An open-source dashboard for Cursor.sh IDE. Log AI code generations, track usage, and control AI models (including local ones). Run locally or use upcoming hosted version.
No reviews yetBe the first to leave a review for Cursor Lens
I get the idea behind this dashboard for AI coding but it feels a bit overhyped given we have other tools doing similar stuff already, logging AI code generations and tracking usage is useful but I'm skeptical about the customization claims and how different it really is from the competition and let's be honest, throwing in support for multiple AI providers while cool doesn't necessarily make it groundbreaking, I'll give it a try but I'm not expecting miracles.
Report
Did we really need another dashboard for AI-assisted coding IDEs, with so many similar tools like GitHub Copilot and Kite already in the market it's hard to see how much a new product adds, the analytics might be useful but what new features can we expect down the line, plus how does it handle security for local AI deployments, seems quite niche, wonder if the market is big enough
Report
I'm interested to see how this open-source dashboard will handle real-time analytics and token tracking because while it sounds promising, I'm not convinced it will live up to the hype and the customizable AI model configurations seem a bit overkill, it would be better if it came with more preset options, anyway curious to hear what other developers think about this approach ain't sure it's the best solution for optimizing AI-assisted coding but lets see if the feedback proves me wrong, happy to try it out and see how it works but got my doubts.
Report
This looks really interesting! I'm curious about the real-time analytics feature you mentioned. How specific can the data get regarding AI interactions? For instance, will it provide insights on which coding patterns are most frequently assisted by AI? Also, could you elaborate on how customizable the AI model configurations are? Looking forward to trying Cursor Lens out!
Hi @alexanderscottwilliams, thanks for the feedback and the questions.
Coding patterns tie closely with what @_ivan1 mentioned as ML capabilities. A path to explore more. I'm willing to hear your ideas on this.
Re. interactions, we have access to full requests being sent and received by Cursor, so except inside Cursor actions (like if the response is accepted or not, ...) we can have good intel on the interactions of the developer with the LLM models.
On LLM configuration, if you mean which LLMs we can support, atm we are using AI SDK by Vercel which lets us customize all major parameters on an API call, even Anthropic's prompt caching is now added and we can do prompt caching to reduce costs for LLM calls.
Report
You're launching an open-source dashboard for Cursor.sh IDE, helping developers monitor and optimize their AI coding workflow in real-time. With Cursor Lens, users can track AI usage, estimate costs, and customize model configurations. Keep driving this innovation forward, empowering developers to make the most of AI tools. 🚀🖥️✨
Cursor Lens
Cursor Lens
Cursor Lens
Cursor Lens