RUNLOCALAIv38
->Will it run?Best GPUCompareTroubleshootStartLearnPulseModelsHardwareToolsBench
Run check
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Prompting kits
  • Quick answers
REF
  • All buyer guides
  • Learn local AI
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
← Home·/apps·Chat UI

AnythingLLM

Hybrid (offline or cloud)

Docs-aware chat with workspaces. Drop a folder of PDFs, get a working RAG chatbot in 5 minutes.

Editorial verdict: “Best fast-RAG app. Workspace model is the right abstraction for doc-corpora chat.”

Chat UI
Free
MIT
★ 4.5 / 5
GitHub ★ 34,000
↗ Homepage↗ GitHub↗ Docs

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
ollamalm-studioopenai-compat
§ OS / platform
macoslinuxwindows
§ Hardware + model hint
Minimum VRAM
8 GB
Recommended starter model
Llama 3.1 8B Q4_K_M + bge-m3 embedder
→ Build the rest of the stack with /stack-builder→ Pick a GPU for this app

What it is

AnythingLLM is for anyone who needs to turn a folder of PDFs, markdown files, or plain text into a working RAG chatbot in minutes. Its workspace abstraction—each workspace bundles a chat, a knowledge base, and a model config—is the cleanest implementation of this idea. You point it at Ollama or LM Studio, drop in an 8B model like Llama 3.1 Q4_K_M plus a local embedder like bge-m3, and you’re chatting against your documents with citations back to source passages. The trade-off: default Docker setup can eat disk space for embeddings, and best retrieval quality requires running a separate embedding service. It’s hybrid by default—you can keep everything local or mix in cloud APIs—but the fastest path to a working doc-aware chat is still all-local on macOS, Linux, or Windows with at least 8 GB VRAM.

✓ Strengths

  • +Workspace abstraction is genuinely well-designed
  • +Local + cloud embedding options
  • +Citations link back to the source doc passages

△ Caveats

  • −Default Docker config consumes a lot of disk for embeddings
  • −Best perf needs a separate embedding-model service

About the Chat UI category

Web or desktop chat client that connects to your local runtime.

§ Other chat ui apps
LibreChat

Best if you mix local + cloud models in the same workflow. Strong team features.

Jan

Best one-binary desktop chat. Curated catalog removes 'which model?' decision paralysis.

Open WebUI

Best default chat UI for solo Ollama users. Pick this first; switch only if you outgrow it.

Odysseus

The most visible on-ramp to local AI yet — its hardware-aware Cookbook makes it a genuine beginner pick, but it's young and 'janky' by its own README; treat Agent mode's shell access with caution.

Where to go from here

Stack Builder →

Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.

Back to /apps →

The full directory — filter by category, runtime, OS, privacy posture, or VRAM.

Runtimes (/tools) →

What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.

Community benchmarks →

Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.