Memori
https://github.com/MemoriLabs/Memori
Structured, persistent memory layer for AI agents. Open source.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 50 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Structured persistent memory layer repo fix
- Tier
- T2
- Section
- Dedicated memory layers
- Latest release
- v3.3.6 (2026-05-28) registry fix
- License
- Apache-2.0 repo fix
- GitHub
- MemoriLabs/Memori — ~17.1k stars, last commit n/a repo fix
- Pricing
- Free + paid (Memori Cloud; tiered plans for builders / growing / production teams) vendor fix
- Funding
- $3.7M Seed (4 investors; round closed May 2024) third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- SDK languages
- python, typescript repo fix
- Protocols
- mcp-server repo fix
- Developer activity
- OpenRank 2.61 (12-mo avg 6.67) · 5 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- relational
- retrieval
- similarity
- persistence
- cross-session
- update
- extraction
- unit
- fact
- governance
- inspectable
- conflict
- append
When to use
Optimised for: structured persistence + simplicity
Anti-fit: no anti-fit explicitly stated
Pros & cons
Pros
OSS dual-mode model (conscious + autonomous ingestion) lets developers control memory decisions explicitly.
Cons
Smaller community than Mem0/Letta; documentation is uneven.
Claims & capabilities
Apache-2.0; structured persistent memory layer (relational + vector hybrid); +175/mo; v3.3.3 released 2026-05-05; dual-mode (conscious + autonomous ingestion); $3.7M seed (May 2024); founders Harish Mukhami (CEO) and Michael Montero (CTO) NYC
Technical surface
- API surface
- SDK: Python (memori.enable() one-liner; integrates LiteLLM, OpenAI, Anthropic)
- Backend storage
- SQL (SQLite/Postgres/MySQL)
- Deployment
- Both (Memori Cloud zero-config + self-hosted OSS)
- Embedding model
- multiple supported
- Multi-tenancy
- not applicable — library; multi-tenancy is the embedding application's concern
- MCP
- yes — first-party hosted remote MCP endpoint (api.memorilabs.ai/mcp) for Claude Code, Cursor, Codex etc.
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to Memori → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other dedicated memory layers in the catalog, ranked by inbound references.
- Mem0 T1
Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.
- Zep & Graphiti T1
Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.
- Cognee T1
"Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.
- Hindsight (Vectorize) T1
Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.
- Letta / MemGPT T1
Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.
- Memvid T2
Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).
Sources (49 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 Structured persistent memory layer repo
- What it does & what's distinct Structured, persistent memory layer for AI agents. Open source. repo
- Claims / benefits Apache-2.0; structured persistent memory layer (relational + vector hybrid); +175/mo; v3… repo
- Modalities text repo
- Created 2025-07 repo
- Latest release v3.3.6 (2026-05-28) registry
- License Apache-2.0 repo
- GitHub MemoriLabs/Memori — ~17.1k stars, last commit n/a repo
- Funding $3.7M Seed (4 investors; round closed May 2024) third-party
- Pricing Free + paid (Memori Cloud; tiered plans for builders / growing / production teams) vendor
- Deployment Both (Memori Cloud zero-config + self-hosted OSS) vendor
- HQ US (New York City) third-party
- Founders / pedigree Harish Mukhami (CEO) and Michael Montero (CTO); founded 2024 third-party
- Memory volume / scale no scale claim repo
- API surface SDK: Python (memori.enable() one-liner; integrates LiteLLM, OpenAI, Anthropic) repo
- Backend storage SQL (SQLite/Postgres/MySQL) repo
- Embedding model multiple supported repo
- Schema evolution schema with migration repo
- Namespace primitives per-tenant repo
- Contradiction handling LLM resolves and overwrites repo
- MCP support yes — first-party hosted remote MCP endpoint (api.memorilabs.ai/mcp) for Claude Code, Cu… repo
- Import / export JSON; SQLite backend repo
- Integration count 0 repo
- Orchestration both (multi-tenant via namespace; per-agent or shared) repo
- Programmatic control full CRUD via SDK vendor
- Pricing specifics tier flat-rate: free + paid Memori Cloud (builders/growing/production) vendor
- Validated verticals agent developers (horizontal) repo
- Time to running <10min (pip install) repo
- Anti-fit no anti-fit explicitly stated repo
- Optimised for structured persistence + simplicity repo
- Adjacent infrastructure BYO LLM; SQLite/Postgres repo
- Pros OSS dual-mode model (conscious + autonomous ingestion) lets developers control memory de… repo
- Cons Smaller community than Mem0/Letta; documentation is uneven. repo
- Project & sources GitHub MemoriLabs/Memori repo
- commit-trajectory [{"ym":"2025-07","cum":15},{"ym":"2025-08","cum":198},{"ym":"2025-09","cum":265},{"ym":"… repo
- download-trajectory [{"ym":"2025-11","monthly":779,"cum":779},{"ym":"2025-12","monthly":5650,"cum":6429},{"y… registry
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus hybrid repo
- licensing-bucket open-core vendor
- positioning-platform-vs-product platform repo
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":10.06,"as_of":"2026-09","openrank_12mo":6.67,"openrank_current":2.61,"partic… third-party
- sdk-languages python,typescript repo
- protocol-support mcp-server repo
- maturity alpha registry
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
Referenced by (2)
- AgentOps integrates with — AgentOps docs have a Memori integration page. (verified 2026-10-29)
- MongoDB Atlas Vector Search integrates with — MongoDB's Atlas AI Integrations page lists Memori as an integration (some entries are marked community-maintained). (verified 2026-10-29)