BlazeUp-AI

BlazeUp-AI / pi-insights

Public

Personal usage analytics for Pi coding agent. Temporal-aware insights, context-aware suggestions, model efficiency analysis.

www.npmjs.compackage@observalpi-insights ai-agent analytics insights observability pi-coding-agent
11
1
85% credibility
Found May 26, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Pi Insights is a personal analytics tool for people who use the Pi coding assistant. After you install it, the tool reads through your work history and creates a detailed HTML report showing your coding patterns, efficiency metrics, and costs. The report compares your recent work to previous weeks, spots any unusual spikes in activity, and uses AI to understand what you're actually trying to accomplish. It then gives you personalized suggestions: what new features might help your specific workflow, which bad habits are costing you time or money, and whether you're overspending on AI model choices. The whole thing runs locally on your machine and caches results so re-running is fast.

How It Works

1
💡 Curious about your coding patterns

You've been using Pi to help with coding work and wonder how efficient you've been.

2
📦 Install Pi Insights

You add the tool to your Pi setup with a simple one-line command.

3
🔍 Generate your personal report

You run the insights command and watch as it reads through all your past work sessions.

4
📊 See your work statistics

Your report shows how many sessions you've completed, tokens used, costs, and lines of code changed.

5
Explore different insights
✨
Try new features

See suggestions for tools and skills that would fit your workflow

🛑
Stop bad habits

Learn which patterns are wasting your time or money

💰
Save on costs

See if you're using expensive AI models for simple tasks

🎉 Understand and improve your workflow

You now have clear insights about how you work, what to keep doing, and what to change.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is pi-insights?

pi-insights is a TypeScript analytics tool for the Pi coding agent. It scans your session history, extracts deterministic stats like tokens, cost, and lines changed, then runs LLM-powered analysis to surface patterns in your workflow. The output is a self-contained HTML report showing your coding habits, friction points, and concrete suggestions for improvement. Run it with `/pi-insights` inside any Pi session and it opens in your browser automatically.

Why is it gaining traction?

Most analytics tools give you flat aggregates. This one is temporal-aware: it tracks week-over-week changes, applies decay weighting so recent sessions matter more, and detects whether your patterns are improving or degrading. The "Stop Doing" section is the hook. It tells you what is actually costing you time or money, like using Opus on simple tasks that Sonnet could handle. Context-aware suggestions mean it reads your existing setup and does not recommend what you already have.

Who should use this?

Pi power users who want to understand where their money goes. Developers debugging why their sessions feel slow or expensive. Teams evaluating whether their Pi usage is efficient. If you have hundreds of sessions and no idea what patterns emerge, this is for you.

Verdict

This fills a real gap for Pi users. The credibility score of 0.8500000238418579% signals early-stage software with only 11 stars and minimal community validation. The AGPL-3.0 license may deter some commercial users. Try it if you want data-driven insight into your coding agent habits, but treat it as a personal tool rather than mission-critical infrastructure.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.