Trustworthy memory and security for AI agents. Recall debugging, review queue, OpenClaw session capture, and memory poisoning defence for Claude Code, Codex, OpenClaw, LangChain, and MCP agents.
Persistent memory for Pi agents — one local-or-cloud brain shared across sessions, compactions, and MCP agents
SAIHM production thin-client. Seals client-side via @saihm/client-pro (ML-DSA-65 identity, per-cell AES-256-GCM DEK wrapped under a client KEK, ML-KEM-768 authenticated sharing) and POSTs opaque ciphertext to the blind, non-custodial SAIHM /mcp endpoint.
The open MCP client for SAIHM sovereign agent memory — eight tools (remember · recall · forget · share · govern) any MCP agent uses to reach a SAIHM operator endpoint. Implements the publicly documented SAIHM memory protocol (Independent-Submission Intern
Forge persistent memories for your AI agent. 9 MCP tools + 5 auto-engines. Powered by Shelby decentralized cloud.