# kingjulio8238/Memary

The Open Source Memory Layer For Autonomous Agents

Repository: https://github.com/kingjulio8238/Memary
Canonical: https://ross.abutalabs.com/products/memary
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: agents, memory, knowledge-graph, rag, multiagent-systems, self-improvement
Last push: 2024-10-22T00:46:00+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 28, longevity 62
- inputs: {"age_days": 875, "days_push": 681, "days_rel": 681, "gap_med": 42, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2641, forks 203 (observed 2026-08-28T04:07:06.500921+00:00)

## What it is
Memary is an open-source memory layer for autonomous AI agents that emulates human memory using knowledge graphs. It is a Python library (pip-installable) that integrates with local models via Ollama or OpenAI APIs to give agents long-term memory.

## Use cases
- add long-term memory to autonomous ai agents
- build agents that remember past interactions
- implement knowledge-graph based memory for llm agents
- run agent memory with local ollama models
- build multi-agent systems with shared memory
- improve agent reasoning with human-like memory

## When to choose
- you are building autonomous agents in Python and need persistent, human-like memory
- you want to run models locally with Ollama instead of paid APIs
- you want knowledge-graph-backed memory rather than plain vector stores

## When to avoid
- you need a managed memory service with no self-hosting
- your stack is not Python or requires Python > 3.11
- you need production-hardened, enterprise-supported memory infrastructure

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, llm-inference
- domain: artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: agent-memory, knowledge-graph, ollama, long-term-memory, multi-agent-systems, ai-agents, retrieval-augmented-generation

## Member repositories
- kingjulio8238/Memary (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.500921+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 2026-08-30T02:19:04.498877+00:00, confidence not recorded.
  - readme: https://github.com/kingjulio8238/Memary (fetched 2026-08-28T04:07:06.500921+00:00, sha af160c4efe9f)
  - registry_pypi: https://pypi.org/pypi/memary/json (fetched 2026-08-29T10:02:02.943676+00:00, sha 50e3b3a8383b)
- Data as of 2026-08-30T08:39:29.467469+00:00.