NORTHTEKDevs

MCP server with a context ledger: cryptographically signed receipts of exactly which file versions the model was shown. Honest benchmarks: no real-world token savings (-1.4% measured); ~72% applies only to a synthetic re-read loop.

Verified skill memory for AI agents: your agent proves a skill works, then remembers it. MCP server. Memory stores what you saw; Praxis stores what you proved.

Governed Kryos code execution for AI agents — capability-verified compile/run/audit over MCP

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).