iampantherr/SecureContext
8 stars · Last commit 2026-09-19
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.
README preview
# SecureContext > **SecureContext is the persistent memory, delivery, and security layer for Claude Code.** It gives coding agents project memory that survives every restart, a program/phase layer for delivering long-running projects with orchestrator handoff, a cryptographic audit trail for every tool call, and an HMAC-verified admission gate for Anthropic-style filesystem skills. Runs 100% locally on PostgreSQL + Ollama — no cloud sync, no subscription, MIT-licensed. [](package.json) [](src) [](security-tests) [](https://github.com/iampantherr/SecureContext/actions) [](LICENSE) [](package.json) > **Note for security scanners:** `security-tests/` intentionally contains prompt-injection and tool-abuse payloads — they are red-team fixtures that verify SecureContext blocks those attacks, not live threats. --- ## What is SecureContext? If you use Claude Code on real projects, you have hit these walls: 1. **Every session starts cold.** You re-paste the same files, re-explain the same decisions, re-discover the same gotchas — and pay tokens for the same orientation work over and over.