Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, an append-only log, so you can see exactly what your agent did and why.
This repository also configures its own agents. See what vestige tells them →
Agent Claude Code
Optional Sanhedrin fallback verifier. Decomposes a draft into check-worthy claims, checks high-trust durable Vestige evidence, and returns a pass/veto verdict.
Agent Claude Code
Subconscious subagent that surfaces cross-disciplinary structural parallels from the Vestige memory graph. Invoked by the preflight-swarm.sh UserPromptSubmit hook (Pre-Cognitive Triad v2.3 "Thalamus"). Fresh context, Haiku 4.5, Vestige MCP tool access. Outputs a single XML block or EMPTY.
Agent Claude Code
Optional decision helper that turns Vestige retrievals into concise recommendations. Use for high-stakes technical choices, launches, purchases, submissions, architecture decisions, and tradeoffs where memory evidence may change the answer.