# memodb-io/memobase

User Profile-Based Long-Term Memory for AI Chatbot Applications.

Repository: https://github.com/memodb-io/memobase
Canonical: https://ross.abutalabs.com/products/memobase
Homepage: https://memobase.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chatgpt, llm-application, memory, rag, retrieval, user-memory, ai-companion, ai-memory, long-term-memory, llm-memory
Last push: 2026-01-11T03:51:40+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 35, longevity 52
- inputs: {"age_days": 729, "days_push": 234, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2862, forks 231 (observed 2026-08-28T04:07:26.323913+00:00)

## What it is
Memobase is a user profile-based long-term memory system for LLM applications, providing per-user profiles and event timelines that chatbots can query with low latency. It ships client SDKs for Python, TypeScript, and Go, an MCP server, and can be self-hosted or used as a hosted service.

## Use cases
- add long-term memory to my ai chatbot
- remember user preferences across chat sessions
- build a personalized ai companion that remembers users
- store and retrieve user profiles for llm apps
- give my assistant memory without building a rag pipeline
- track user event timelines for personalization

## When to choose
- you need persistent, structured user memory for chatbots or companions
- you want low-latency memory access without heavy pre-processing
- you care about keeping LLM memory costs low with batched processing

## When to avoid
- you need a general-purpose vector search or document RAG engine
- you only need short-term conversation context within a single session
- you require a fully offline solution with no external service dependency

## Facets
- artifact type: service
- maturity: active
- function: rag, llm-inference, agent-framework, database, sdk
- domain: artificial-intelligence, large-language-models, chatbots
- platform: python, go, self-hosted
- tags: long-term-memory, user-profiles, llm-memory, ai-companion, mcp, memory-system, retrieval-augmented-generation, ai-agents, nodejs, docker

## Member repositories
- memodb-io/memobase (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:26.323913+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 2026-08-30T07:36:22.617399+00:00, confidence not recorded.
  - readme: https://github.com/memodb-io/memobase (fetched 2026-08-28T04:07:26.323913+00:00, sha 0bb1f1a9b9ac)
  - registry_pypi: https://pypi.org/pypi/memobase/json (fetched 2026-08-29T09:52:00.177710+00:00, sha 63cb277893c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.