Memory Poisoning Python Packages

agent-memory-guard

OWASP Foundation web repository

memdebug

See what your AI agent's memory holds, what changed, and put it back. Local-first and agent-neutral. Alpha.

langchain-agent-memory-guard

OWASP Foundation web repository

memwall

Antivirus for AI agent memory - scanner + MCP firewall for memory poisoning (OWASP ASI06)

lagrange-memory

Byzantine Fault Tolerant consensus middleware that protects AI agent memory from poisoning attacks (MINJA, indirect prompt injection). Every write is validated by three independent nodes; stored only on 2/3 agreement.

metaworkers

Open-source governed memory for AI agents: prompt-injection-resistant writes, purpose-bound retrieval, provenance, and tamper-evident audit.

assay-gate

A write-path admission gate for AI agent memory — reject poisoned, contradictory, and stale writes before they enter long-term memory.

ulockai

AI Security SDK for Agents, LLMs & SLMs