# MemoriLabs/Memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Repository: https://github.com/MemoriLabs/Memori
Canonical: https://ross.abutalabs.com/products/memori
Homepage: https://memorilabs.ai
Language: Python
License: NOASSERTION
License Family: other
Topics: agent, ai, long-short-term-memory, memory, python, rag, state-management, memory-management, llm, agent-memory, ai-memory, stateful, typescript, agenticai, claude-code, enterprise, hermes, openclaw
Last push: 2026-08-21T23:44:53+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 86, longevity 28
- inputs: {"age_days": 405, "days_push": 12, "days_rel": 98, "gap_med": 5, "n_releases_24m": 36}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16241, forks 3254 (observed 2026-08-28T04:11:14.971377+00:00)

## What it is
Memori is agent-native memory infrastructure that turns LLM agent execution and conversation into structured, persistent state. It ships as Python and TypeScript SDKs with a managed cloud or self-hosted BYODB deployment, and is LLM, datastore, and framework agnostic.

## Use cases
- give my ai agent long-term memory across conversations
- persist agent state in production llm apps
- remember user preferences and facts from chat automatically
- add memory to claude code or openai agents
- reduce token usage when recalling conversation context
- self-host agent memory with my own database
- semantic recall of past conversations for a chatbot

## When to choose
- you need production-grade, persistent memory for LLM agents with enterprise deployment options (VPC, on-prem)
- you want LLM- and datastore-agnostic memory that works with your existing stack
- you need explainable, traceable memory recall with audit logging and access control

## When to avoid
- you only need simple in-process session state with no persistence
- you want a fully open-source solution without any cloud dependency or API key
- your project is not agent- or LLM-based

## Facets
- artifact type: library
- maturity: active
- function: rag, agent-framework, state-management, llm-inference, database, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, self-hosted, cloud
- tags: agent-memory, memory-infrastructure, llm-agnostic, enterprise, mcp-server, conversation-memory, byodb, ai-agents, retrieval-augmented-generation, nodejs

## Member repositories
- MemoriLabs/Memori (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.971377+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:10.454793+00:00, confidence not recorded.
  - readme: https://github.com/MemoriLabs/Memori (fetched 2026-08-28T04:11:14.971377+00:00, sha d6818b712ff2)
  - homepage: https://memorilabs.ai (fetched 2026-08-29T08:02:43.501127+00:00, sha adf5b7e4c1af)
  - site_page: https://memorilabs.ai/docs (fetched 2026-08-29T08:02:43.504326+00:00, sha bf1be69e0110)
  - registry_pypi: https://pypi.org/pypi/memori/json (fetched 2026-08-29T08:02:43.508074+00:00, sha a6428f56c509)
  - site_page: https://memorilabs.ai/pricing (fetched 2026-08-29T08:02:43.506173+00:00, sha 6cf35b48709b)
- Data as of 2026-08-30T08:39:29.467469+00:00.