llm by Simon Willison
Hacker ApprovedShares rank 24 of 86 privilege escalation tools by recommenders
Free command-line tool for sending prompts to cloud and local AI models, often used as a building block in other tools. Critics dislike how it stores template state.
Free command-line tool for sending prompts to cloud and local AI models, often used as a building block in other tools. Critics dislike how it stores template state.
16 people gave an opinion
- recommend it
- 15
- criticize it
- 1
- approval share
- 94%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 15 people recommend itNeeds 10 or more, met.
- 15 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 8 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Good building block for custom tools
“Like I wanted a tool that can summarise different sources quickly, took me ~3 hours to build it using llm + fragments + OpenAI API.”
Comment from 12 Jan 2026 in “Don't fall into the anti-AI hype” “`llm` gives my tool a standard bin to call to invoke completions, and configuring and managing it is the user's responsibility.”
Comment from 10 Jan 2026 in “Ask HN: What's a standard way for apps to request text completion as a service?” “use a lightweight one, such as @simonw's llm”
Comment from 27 Nov 2025 in “Show HN: Runprompt – run .prompt files from the command line” - Comment from 7 Nov 2025 in “I was right about dishwasher pods and now I can prove it [video]”
Works with cloud and local models
“This is of course cross-platform and works with both models accessible through an API and local ones.”
Comment from 10 Jan 2026 in “Ask HN: What's a standard way for apps to request text completion as a service?” “no need for ollama, simonw's llm tool is good enough”
Comment from 31 Mar 2026 in “Anthropic: Claude Code users hitting usage limits 'way faster than expected'” Lightweight and good enough
“no need for ollama, simonw's llm tool is good enough”
Comment from 31 Mar 2026 in “Anthropic: Claude Code users hitting usage limits 'way faster than expected'” “use a lightweight one, such as @simonw's llm”
Comment from 27 Nov 2025 in “Show HN: Runprompt – run .prompt files from the command line”
What people warn about
Each mark is one comment
Dislikes how it stores templates
“I don't like the way it stores template state.”
Comment from 27 Nov 2025 in “Show HN: Runprompt – run .prompt files from the command line” Prefers files in project directory
“I prefer a tool like this to default to storing things in a file or files in the project directory”
Comment from 29 Nov 2025 in “Show HN: Runprompt – run .prompt files from the command line”
Other privilege escalation tools people recommend
The four most recommended other privilege escalation tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
See all 86 privilege escalation tools, rankedWhat people said
17 of the 21 comments that mention it, newest first. Each links to the original comment.
“the LLM was right in both cases”
“I think ~15,000 downloads a day is pretty good”
“It's allowed me to learn things more quickly.”
“it's just an interface to the cloud LLMs”
“no need for ollama, simonw's llm tool is good enough”
“I remain very proud of my current open source projects too”
“Like I wanted a tool that can summarise different sources quickly, took me ~3 hours to build it using llm + fragments + OpenAI API.”
“My https://llm.datasette.io/ tool is from that era though, and it's pretty cool.”
“`llm` gives my tool a standard bin to call to invoke completions, and configuring and managing it is the user's responsibility.”
“This is of course cross-platform and works with both models accessible through an API and local ones.”
“I prefer a tool like this to default to storing things in a file or files in the project directory”
“I don't like the way it stores template state.”
“use a lightweight one, such as @simonw's llm”
“I think llm has the best docs of the Python API of the three.”
“I pipe it to Simon Willison's `llm` tool.”
“It only worked because of your LLM tool.”
“This is especially true if you use something like `llm`”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.