Memory poisoning detection primitives for AI agents — pure pattern matchers (RAG trust, agent-role imperatives, tool-output poisoning, capability expansion, injection fingerprints) + opt-in Agentic Control Center event bus. Extracted from chitta-guard.
Cross-referenced across 55 tracked directories
#341
Popularity Rank
2 / 55
Listed In
Growing
Adoption Stage
5/17/2026
First Seen
Gaining traction in the ecosystem
Cross-Posting Opportunities
Could also be listed in these directories:
Ian Webster <[email protected]>
Python wrapper for the promptfoo CLI - LLM testing, red teaming, and security evaluation
LangChain <[email protected]>
Client library to connect to the LangSmith Observability and Evaluation Platform.
wolffiex
SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
...more