claude-code-karma
Provides visibility into Claude code session activity, resource usage, and patterns—enabling teams to optimize workflows, identify bottlenecks, and make data…
A local-first, open-source dashboard that turns the data in your ~/.claude/ folder into a visual view of your Claude Code sessions — timelines, costs, token usage, file changes, subagents, tasks, and live activity. Runs entirely on your machine (Python API plus a SvelteKit frontend); no cloud, accounts, or telemetry.
- Monitor Claude code generation sessions in real-time across your team
- Track code quality metrics and performance from multiple Claude interactions at once
- Identify bottlenecks in Claude-assisted development workflows visually
Provides visibility into Claude code session activity, resource usage, and patterns—enabling teams to optimize workflows, identify bottlenecks, and make data-driven decisions about AI-assisted development practices.
Engineering teams integrating Claude into development pipelines who need session-level observability and performance metrics.
https://github.com/JayantDevkar/claude-code-karma
By JayantDevkar
How to Get It
git clone https://github.com/JayantDevkar/claude-code-karma.git cd claude-code-karma # Terminal 1 — API cd api && pip install -e ".[dev]" && pip install -r requirements.txt && uvicorn main:app --reload --port 8000 # Terminal 2 — frontend cd frontend && npm install && npm run dev # Open http://localhost:5173
After installing, paste this into Claude:
Help me monitor Claude code generation sessions in real-time across my team
Trust Signals Auto-scanned
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 228 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 228 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.