Memori
Memori LabsMemori adds long-term memory to LLM applications by wrapping the model client, extracting facts, preferences, skills and agent-trace events from each conversation in the background and injecting the relevant ones into later prompts. Memories are kept in the developer's own SQL or document database or in Memori Cloud, linked by a graph of subject-predicate-object triples. Memori Labs builds it.
The repository was GibsonAI/memori before the project moved to Memori Labs, and memorisdk is the SDK's earlier PyPI name.
Openness
2 medium confidence- license
- Apache-2.0 (Python and TypeScript SDKs and the Rust core: storage, embeddings and recall)+Proprietary (the Advanced Augmentation extraction service)
- source
- partial (the published core sends each conversation to Memori's hosted sdk/augmentation endpoint and writes back what it returns; the engine that extracts facts, preferences and triples is in no repository)
- managed-tier
- Memori Cloud (managed storage and dashboard; production plans sell managed, single-tenant or on-prem deployments)
Memori's SDKs and core, which store memories in the developer's database and recall them, are published under Apache 2.0. The step that decides what to remember is not: the SDK sends each conversation to Memori's hosted service to extract facts and relationships, metered by a free quota, so the memory logic can be neither read nor run locally.
- https://memorilabs.ai/pricing recorded 2026-11-20
Pricing says "Start free and open. Bring your own database." and sells Team, Business and Enterprise production plans with managed, single-tenant or customer-VPC deployment.
- https://pypi.org/pypi/memori/json recorded 2026-11-20
PyPI lists memori, "Memori Python SDK", license Apache-2.0, repository MemoriLabs/Memori.
- https://raw.githubusercontent.com/GibsonAI/memori/main/README.md recorded 2026-11-20
The old GibsonAI/memori path serves the MemoriLabs/Memori README byte for byte, so the repository moved rather than forked.
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/core/src/augmentation/pipeline.rs recorded 2026-11-20
run_advanced_augmentation logs "augmentation calling Memori API: sdk/augmentation" and builds the database write batch from that API's response.
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/docs/memori-byodb/concepts/advanced-augmentation.mdx recorded 2026-11-20
Advanced Augmentation "turns raw conversations and agent trace into structured, searchable memories" and "All extracted data is stored directly in your database."
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/docs/memori-byodb/support/faq.mdx recorded 2026-11-20
"No, the open-source version works without one. An API key only unlocks higher Advanced Augmentation quotas (5,000/month with a free key)."
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/LICENSE recorded 2026-11-20
The LICENSE is the Apache License 2.0 text with the appendix boilerplate "Copyright [2025] [Memori Team]".
Adoption
2 medium confidenceAdoption is the sum of monthly downloads of memori and memorisdk on PyPI and @memorilabs/memori on npm, the three packages that ship the SDK, most of it the memori package. Memori Cloud usage, the hosted MCP endpoint and the agent-host plugins are not counted.
- https://api.npmjs.org/downloads/point/last-month/@memorilabs/memori recorded 2026-11-20
408 downloads of @memorilabs/memori between 2026-10-20 and 2026-11-18.
- https://pypi.org/pypi/memorisdk/json recorded 2026-11-20
memorisdk is the "Memori Python SDK" with repository MemoriLabs/Memori.
- https://pypistats.org/api/packages/memori/recent recorded 2026-11-20
16,978 downloads of memori in the last month.
- https://pypistats.org/api/packages/memorisdk/recent recorded 2026-11-20
769 downloads of memorisdk in the last month.
Capability
4 medium confidenceMemori extracts typed memories from conversations and agent traces, keeps a knowledge graph beside them and merges repeated facts, all without changes to the calling code. Nothing in it retires a memory over time, and the extraction itself runs on Memori's hosted service.
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/docs/memori-byodb/concepts/advanced-augmentation.mdx recorded 2026-11-20
The engine "Identifies facts, preferences, skills, attributes, and events" and "Extracts semantic triples"; "Memori automatically deduplicates triples", incrementing the mention count and timestamp.
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/docs/memori-byodb/concepts/how-memory-works.mdx recorded 2026-11-20
Every memory is attributed to an entity, process and session; recall runs automatically on each call or through mem.recall(), over facts, preferences, skills, rules, events and agent traces.
- https://raw.githubusercontent.com/MemoriLabs/Memori/main/README.md recorded 2026-11-20
The README says Memori "automatically captures structured memory from conversation and agent execution after each turn - including tool calls, decisions, and outcomes".
Verified 2026-11-20, except some scores, still awaiting re-confirmation