SupaPM

AI-powered product management assistant with context-aware chat

Think "Cursor for Product Managers and Project Managers". SupaPM is your context-aware AI agent that comes with you in your browser to make everything you do quicker, easier and higher impact. It makes switching contexts easy, giving you the latest context about ongoing projects. It makes it easy to create your own automations and workflows that do the grunt work so you don't have to. Features: - Local-first - your data doesn't leave your browser - Use any tool-calling LLM you like. If a new one comes out, just switch over in seconds - Build your own shortcuts and automations - Create your own skills that your LLM can use to help you get your work donw - Give the LLM your own personal organisational context on how work should be done. What the product does, who's responsible for what, all so that your SupaPM agent can be as helpful as possible in getting your work done --- Latest update ## 0.0.21 Chat now shows what it costs. A subtle running total sits right under the model selector and in the context-usage popover, priced automatically using each provider's published rates — no setup needed for OpenAI, Anthropic, or Google models. You can also add an optional AI Classifier key to speed up chat: a fast, cheap routing step decides which tools a message likely needs before the main model call, so simple turns skip the full tool list. Provider key management in Settings gained a "Test key" button and per-model pricing you can override. - Sidepanel chat shows a muted "Conversation cost" line under the model selector, and a fuller breakdown in the context-usage popover — both are running totals across the whole chat, not just the latest turn. - Session cost is priced automatically out of the box for every current OpenAI, Anthropic, and Google model using each provider's own published rates (including the discounted rate for cached input and the premium rate for cache writes), sourced from their pricing pages. Turns using a model with no known price are excluded from the total rather than assumed free. - Settings → AI Configuration now has a "Test key" button on every provider (OpenAI, Anthropic, Google, Custom endpoint, and the new AI Classifier) that makes a minimal live call to confirm the key actually works before you rely on it. - Settings → AI Configuration now shows per-model pricing directly in each provider's key modal, pre-filled with the published rate and editable if your account has a different one; a "Reset to default" link reverts an override. - Added an optional AI Classifier connector (BYO key, same local-only privacy model as your other provider keys): before calling your main model, SupaPM asks a fast/cheap routing model which category of tools a message likely needs, and only sends that category plus a small always-on core. Without a key configured, every tool is sent every time, exactly like before this existed.