Enkrypt AI
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. Acquired by Anaconda (2026-08-04); Enkrypt AI is now sold as Anaconda's AI security and guardrails product.
Acquired · Verified 2026-10-29 · fresh as of 2026-10-29 · 43 cited facts, 6 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Three-point RAG / memory pipeline guardrails vendor fix
- Tier
- T1
- Created
- 2022 (founded 2022 by Sahil Agarwal and Prashanth Harshangi; Yale PhDs) third-party fix
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Explore free; Launch $149/mo ($134/mo annual); Scale $1,499/mo ($1,349/mo annual); Enterprise custom vendor fix
- Funding
- Acquired by Anaconda (2026-08-04; terms undisclosed); prior total $2.35M (Seed led by Boldcap, 2024-02-27) third-party fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- Accelerator
- aws-genai-accelerator-2024 third-party fix
Memory taxonomy
- storage
- n/a
- retrieval
- injection
- persistence
- session
- update
- read-only
- unit
- policy
- 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
Comprehensive AI security product covering training data, model, and runtime — broader than memory but addresses memory-specific threats too.
Cons
Memory is one of many concerns; less depth on memory-injection attacks than Lakera.
Claims & capabilities
Sub-100ms latency. Documented MongoDB Atlas Vector Search integration.
Technical surface
- API surface
- REST (typical SaaS REST + first-party SDK pattern; see vendor docs for language coverage)
- Backend storage
- custom
- Deployment
- SaaS for self-serve tiers; Enterprise offers VPC / on-prem deployment
- Embedding model
- locked
- Multi-tenancy
- hard-isolation
- MCP
- yes — MCP server scanning (Launch tier) and MCP Gateway + Registry (Scale/Enterprise)
- A2A
- no data — searched enkryptai.com, enkryptai.com/platform/capabilities/ai-risk-removal, docs.enkryptai.com; A2A protocol not advertised
- OpenTelemetry
- no data — searched enkryptai.com, docs.enkryptai.com; OpenTelemetry export not advertised
Compare Enkrypt AI with…
Alternatives to Enkrypt AI → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other memory governance, privacy & safety in the catalog, ranked by inbound references.
- Lakera Guard / Lakera Red T1
Acquired by Check Point Software (completed by 2025-11-11); being folded into Check Point's AI security platform. 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.
- Acuvity (now Proofpoint) T1
Acquired by Proofpoint (closed 2026-02-12). 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.
- HiddenLayer AISec Platform 2.0 T1
AI security platform with four modules: AI asset discovery, supply-chain/model integrity validation, continuous attack simulation, and runtime detection/response, including protection of agents and MCP-based systems.
- Hyperconsciousness (hc) T3
Developer-alpha encrypted, append-only knowledge store for humans and agents, with CLI/MCP access and scoped, expiring grants. Traction: Submitted via intake issue #181
- Mem0 Security / OpenMemory T1
Commercial Mem0 ships SOC 2 / HIPAA, zero-trust access controls, BYOK encryption, real-time monitoring, audit logs and workspace governance as defaults (Trust Center at trust.mem0.ai). For privacy-first deployments the self-hosted path is now the Mem0 open-source server (REST API + dashboard via Docker Compose with pgvector Postgres, admin setup wizard, per-user API keys, request audit log). As of Oct 2026 OpenMemory itself is a hosted MCP service and its old local Docker variant is no longer in the repo.
- 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.
Sources (42 cited facts, 6 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Three-point RAG / memory pipeline guardrails vendor
- What it does & what's distinct Applies guardrails at three points: (1) before write to vector DB, (2) before query reac… third-party
- Claims / benefits Sub-100ms latency. Documented MongoDB Atlas Vector Search integration. vendor
- Modalities text vendor
- Created 2022 (founded 2022 by Sahil Agarwal and Prashanth Harshangi; Yale PhDs) third-party
- Funding Acquired by Anaconda (2026-08-04; terms undisclosed); prior total $2.35M (Seed led by Bo… third-party
- Customers / scale 1-10 ppl Enterprise AI governance users third-party
- Pricing Explore free; Launch $149/mo ($134/mo annual); Scale $1,499/mo ($1,349/mo annual); Enter… vendor
- Data handling SaaS cloud API; real-time screening of prompts and responses; no self-host confirmed vendor
- Deployment SaaS for self-serve tiers; Enterprise offers VPC / on-prem deployment vendor
- HQ US (Brighton MA) third-party
- Founders / pedigree Enkrypt AI (Sahil Agarwal, CEO; ex-IBM Research; YC-backed) vendor
- Memory volume / scale internal — undisclosed (SaaS guardrails) vendor
- Performance no public benchmark scores found — vendor does not publish quantitative perf metrics vendor
- API surface REST (typical SaaS REST + first-party SDK pattern; see vendor docs for language coverage) vendor
- Backend storage custom vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC vendor
- Embedding model locked vendor
- Consistency not specified — vendor docs do not address this dimension vendor
- Versioning none vendor
- Schema evolution not specified — vendor docs do not address this dimension vendor
- Namespace primitives not specified — vendor docs do not address this dimension vendor
- MCP support yes — MCP server scanning (Launch tier) and MCP Gateway + Registry (Scale/Enterprise) vendor
- Import / export Postman Collection (import-ready API collection) for integrating with Enkrypt AI services vendor
- Validated verticals regulated enterprise: financial-services, healthcare, government, legal vendor
- Time to running <1day to <1week (enterprise procurement + integration) vendor
- Anti-fit not for hobbyist / non-production use cases vendor
- Optimised for governance + compliance + audit + adversarial hardening vendor
- Adjacent infrastructure BYO agent stack; this layer guards it vendor
- Pros Comprehensive AI security product covering training data, model, and runtime — broader t… vendor
- Cons Memory is one of many concerns; less depth on memory-injection attacks than Lakera. vendor
- Project & sources enkryptai.com vendor
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- adoption-accelerator aws-genai-accelerator-2024 third-party
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications iso27001 vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-29
- Homepage “https://www.enkryptai.com/platform/capabilities/ai-risk-removal” → “https://www.enkryptai.com/”
- Funding / ownership “total $2.35M (Seed led by Boldcap, 2024-02-27)” → “Acquired by Anaconda (2026-08-04; terms undisclosed); prior total $2.35M (Seed led by Boldcap, 2024-02-27)” source
- 2026-10-22
- Pricing “free starter + pay-as-you-go; Enterprise: contact sales” → “Explore free; Launch $149/mo ($134/mo annual); Scale $1,499/mo ($1,349/mo annual); Enterprise custom” source
- Funding / ownership “$2M Seed · 2024-02” → “total $2.35M (Seed led by Boldcap, 2024-02-27)” source
- Deployment “REST API SaaS (cloud-hosted); no self-host option confirmed” → “SaaS for self-serve tiers; Enterprise offers VPC / on-prem deployment” source
- MCP support “Yes — MCP Hub: vulnerability scanning for MCP (Model Context Protocol) servers; source-based + hosted scans; MCP Registry” → “yes — MCP server scanning (Launch tier) and MCP Gateway + Registry (Scale/Enterprise)” source
Related systems
Referenced by (1)
- LiteLLM integrates with — LiteLLM proxy docs have an Enkrypt AI guardrail integration page. (verified 2026-10-29)