Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), every tool call lands in a tamper-evident HMAC audit chain, and skills are AST-scanned + HMAC-verified before they run. 100% local: PostgreSQL + Ollama, no cloud, MIT.
Latest release v0.48.1 — v0.48.1 — Temporal block: advisory, not commanding · 23 Jul 2026
1 file for Claude Code: SecureContext CLAUDE.md — 1,689 tokens loaded in every session.
CLAUDE.md A 1,689 tok These files are iampantherr/SecureContext's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.