Home/Data & Retrieval/OpenMemory

OpenMemory

CaviraOSS/OpenMemory

Local persistent memory store for LLM applications

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

67views this month

4.5k stars504 forksLast push Sep 14, 2026 TypeScript Apache-2.0

Decision brief

OpenMemory offers local storage tailored for AI agents like Claude Desktop and GitHub Copilot.

Good fit when

Need to integrate persistent memory support for specific LLMs like Claude.
Looking for a TypeScript-based solution.

Avoid when

Require cloud-based memory storage services.
Your project must use languages other than TypeScript.

Observed Jul 12, 2026 · Source: enrich:decision_facts

OpenMemory alternatives Trust report

OpenMemory vs mempalace OpenMemory vs memvid OpenMemory vs Memori

Verify the decision

Adoption

Package downloads where a registry match exists. GitHub stars (4,510) are secondary evidence.

npm downloads (30d): 203·npm downloads API·Sep 20, 2026

Maintenance and security

Full trust report

Maintenance: Very active (5d since push); As of Sep 20, 2026
Provenance: Not a fork · Organization account; As of Sep 20, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install OpenMemory

How it fits your stack(8)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Alternative

Both OpenMemory and mem0 provide memory storage solutions for AI agents aiming to solve the problem of persistent memory.

Mempalace is an open-source AI memory system similar to OpenMemory in that both are designed for persistent stateful operations of AI agents with benchmarking potential.

Memvid and OpenMemory both aim to provide a memory layer for AI Agents, focusing on state persistence over sessions.

Integrates

OpenMemory explicitly mentions integration with LangChain, making them compatible and designed for joint use in AI applications.

Related

AI-Driven Development

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

TencentDB-Agent-Memory

A team-level memory hub for AI Agents, transforming conversations, documents, and code into reusable memory assets.

Personal memory for agents with fast retrieval and self-evolving skills

Memory library for building stateful agents

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Provides local storage and retrieval capabilities for various AI agents including claude desktop, GitHub Copilot, Codex, and more. Built with TypeScript.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Sep 20, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Sep 20, 2026
CLI: CLI entrypoint
Source: package.json:bin|scripts · Sep 20, 2026
MCP server: Ships MCP server
Source: package.json:@modelcontextprotocol/* · Sep 20, 2026
Languages: typescript, javascript
Source: github.language+package.json · Sep 20, 2026

Categories

Data & Retrieval Vector Databases

Graph entities

LangChainframework LangGraphframework CrewAIframework AutoGenframework Ollamaframework

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Sep 20, 2026)

npm install longmemory

Tags

ai-agents embeddings long-term-memory memory-engine vector-database

README

Install as a library No service or external database is required for in memory use. For optional evidence grounded answers with your own model, use the exported adapter. It accepts authorized evidence, validates cited excerpts, and makes at most one model call; ordinary recall is...

For agents

This page has a .md twin and JSON over the API.

/tools/caviraoss-openmemory.md GET /api/graphcanon/tools/caviraoss-openmemory GET /api/graphcanon/graph?tool=caviraoss-openmemory

Was this helpful?

Anonymous feedback helps us improve pages and translations.