Home Projects marm-memory
marm-memory
Python

marm-memory

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swar

by Lyellr88 · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
Likely
Self-hostable
agent-memoryai-agentsai-memoryApache-2.0PythonSelf-hostable
View on GitHub
In plain words

Set up a local memory system for AI agents that keeps track of context and history (Claude Code required)

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
marm-memory — GitHub preview card
📈 Star history
329314
2026-07-202026-08-31
📈 Track marm-memory

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swar

marm-memory has 329 stars on GitHub. It has been forked 62 times. marm-memory is written mainly in Python. It has been in active development since 2025. marm-memory is available under the Apache-2.0 license. Its main topics are agent-memory, ai-agents, ai-memory, claude-code.

Frequently asked questions

What is marm-memory?

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swar

Is marm-memory open source?

marm-memory is an open-source project. It is released under the Apache-2.0 license.

Is marm-memory free?

Yes. marm-memory is free and open source — you can use, modify and self-host it.

What license does marm-memory use?

marm-memory is available under the Apache-2.0 license.

What language is marm-memory written in?

marm-memory is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — marm-memory

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=lyellr88-marm-memory)](https://olud.ai/project/lyellr88-marm-memory.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
Ori-Mnemos
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source mu…
318 · agent-memory
sharespersistent-memorysqlite
TrueMemory
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% lo…
378 · agent-memory
sharessqliteai-memory
iai-personal-memory-engine
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and lear…
826 · agent-memory
sharespersistent-memorylong-term-memory
agentkeeper
Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about yo…
120 · agent-memory
shareslong-term-memorysqlite
MegaMemory
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-proce…
513 · agentic-coding
sharespersistent-memorysqlite
pmb
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decis…
275 · ai-agents
sharessqliteai-memory
Compartment
Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agent…
587 · agent-memory
shareslong-term-memoryai-memory
ai-agent-book
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
43.6k · agent
tidb
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native su…
40.5k · agent
OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
34.5k · agent-memory

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.