iampantherr/SecureContext
8 stars · Last commit 2026-08-01
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) --- ## 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. 2. **Long projects have no delivery state.** When an orchestrating agent dies mid-feature (crash, closed window, exhausted context), its replacement starts blind. People compensate with hand-written CHECKPOINT files. 3. **There is no record of what agents actually did.** When something goes wrong, Claude Code has no tamper-evident history of what ran.