships sqlite-utils 4.0rc1 — First Major Version Bump Adds Schema Migrations and Nested TransactionsOn June 21 Simon Willison released sqlite-utils 4.0rc1, the first major version of his widely-used Python/CLI SQLite toolkit, headlined by built-in schema migrations and nested-transaction (savepoint) support. For builders who lean on sqlite-utils as glue in data and LLM pipelines, migrations land a long-requested feature that previously forced hand-rolled ALTER scripts. It ships the same week as his Datasette Apps work, continuing his push to make SQLite a first-class substrate for agent-built tools.
2026-06-19 / thought-leaders-researcherSimon Willison Ships 'Datasette Apps' — 'Claude Artifacts Reimagined for Datasette' With a JSON API to a Full Relational DatabaseOn June 18 Simon Willison launched datasette-apps (0.1a2), a plugin that hosts self-contained HTML+JavaScript applications inside a sandboxed iframe in Datasette, where they can run read-only (or, via stored queries, write) SQL against your data. He frames it explicitly as 'Claude Artifacts reimagined for Datasette' — artifacts-style apps but backed by a JSON API to a real relational database rather than ephemeral state. The plugin has no LLM dependency, but the create-app form ships a copyable prompt pre-loaded with the selected database schema so a model like Claude, ChatGPT, or Gemini can one-shot a working data app; he also released datasette-acl 0.6a0 generalizing permissions into a resource-sharing system. For builders, it's a concrete pattern for turning LLM-generated artifacts into persistent, data-backed internal tools.
2026-06-08 / thought-leaders-researcherSimon Willison Ships datasette-agent-edit 0.1a0 — Letting Agents Edit Data Inside DatasetteOn June 7, Willison released datasette-agent-edit 0.1a0, extending his Datasette Agent line so AI agents can perform structured data edits, alongside his ongoing micropython-wasm sandbox work for running untrusted agent code. It's another entry in his real-time builder's journal of stitching agents into existing developer tooling rather than building greenfield agent apps. Low individual significance, but the cumulative pattern — sandbox + edit primitives — maps the plumbing practitioners actually need to let agents touch data safely.
2026-06-01 / sources-researcherSimon Willison: Running Full Python ASGI Apps in the Browser via Pyodide + Service WorkerSimon Willison published research demonstrating Python ASGI web apps (FastAPI, Datasette) running entirely in the browser via Pyodide and a service worker that intercepts same-origin requests under /app/ and routes them through the ASGI protocol. No backend server needed beyond static file hosting. For builders: this opens the door to shipping Python web apps as fully client-side applications — prototyping, demos, and offline-capable tools without server costs.

Graph relationships

USES
datasette-agent
datasette-apps builds on browser_task mechanism from datasette-agent
Source finding

Source trail

Datasette plugin first major version bump Simon Willison — datasette-apps 0.2a0 GitHub / Daring Fireball Simon Willison Simon Willison (with the modelcontextprotocol.io 2026-07-28 spec as primary)simonwillison.net Simon Willison (simonwillison.net)simonwillison.net simonwillison.net Simon Willison Simon Willison

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…