LongMemory

LongMemory is a vector database - Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Overview

LongMemory is a cognitive memory engine for LLM applications and autonomous agents.

Your model stays stateless. Your application stops being amnesiac.

No service or external database is required for in-memory use.

Reopening the same database restores nodes, worlds, entities, edges, temporal history, grounding, and lifecycle state.

1. Split text into chunks. 2. Embed the chunks. 3. Return the nearest vectors.

That does not establish what was true at a particular time, whether a new fact superseded an old one, which source is authoritative, who may see it, or why a result belongs in context.

• Temporal truth: recorded time and valid time are separate. - Immutable memory: content, vectors, hashes, and provenance are not rewritten by recall or decay. - Executable graph: typed relationships participate in recall and explanation. - Governance: project, tenant, user, team, role, agent, task, and framework scope are enforced. - Lifecycle: deterministic decay, explicit reinforcement, consolidation, compression, and reconsolidation. - Evidence: recall is bounded by relevance, contradictions, grounding, permissions, and token cost.

Strict recall applies temporal, contradiction, contract, confidence, and grounding gates. Historical recall preserves superseded truth. Associative recall follows semantic, lexical, entity, activation, and graph signals. World-grounded recall requires current external evidence.

LongMemory is open-source, written primarily in TypeScript, with 4,479 GitHub stars under the Apache 2.0 license. The latest release is v1.2.3 (2025-12-12).

Key capabilities

From the project's documentation:

• Durable local-first storage with SQLite
• Immutable content, provenance, and temporal truth
• Strict, historical, associative, grounded, and multilingual recall
• Explainable evidence selection and token-bounded context
• Governed project memory, Skills, Chat Memory, LLM-Wiki, and CodeGraph
• One TypeScript engine across npm, CLI, HTTP, MCP, dashboard, and VS Code

Install

A quick way to get started (always check the official docs for the latest):

docker run --rm \

How it fits a local-AI stack

LongMemory runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related vector databases in the directory:

• Chroma
• "cognee"
• "Langchain-Chatchat"
• Milvus

Sources

• Source code & docs: CaviraOSS/LongMemory
• Official website: https://openmemory.cavira.app

Stats from GitHub, 2026-09-03.