AnythingLLM
Hacker ApprovedShares rank 15 of 27 local LLM runners by recommenders
People recommend it as a plug-and-play front end for chatting with documents and local open source models. The most common caveat is its memory use, with critics noting it takes about 2GB of RAM even when idle.
People recommend it as a plug-and-play front end for chatting with documents and local open source models. The most common caveat is its memory use, with critics noting it takes about 2GB of RAM even when idle.
13 people gave an opinion
- recommend it
- 11
- criticize it
- 2
- approval share
- 85%
Recommended in 8 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 11 people recommend itNeeds 10 or more, met.
- 5.5 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
Runs local open source models
“AnythingLLM + qwen2.5:14b is what I use — good for pattern recognition across metrics you wouldn't think to look for manually.”
Comment from 20 Mar 2026 in “Garmin data archive – local, offline, Ollama-ready” “I just use AnythingLLM with DuckDuckGo + local LLM model to do searches now.”
Comment from 21 Aug 2026 in “I Just Want to Search” “AnythingLLM.com lets you run local open source models.”
Comment from 17 Apr 2026 in “Cloudflare's AI Platform: an inference layer designed for agents” Feature-rich, understands workflows
“Feature-rich orchestrator, not a runner; requires another engine and double memory.”
Comment from 26 Dec 2025 in “Local AI apps worldwide 26 Dec 2025” “understands the workflows a bit more”
Comment from 26 Nov 2025 in “Launch HN: Onyx (YC W24) – Open-source chat UI”
What people warn about
Each mark is one comment
Large memory and install footprint
“Feature-rich orchestrator, not a runner; requires another engine and double memory.”
Comment from 26 Dec 2025 in “Local AI apps worldwide 26 Dec 2025” “AnythingLLM requires about 2GB of RAM, just to be idle”
Comment from 27 Apr 2026 in “Ask HN: Anyone want to collaborate on a local-first AI-based research assistant” “I wasn't a fan of installing a 500MB desktop app”
Comment from 15 Sep 2026 in “Show HN: AirmailAI, a BYOK LLM chat app with a browser extension backend” Needs a separate model engine
“Feature-rich orchestrator, not a runner; requires another engine and double memory.”
Comment from 26 Dec 2025 in “Local AI apps worldwide 26 Dec 2025” Manually selects one model per chat
“Both are excellent tools, but they're manual model selectors — you pick one model and chat.”
Comment from 1 Mar 2026 in “Show HN: I built a desktop app combining Claude, GPT, Gemini with local Ollama”
Other local LLM runners people recommend
The four most recommended other local LLM runners, 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.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| llama.cpp | 471 | 109 | 81% | 13 | 1 yr4 owners | Approved |
| Ollama | 350 | 247 | 59% | 12 | 1.5 yrs8 owners | — |
| LM Studio | 217 | 74 | 75% | 12 | 3 yrs4 owners | Approved |
| DS4 by antirez | 109 | 20 | 84% | 7 | 1 mo3 owners | Approved |
| AnythingLLMThis page | 11 | 2 | 85% | 8 | — | Approved |
What people said
13 of the 14 comments that mention it, newest first. Each links to the original comment.
“I wasn't a fan of installing a 500MB desktop app”
“I just use AnythingLLM with DuckDuckGo + local LLM model to do searches now.”
“anythingLLM (in docker) replaced 90%+ of my AI usage”
“at least they do it with intentionality and direction”
“AnythingLLM requires about 2GB of RAM, just to be idle”
“AnythingLLM.com lets you run local open source models.”
“AnythingLLM + qwen2.5:14b is what I use — good for pattern recognition across metrics you wouldn't think to look for manually.”
“Both are excellent tools, but they're manual model selectors — you pick one model and chat.”
“AnythingLLM for documents, amazing tool!”
“Feature-rich orchestrator, not a runner; requires another engine and double memory.”
“Pretty much plug and play. Used it for simple testing for an idea before getting into the weeds”
“understands the workflows a bit more”
“with an anythingllm web interface in front of it.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.