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·Eruo Fredoline
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
  • Suggest a feature
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·RAG app

Khoj

Hybrid (offline or cloud)

Self-hosted AI assistant for your notes, emails, docs. Web + mobile + desktop, all local-first.

Editorial verdict: “Best 'AI second brain' app. Self-hosted, local-first, works against Obsidian.”

RAG app
Freemium
AGPL-3.0
★ 4.3 / 5
GitHub ★ 18,000
↗ 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
ollamallama-cppopenai-compatanthropic
§ OS / platform
linuxmacoswindowsiosandroidweb
§ Hardware + model hint
Minimum VRAM
8 GB
Recommended starter model
Llama 3.1 8B Q4_K_M
→ Build the rest of the stack with /stack-builder→ Pick a GPU for this app

What it is

For solo users running Ollama on a laptop or desktop, Khoj turns local notes, emails, and PDFs into a searchable chat interface. It bridges directly to Ollama or llama.cpp, and works well with an 8B model like Llama 3.1 8B Q4_K_M on 8 GB VRAM. The Obsidian integration is its strongest feature—indexing is local-first, with cloud sync as an opt-in fallback. Cross-platform coverage (web, iOS, Android, desktop) is genuine, not an afterthought. Be aware that indexing a large corpus is slow on initial run, and features like image generation require cloud.

✓ Strengths

  • +Genuinely cross-platform (mobile apps work)
  • +Strong Obsidian integration
  • +Self-host + cloud sync is well-designed

△ Caveats

  • −Initial index of a large corpus is slow
  • −Some niche features (image generation) require cloud

About the RAG app category

Document retrieval + chat, fully offline-capable.

§ Other rag app apps
PrivateGPT

Best when air-gap compliance is the requirement. Less polished than AnythingLLM, more configurable.

Verba

Best for 'don't make me choose chunking strategy' teams. Opinionated stack works.

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.