quantifylabs/aegis-memory

Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

Governed memory runtime for AI assistants: policy-before-storage, context admission, memory usage trace, deletion proof, leakage evals, auth adapters, vector backends, observability, evidence bundles, SDK, benchmarks, and agent integrations.

Production-grade AI agent memory and context management platform (monorepo)

Open-source, self-hostable, zero-knowledge memory for AI agents. End-to-end encrypted — the server stores only ciphertext and can't read your agent's memory. Works with any MCP agent .

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.