6 projects
agora-mnemo
mnemo - a zero-dependency memory layer for AI agents: value-ranked recall, per-type decay, consolidation, and semantic+lexical auto-mode. Extracted from an autonomous research system running over ~9,000 notes.
agora-agent-receipts
Tamper-evident, third-party-verifiable receipts for AI agent / MCP tool calls
folklore-index
A runnable benchmark of widely-repeated AI / data-science claims, each ruled REPRODUCED / FAILED / NOT_COMPUTABLE.
grounding-firewall
An answer-or-ABSTAIN gate for RAG/agent answers, driven by grounding-DROP sensitivity - catches poisoned-context errors that confidence misses. Zero dependencies.
dae-client
Decision Audit Engine — Python SDK for AI agent audit trails
vault-health
Epistemic Calculus CLI — measure and improve your knowledge vault health
