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·Browser extension

Leo (Brave)

Hybrid (offline or cloud)

Brave's built-in AI assistant. Configurable to talk to local Ollama out of the box.

Editorial verdict: “Best built-in browser AI for Brave users. Local mode is a checkbox, not a hack.”

Browser extension
Free
MPL-2.0
★ 4.2 / 5
GitHub ★ 18,000
↗ Homepage↗ GitHub

Compatibility at a glance

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

§ Runtimes supported
ollamaopenai-compat
§ OS / platform
macoslinuxwindows
§ Hardware + model hint
Minimum VRAM
4 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 Brave users who already keep a local Ollama instance running, Leo is the fastest path to a browser-native AI assistant that doesn't phone home. Flip a single setting in Brave's preferences, paste your Ollama URL, and you're talking to a local Llama 3.1 8B or similar model — no extension, no API key, no extra daemon. It works on macOS, Linux, and Windows with 4 GB VRAM minimum. The trade-off is that Leo's tooling is deliberately minimal: it handles chat and page summaries, but won't replace a dedicated agent UI like Page Assist for heavy workflows. If you're already committed to Brave and want a zero-friction local assistant, this is the cleanest option available.

✓ Strengths

  • +Built in — no extension to install
  • +Local Ollama mode is officially supported, not a community hack
  • +Privacy stance is consistent with Brave's overall brand

△ Caveats

  • −Brave-only
  • −Limited tooling vs Page Assist for power users

About the Browser extension category

Browser extension that uses your local model.

§ Other browser extension apps
Page Assist

Best 'sidebar AI' browser extension that's truly local-first.

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.