OWASP Agent Memory Guard
https://owasp.org/www-project-agent-memory-guard/
Open-source runtime defense. Enforces YAML policies on every memory read/write. SHA-256 baselines detect tampering, injection, sensitive-data leakage, protected-key modification, rapid-change anomalies. Forensic snapshots + rollback. Reference impl for OWASP ASI06 (Memory Poisoning).
At a glance
- Type
- Declarative YAML policies + SHA-256 baselines
- Tier
- T3
- Created
- 2026-Q1 (OWASP project page set up Q1 2026; v0.2.1 with OWASP branding; v0.3.0 roadmap Q2 2026)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- free / open source
- Funding
- not applicable — OWASP Foundation open-source project; community-maintained
Taxonomy
- storage
- file
- retrieval
- exact-match
- persistence
- long-term
- update
- read-only
- unit
- file
- governance
- auditable
- conflict
- n/a
When to use
Optimised for: governance + compliance + audit + adversarial hardening
Anti-fit: not for hobbyist / non-production use cases
Pros & cons
Pros
Standardized threat taxonomy for memory in agents — closest thing to industry consensus on memory threats.
Cons
Framework / taxonomy, not a tool; adoption depends on practitioner uptake.
Claims & capabilities
v0.3.0 roadmap (Q2 2026): LlamaIndex + CrewAI integrations, Redis + Postgres backends, Prometheus metrics.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- local deployment; Python; run against local memory stores
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — guidance / standard, not a product
- A2A
- not applicable — guidance / standard
- OpenTelemetry
- not applicable — guidance / standard
Similar systems
Other memory governance, privacy & safety in the catalog, ranked by inbound references.
- Acuvity (now Proofpoint) T1
Runtime enforcement targeting memory poisoning, unauthorised execution, identity spoofing per the OWASP LLM threat list. Visibility/control over MCP servers and locally-installed AI tools — the infrastructure layer where memory is most exposed.
- Enkrypt AI T1
Applies guardrails at three points: (1) before write to vector DB, (2) before query reaches embedding model, (3) before response. Detects malicious instructions in stored memory before retrieval; scans for PII/PHI in/out. Text + image + voice modalities.
- HiddenLayer AISec Platform 2.0 T1
Targets the supply-chain / lineage layer rather than runtime memory writes. Model Genealogy tracks training/fine-tuning/modification history — catches poisoning baked in during training. AIBOM generates auditable inventory of model components + datasets. Runtime layer also monitors agentic workflows.
- Lakera Guard / Lakera Red T1
Screens every prompt, response, and retrieved document for indirect prompt injection — primary vector for memory poisoning. Treats memory as untrusted: anything written to or read from memory is adversarial until proven clean. Lakera Red provides "Agent Breaker" gamified red-teaming.
- Mem0 Security / OpenMemory T1
Commercial Mem0 ships SOC 2 / HIPAA, zero-trust access controls, BYOK encryption, real-time monitoring, audit logs, workspace governance as defaults. OpenMemory is the local self-hosted variant (Docker + FastAPI + Postgres + Qdrant) for privacy-first deployments.
- Microsoft Agent Governance Toolkit T2
Cross-Model Verification Kernel (CMVK) requires majority-voting agreement across multiple model calls before a memory-influenced action. Agent OS package intercepts every action (memory included) at sub-millisecond latency. MIT licensed.