Relevance AI Memory
https://relevanceai.com/docs/agent/build-your-agent/memory
Two memory scopes: conversation metadata (KV per-conversation) and persistent memory (cross-session). Enabling metadata auto-adds Add/Read conversation metadata tools.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 43 cited facts, 4 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Short-term metadata + persistent KV store vendor fix
- Tier
- T1
- Section
- Framework-embedded memory
- Created
- 2020 (Relevance AI founded 2020) third-party fix
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Public pricing page now lists only Enterprise (custom actions/vendor credits; contact sales) vendor fix
- Funding
- $24M Series B May 2025 led by Bessemer VP; total ~$30M+ raised; Series A ~$6M prior third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- Accelerator
- aws-genai-accelerator-2024 third-party fix
- Protocols
- mcp-client, mcp-server vendor fix
- Compliance
- gdpr, iso27001, soc2-type2 vendor fix
Memory taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- cross-session
- update
- overwrite
- unit
- fact
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: low-code agent platform + dual-scope memory
Anti-fit: searched not found
Pros & cons
Pros
No-code agent platform with memory built in — fastest path to a deployed agent for non-engineers.
Cons
Memory abstractions are simple; sophisticated agent designs hit ceilings quickly.
Claims & capabilities
Free 200 actions/mo; Pro $19/mo; Team $234/mo.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Managed cloud only (SaaS); multi-region on enterprise tier
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- yes — hosted MCP server at mcp.relevanceai.com exposing agents/tools/knowledge to Claude, ChatGPT, Cursor etc. (OAuth, role-scoped); MCP client for external servers also documented
- A2A
- searched not found
- OpenTelemetry
- searched not found
Alternatives to Relevance AI Memory → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- Spring AI ChatMemory T3
Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.
- Flowise Memory T1
Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.
- LangGraph Persistence T2
Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.
- AutoGen Memory T2
AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Hermes Agent memory (Nous Research) T3
Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.
Sources (42 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Short-term metadata + persistent KV store vendor
- What it does & what's distinct Two memory scopes: conversation metadata (KV per-conversation) and persistent memory (cr… vendor
- Claims / benefits Free 200 actions/mo; Pro $19/mo; Team $234/mo. vendor
- Modalities text vendor
- Created 2020 (Relevance AI founded 2020) third-party
- Funding $24M Series B May 2025 led by Bessemer VP; total ~$30M+ raised; Series A ~$6M prior third-party
- Customers / scale 51-200 ppl No named customers publicly disclosed vendor
- Pricing Public pricing page now lists only Enterprise (custom actions/vendor credits; contact sa… vendor
- Compliance Enterprise: SSO via SAML, RBAC, audit logs, multi-org management third-party
- Data handling Multi-region hosting; encryption; enterprise RBAC; no specific BAA / SOC 2 cert found pu… vendor
- Deployment Managed cloud only (SaaS); multi-region on enterprise tier vendor
- HQ Australia (Sydney) vendor
- Founders / pedigree Relevance AI (Daniel Vassilev & Jacky Li, co-founders; Sydney-based; AirTree / GV-backed) vendor
- Memory volume / scale no scale claim — SaaS; vendor undisclosed vendor
- Schema evolution free-form / no schema vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- MCP support yes — hosted MCP server at mcp.relevanceai.com exposing agents/tools/knowledge to Claude… vendor
- Webhooks / events webhooks supported vendor
- Import / export JSON via REST; CSV/JSONL dataset import vendor
- Integration count 0 vendor
- Orchestration multi-agent supervisor vendor
- Programmatic control full CRUD via API + visual builder vendor
- Pricing specifics per-API-call + tier flat-rate: Free 200 actions/mo; Pro $19/mo; Team $234/mo; Business/E… vendor
- Agent abstraction multi-agent supervisor (Workforce) vendor
- Memory primitives multiple (conversation metadata KV + persistent cross-session) vendor
- LLM lock multi-vendor vendor
- Runtimes declarative cross-language vendor
- Session handling persistent thread vendor
- Validated verticals sales, support, internal IT vendor
- Time to running <10min (hosted SaaS) vendor
- Optimised for low-code agent platform + dual-scope memory vendor
- Adjacent infrastructure requires Relevance AI; managed vendor
- Pros No-code agent platform with memory built in — fastest path to a deployed agent for non-e… vendor
- Cons Memory abstractions are simple; sophisticated agent designs hit ceilings quickly. vendor
- Project & sources memory docs 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 gdpr,iso27001,soc2-type2 vendor
- protocol-support mcp-client,mcp-server vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-23
- Compliance “Enterprise: SSO via SAML, RBAC, audit logs, multi-org management; data stays within region (multi-region support on…” → “Enterprise: SSO via SAML, RBAC, audit logs, multi-org management” source
- 2026-10-22
- Pricing “Free 200 actions/mo; Pro $19/mo; Team $234/mo; Business/Enterprise: 2 credits per run (vs 4 for free). Actions + Ve…” → “Public pricing page now lists only Enterprise (custom actions/vendor credits; contact sales)” source
- MCP support first recorded as “yes — hosted MCP server at mcp.relevanceai.com exposing agents/tools/knowledge to Claude, ChatGPT, Cursor etc. (OAuth, role-scoped); MCP client for external servers also documented” source