Solo Developer / in progress
TokenOps
Local-first observability that connects AI coding-agent usage to the work developers actually complete.
- Python
- FastAPI
- SQLite
- React
- AST
- Gemini API
- CLI
THE PROBLEM
What needed to work better
AI coding session logs show activity, but they do not clearly connect that activity to code changes, validation, commits, cost, or rework.
THE DECISION
The choice that shaped it
Keep analysis local and treat attribution as evidence with confidence, rather than presenting a single score as a universal measure of productivity.
HOW IT FITS TOGETHER
A path through the system
- 01Agent session logs
- 02Normalized work units
- 03Code and test evidence
- 04Reviewable report
WHAT EXISTS NOW
The result
A local dashboard that brings Claude Code, Codex, and OpenCode sessions together with code graph changes, validation evidence, commits, and cost.
IN THE BUILD
Details that matter
- Multi-provider ingestion: Claude Code JSONL, Codex sessions, OpenCode SQLite
- Python AST code-graph snapshots with baseline-aware work attribution
- Evidence-weighted session scoring with semantic churn and confidence labels
- Local FastAPI + React dashboard with model efficiency comparison
- Privacy modes, retention purge, and redacted public profile export