Tracine builds open-source tools that make AI coding agents safer, more transparent, and easier to trust in production workflows.
| Project | Description | Install | |
|---|---|---|---|
| Guard | guard | Security hooks for Claude Code — path-aware credential, protected-file, and commit-safety guardrails; ships a decision-log CLI for observability | /plugin marketplace add TracineHQ/guard |
| Convo | convo | Claude Code plugin + CLI — auto-indexes session logs to SQLite, FTS5 search, slash commands, and a history-recall skill | /plugin marketplace add TracineHQ/convo or pipx install tracine-convo |
| Triage | tracine-triage | AI-assisted SAST triage — prioritizes security findings with LLM analysis | Coming soon |
- Safe by default — Pre-built guardrails that validate every tool call before execution
- Observable — Query what your AI agent actually did, not what it said it did
- Zero dependencies — Pure Python stdlib. No bloat, no supply chain risk