Page Assist
Browser sidebar that talks to your local Ollama. Summarize pages, chat, vision support.
Editorial verdict: “Best 'sidebar AI' browser extension that's truly local-first.”
Compatibility at a glance
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
What it is
For solo Ollama users who want a browser sidebar that actually talks to their local models, Page Assist is the cleanest integration available. It bridges directly to Ollama (or any OpenAI-compatible runtime) and works fully offline — no cloud account, no data leaving your machine. You can summarize the current page, paste an image at a vision model like LLaVA, or build a small knowledge base from URLs across multiple tabs. It runs as a Chrome or Firefox extension, and with a 4 GB VRAM floor, an 8B Q4_K_M model handles most tasks. The Manifest V3 Chrome rollout had some hiccups in 2024–2025, and the polish isn't at Microsoft Copilot level, but for a free, MIT-licensed tool that keeps your browsing context local, it's the best option right now.
✓ Strengths
- +Truly local-first browser AI
- +Multi-tab knowledge base feature
- +Vision-model support if your local model has it
△ Caveats
- −Manifest-V3 Chrome rollout had hiccups in 2024-2025
- −Smaller polish than Microsoft Copilot sidebar
About the Browser extension category
Browser extension that uses your local model.
Where to go from here
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.