TAG
Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.
Move both the checklist and the verdict outside the model. Slot-based preconditions for irreversible tool calls — execution reads a verdict record, never a conditional.
Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.
The open-source autonomy kernel MELRA — Modular Execution Layer for Reliable Autonomy. An agent-independent effect runtime for governed, durable, and verifiable autonomous execution. MELRA begins where the tool call leaves the model loop.
