MemTensor's AI memory tooling suffered a security breach affecting the MemoryOS library and associated plugins, including MemoryOS==2.0.34 on PyPI and certain npm plugin versions, according to the Slo…
A threat actor published four malicious releases of MemTensor's MemOS packages on September 23, 2026, compromising npm package @memtensor/memos-cloud-openclaw-plugin (versions 0.1.21, 0.1.23 and 0.1.2…
A threat actor published malicious releases of MemTensor's MemOS AI memory framework on September 23, 2026, compromising npm packages @memtensor/memos-cloud-openclaw-plugin versions 0.1.21, 0.1.23 and…
Researchers from Shanghai Jiao Tong University and Ant Group have demonstrated a new attack technique called InjecMEM that lets hackers plant hidden instructions in an AI agent's memory with a single …
A developer demonstrates that AI agents lose user preferences between sessions unless memory is stored outside the conversation, and builds a key-value memory system that persists across restarts usin…
Researchers have developed S3MEM, a structured memory framework that improves long-horizon interactive question answering by converting agent trajectories into query-aligned evidence. In tests across …