Open-source tools that make AI coding agents safer, more transparent, and easier to trust in production workflows.
Stdlib-only safety hooks for Claude Code. Validates bash commands, protects credentials, enforces git discipline, scopes subagents, and guards protected files.
/plugin marketplace add TracineHQ/plugins
/plugin install guard@tracine
SQLite-backed analytics CLI for AI coding sessions. Indexes session logs, full-text search across transcripts, tool-call analytics, and atomic snapshot/restore.
/plugin marketplace add TracineHQ/plugins
/plugin install convo@tracine
Statistical confidence for LLM evaluation. Welch's t-test, Glass's delta, power analysis. Zero-dep JavaScript, scipy-backed Python, cross-validated on every commit.
AI-assisted SAST triage. Prioritizes static analysis findings with LLM reasoning, reduces false positive noise, accelerates security review.
Guard's hooks fire before the tool call. Block dangerous shell commands, credential exfiltration, and edits to protected files before they execute, not after.
Every Guard decision writes to JSONL. Every session writes to SQLite. Full-text search across what your agent actually did, not what it claimed it did.
Real statistics for LLM comparison. Welch's t-test, Glass's delta, power analysis. Cross-validated against scipy on every commit.
