AI Potluck
Product / UX / UI & API

LLM (Datasette)

Datasette

Command-line tool and Python library for interacting with large language models. Provides a unified CLI and API to send prompts to remote models (OpenAI, Anthropic, Gemini, Llama, etc.) and to local models, with a plugin architecture for adding new backends. Logs prompts and responses to a local SQLite database and supports embeddings and templated prompts. Part of Simon Willison's Datasette ecosystem (docs at llm.datasette.io).

Apache-2.0 (verified LICENSE body). Latest release v0.31 (~24 Apr 2026, PyPI/GitHub). ~12.1k stars. Canonical repo under the personal simonw account; branded under the Datasette ecosystem. Verified 2026-06-19.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public(GitHub)
core-gated
ungated

Apache-2.0 verified against LICENSE body; full source public; CLI/library with no gated tier (model providers need their own API keys, external to the tool).

Adoption

3 medium confidence
3.0

Established CLI/library distributed on PyPI (package 'llm', v0.31) with ~12.1k GitHub stars and a broad plugin ecosystem; widely used across Simon Willison's tooling. No exact monthly download figure captured, so placed at 3 on PyPI-presence + ecosystem signal.

Capability

3 high confidence
3.0

Strong on model breadth and extensibility, but a developer CLI/library rather than a multi-user surface; lacks the built-in RAG/multimodal/auth feature stack of top ui_api entries, so scored 3.

  • https://llm.datasette.io/ recorded 2026-06-19

    docs: unified CLI/Python API for remote+local models, plugins, embeddings, templates, SQLite logging

Unchanged since 2026-07-30 (last edited, not re-checked)