Back to directory
GateMem
Free182GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
About
This toolkit evaluates how LLM agents manage shared memory when multiple users access the same system. It's built for researchers testing memory governance and access control in multi-user AI setups. The benchmark includes test cases that check whether agents properly isolate and protect each user's information.
Key Features
- agent-memory
- ai-safety
- benchmark
- llm-agent
- nlp
Pricing
FreeOpen source. You supply your own LLM API keys.
Categories
General