Memory observability & monitoring
5 systems in the memory observability & monitoring category of the AI Agent Infrastructure Landscape, grouped by maturity tier.
Tier 1 — battle-tested (3)
- Galileo (galileo.ai) Real-time intent / belief drift detection
Treats memory as first-class in multi-agent tracing. Luna-2 SLMs (3B / 8B) scan every interaction for intent drift and belief drift; 20+ checks at sub-200ms latency. Catches when agent A's view of the world splits from teammate B's. Open…
- Langfuse Memory ops as named spans + Agent Graphs
Memory module reads/writes captured as named spans. Trace Log View concatenates every agent step including memory ops. Agent Graphs (GA 2025) infer graph structure from observation nesting; session-level replay tracks how memory state ev…
- LangSmith Memory mutations as distinct span types
Memory reads, vector DB retrievals, state changes are distinct span types in traces. RAG eval separates retrieval quality (context precision) from generation quality (faithfulness). Dataset versioning guards against eval drift.
Tier 2 — production-ready (2)
- AgentOps Operational metrics for agent memory
When Mem0 is connected, gains Memory Operation Timeline, Search Analytics, Memory Growth tracking, Error Tracking per memory call. Standalone, records context at each step but doesn't analyse memory quality.
- Ratine Offline scanner — memory poisoning detector
Only tool found that scans the persistent memory layer on disk rather than runtime tracing. Detects injected instructions, obfuscated payloads (zero-width Unicode, base64, homoglyphs, hex), C2-pattern URLs, credential leakage. ratine dif…