# AnythingLLM

11 Hacker News commenters recommended AnythingLLM and 2 criticized it, November 2025 to November 2026. It was recommended in 8 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** 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.

## Why people recommend it

- Runs local open source models (3 comments): "AnythingLLM + qwen2.5:14b is what I use — good for pattern recognition across metrics you wouldn't think to look for manually." ([source](https://news.ycombinator.com/item?id=47455301)) "I just use AnythingLLM with DuckDuckGo + local LLM model to do searches now." ([source](https://news.ycombinator.com/item?id=49391414)) "AnythingLLM.com lets you run local open source models." ([source](https://news.ycombinator.com/item?id=47806655))
- Feature-rich, understands workflows (2 comments): "Feature-rich orchestrator, not a runner; requires another engine and double memory." ([source](https://news.ycombinator.com/item?id=46391671)) "understands the workflows a bit more" ([source](https://news.ycombinator.com/item?id=46061720))

## What people warn about

- Large memory and install footprint (3 comments): "Feature-rich orchestrator, not a runner; requires another engine and double memory." ([source](https://news.ycombinator.com/item?id=46391671)) "AnythingLLM requires about 2GB of RAM, just to be idle" ([source](https://news.ycombinator.com/item?id=47918968)) "I wasn't a fan of installing a 500MB desktop app" ([source](https://news.ycombinator.com/item?id=49717062))
- Needs a separate model engine (1 comments): "Feature-rich orchestrator, not a runner; requires another engine and double memory." ([source](https://news.ycombinator.com/item?id=46391671))
- Manually selects one model per chat (1 comments): "Both are excellent tools, but they're manual model selectors — you pick one model and chat." ([source](https://news.ycombinator.com/item?id=47204557))

## Alternatives hackers recommend

- [llama.cpp](https://hackerapproved.com/p/llama-cpp.md): 471 recommend
- [Ollama](https://hackerapproved.com/p/ollama.md): 350 recommend
- [LM Studio](https://hackerapproved.com/p/lm-studio.md): 217 recommend
- [DS4 by antirez](https://hackerapproved.com/p/ds4.md): 109 recommend
- [Unsloth Studio](https://hackerapproved.com/p/unsloth.md): 94 recommend

## Cite as

Hacker Approved, "AnythingLLM", https://hackerapproved.com/p/anythingllm/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).