AI Potluck
Contribute
Back to Gap Map Product / UX / UI & API

LLM (Datasette)

Datasette
open source / Overall score: 3.0

Command-line tool and Python library for prompting large language models. It provides one CLI and API across remote providers such as OpenAI, Anthropic and Gemini and across local models, with a plugin architecture for new backends. Prompts and responses are logged to a local SQLite database, and it supports embeddings and templated prompts. Part of Simon Willison's Datasette ecosystem.

The canonical repository sits under a personal account rather than a Datasette organization.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public(GitHub)
core features withheld
no

The full source is public, and the tool installs from PyPI or Homebrew with no gated tier. Model providers require their own API keys, which sit outside the tool.

  • https://cdn.jsdelivr.net/gh/simonw/llm@main/LICENSE recorded 2026-09-29

    Repository LICENSE file on the main branch, headed "Apache License" and "Version 2.0, January 2004", with the section "TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION".

  • https://cdn.jsdelivr.net/gh/simonw/llm@main/pyproject.toml recorded 2026-09-29

    Project metadata for version 0.36 declaring the license as "Apache-2.0" and describing the package as "CLI utility and Python library for interacting with Large Language Models"; the runtime dependency list holds open-source packages such as click, openai, pydantic, sqlite-utils, PyYAML and pluggy, with no proprietary or license-key dependency.

  • https://cdn.jsdelivr.net/gh/simonw/llm@main/README.md recorded 2026-09-29

    Repository README opening with "A CLI tool and Python library for interacting with" many models and install steps "pip install llm", "brew install llm" and "uv tool install llm"; a search for enterprise, license key, pricing, subscription, premium and proprietary found nothing.

  • https://github.com/simonw/llm/blob/main/LICENSE recorded 2026-08-13

    Apache License 2.0 full text

Adoption

3 medium confidence
3.0

LLM's adoption is measured as PyPI downloads of the llm package over a trailing 30 days, a direct installation count. It is an established CLI and library with a broad plugin ecosystem, used widely alongside Simon Willison's other Datasette tools.

Capability

3 high confidence
3.0

Plugins give it access to many remote and local models, and it adds embeddings, tools and structured extraction from text and images. It is a developer command-line tool and library rather than a multi-user chat interface.

  • https://llm.datasette.io/ recorded 2026-09-29

    Docs home page describing LLM as "A CLI tool and Python library for interacting with" many models, "both via remote APIs and with models that can be installed and run on your own machine", with "Store prompts and responses in SQLite", "Generate and store embeddings", "Extract structured content from text and images" and "Grant models the ability to execute tools".

  • https://llm.datasette.io/en/stable/plugins/directory.html recorded 2026-09-29

    Plugin directory page with sections headed "Local models", "Remote APIs", "Fragments and template loaders" and "Embedding models".

Verified 2026-09-24