Graph-Native Infrastructure for Context and Accountable AI Systems

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.

Lightning-fast data access platform designed specifically for AI agents

Temporal knowledge graph + authenticated audit chain for AI coding agents. Prevents hallucinations, repeated mistakes, regressions across 12 runtime adapters (Claude Code, Cursor, Codex, Copilot, Cline, Continue, and more). FIPS 205 hybrid signing (Ed25519 + SLH-DSA), streaming offline reference verifier. Hosted companion: etch.systems.

Native agent-graph runtime written in C++20

A simple method for keeping your context and decisions in one place when working with AI. Markdown files. Works with any model.

Thesis: The Software Collapse Has Already Happened

TrustGraph's web UI, built with React 19, TypeScript, and Vite - includes context graph UX

Recursive learning framework, give any AI agent a self-improvement loop with memory. No fine-tuning, just API calls

Deploy TrustGraph in an OVHcloud Kubernetes cluster using Pulumi

Agentic Air Logistics Control Plane ingests real disruption signals (FAA NAS status, METAR/TAF, NWS alerts, OpenSky ADS‑B) for airports, builds a bi-temporal context graph, and runs a deterministic (12-FSM) multi-agent state machine to emit a governed decision packet with a gateway posture