Credit
The Independent 100 list was curated by dan (@irl_danB) and published on 2026-09-24 at independent.prose.md (announcement). The ranks and section names are his, and number 100 is his open wild-card slot. This study is ours and is not endorsed by him or by anyone on the list.
What they publicly do
Creator of Datasette and co-creator of Django [Verified: simonwillison.net/about]. Writes a near-daily weblog on LLMs and coding agents and ships many Apache-2.0 Python CLI tools around LLMs and SQLite [Verified: simonwillison.net, github.com/simonw].
- X profile: x.com/simonw
- GitHub: github.com/simonw
- Site: simonwillison.net
- Blog: simonwillison.net
Public work
- llm repo Apache-2.0 last activity 2026-09-22 · 12,551 GitHub stars on 2026-09-24
CLI and Python library for calling LLMs, with a plugin system; logs prompts and responses to SQLite [Verified: repo description, llm.datasette.io]
- datasette repo Apache-2.0 last activity 2026-09-25 · 11,481 GitHub stars on 2026-09-24
Tool for exploring and publishing SQLite data [Verified]
- showboat repo Apache-2.0 last activity 2026-03-14 · 1,229 GitHub stars on 2026-09-24
Create executable documents that demonstrate an agent's work [Verified: repo description]
- Agentic Engineering Patterns blog no license stated last activity 2026-09
Living guide to working with coding agents: principles, subagents, git, red/green TDD, 'first run the tests', anti-patterns [Verified]
- The lethal trifecta blog no license stated last activity 2025-06-16
Prompt-injection risk framing: private data + untrusted content + exfiltration channel [Verified: URL resolves]
- llm-typesafe repo Apache-2.0 last activity 2026-09-22 · 13 GitHub stars on 2026-09-24
LLM plugin for TypeSafe's Jev decision model: noul/choice/score questions from the CLI [Verified: simonwillison.net/2026/Sep/22/llm-typesafe]
Licenses of GitHub repositories are from the authenticated GitHub license API on 2026-09-25, one row per repository in evidence/licenses.jsonl (“no license file” means the API found none; “license file present, not recognised by GitHub” means GitHub could not classify it). Other licenses are as the source states. Check the license file before reusing anything.
Relevance to our work
5 of 5 lenses: agents, security, verification, writing, evals
Apache-2.0 tools that are adoptable now (llm, showboat, sqlite-utils), a maintained guide to coding-agent practice, and a clear prompt-injection framing. llm-typesafe connects the llm CLI to TypeSafe's Jev model.
Scored 0 to 5 against the study’s relevance rubric: 5 means public, openly licensed work squarely in our lanes that we could study or adopt now, and 1 means little connection to our work. The score is one reviewer’s judgement of how much this public work bears on our own work. It is not a ranking of people and says nothing about the person or the quality of their work.
What we would study next
- showboat (github.com/simonw/showboat). Executable proof-of-work documents for agents; a model for verifiable work receipts Effort: small.
- Agentic Engineering Patterns guide (simonwillison.net/guides/agentic-engineering-patterns). A maintained source of coding-agent practice; he tags 64 posts under agentic-engineering Effort: medium.
- llm + llm-typesafe (github.com/simonw/llm-typesafe). A worked Jev client to study for failure handling and logging Effort: small.
Before reusing anything: Main repos Apache-2.0 (GitHub license API, 2026-09-25, evidence/licenses.jsonl). simonw/claude-skills and simonw/research report no license: treat as all rights reserved. His blog carries sponsor banners; posts are not licensed for reuse [Inference: no license statement seen].
Sources
- simonwillison.net
- github.com/simonw
- github.com/simonw/llm
- github.com/simonw/showboat
- simonwillison.net/guides/agentic-engineering-patterns
- simonwillison.net/2026/Sep/22/llm-typesafe
- simonwillison.net/2026/Sep/23/bof-agentic-engineering
- simonwillison.net/2025/Jun/16/the-lethal-trifecta
Overall confidence in this record: High. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 32 of people.jsonl.
Limits
Not verified: Did not read showboat's README or test its behavior; lethal-trifecta post body not re-read this pass (URL resolves 200).
This record comes from a first-pass survey of public material by an AI agent session on 2026-09-24, edited for publication on 2026-09-25. Nothing was installed or run for it. Roles, stars and licenses change; see the study’s limits.
Request a correction
Is something about this record wrong or out of date, or would you rather not be covered? Open a correction (a GitHub issue form with this page’s address filled in). A request to remove a record is honoured without argument; accepted corrections are recorded in the changelog with the date.