FankChen/tracecrate
Local-first AI agent trace workbench. Inspect Claude Code, Codex and OTLP logs, compare runs, and export privacy-conscious reports. No backend or API keys.
About the project
Local-first workbench for inspecting AI agent traces: reads Claude Code, Codex and OTLP logs, compares runs, and exports privacy-conscious reports with no backend or API keys.
Useful for
- Inspect a Claude Code JSONL session to find tool errors and long calls.
- Compare two agent runs by recorded metrics and tool calls.
- Export a trace report to JSON or HTML with sensitive data removed.
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 5 stars today.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 3 days old and already has 116 stars.
- Top new repositories this week: #121.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 116
- Stars in a day
- 5
- Forks
- 3
- Issues and pull requests
- 6
- Watchers
- 2
- Language
- TypeScript
- License
- MIT
- Latest release
- v0.2.0 · September 13, 2026
- Created
- September 10, 2026
- Last push
- September 13, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 13, 2026Top new repositories this week: #118
Similar projects
-
6.8
melgarafael/DeskcommCRM
Self-hosted CRM with native AI agents for selling over WhatsApp: agents reply, qualify leads and close sales while your data stays on your server. An open alternative to Kommo, Octadesk and Intercom.
-
6.2
kruzovic7/ai-data-extractor
Python tool that extracts local chat histories from AI coding assistants (Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more) into a single normalized JSONL format.
-
6.2
ayghri/i-have-adhd
A skill for a coding agent (Claude Code) that makes it lead with the answer and numbered steps, without preamble or filler. Helps you get concrete actions instead of long-winded reasoning.
-
6.1
tech-leads-club/agent-skills
A registry of validated skills (instruction plugins) for AI coding agents: extends Claude Code, Cursor, Copilot and others with secure, tested capabilities.
-
6.1
jordan-gibbs/hyperresearch
A deep research harness for Claude Code: turns one prompt into a report with verified citations and a persistent source vault. Every source lands in a searchable store reused by later sessions.
-
6.0
NVlabs/SoL-Pi
An extension for Pi that cuts token usage and redundant turns of coding agents via four mechanisms: action fusion, observation packing, log reduction, and context compaction.