Isioma Anofienam

Deterministic tool enforcement and a hash-chained audit ledger for verifiable agent security.

A deterministic, fail-closed policy layer for autonomous agents. Warden governs every tool call without putting an LLM in the security path, with native integrations for Claude Code, OpenCode, Codex CLI, Copilot SDK, and MCP-connected tools.

Available on npm as the @memstack suite — core, server, CLI, and MCP adapter — the neutral adapter layer above every memory provider.

Open-source TypeScript memory pipeline for AI agents. 21 storage adapters in a single package — from in-memory to pgvector to Mem0 — with a unified interface and token-budgeted context assembly. The ecosystem spans a headless server with HTTP API, a CLI for managing memory environments, and an MCP server that plugs agent memory directly into Claude Code, Cursor, and other MCP-compatible tools.

Turns product claims into replayable reports and a hash-chained evidence ledger.

An evaluation harness for CLI and HTTP products. Val captures real behaviour, verifies deterministic assertions, and can use an independent LLM judge to score evidence against a product claim.

App Store approved — AI baby tracking with embedded vector memory and a proactive Claude-powered co-pilot.

AI-native baby tracking app with a reasoning engine powered by Claude. Parents log feeds, sleep, nappies, and milestones in natural language; a vector-memory pipeline surfaces pattern detection, anomaly flags, and developmental guidance. Approved by Apple for App Store release.