Built something? We create video reels & spotlights for GitHub projects.Promote your project →
Lyellr88
Home / Python / marm-memory

Lyellr88/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 swarms.

Python ◇ agent-memory Apache-2.0
★409STARS
⑂86FORKS
!17ISSUES
🏆#7,736GLOBAL RANK
🔥11DAYS TRENDING
🚀
Maintainer Growth Kit for marm-memory

Claim this project, add your verified backlink badge to your README, and download milestone cards.

Claim Repo

Star History

Continuous Observations
Interactive star growth chart for Lyellr88/marm-memory
CSV
⭐ VIRAL README KIT

Add Live Star History & Verified Badges to README.md

Keep your repository README looking professional and dynamic. As our continuous crawler records new stars, these official SVG badges update in real time with zero maintenance.

Open README on GitHub ↗
Option 1: Interactive Star History Chart Dynamic SVG

Renders your high-resolution star trajectory chart right inside your GitHub README or project docs.

Lyellr88/marm-memory Star History Preview
markdown
[![Star History Chart](https://githubrepo.cloud/api/badge/chart/Lyellr88/marm-memory.svg?theme=dark)](https://githubrepo.cloud/repo/Lyellr88/marm-memory?utm_source=readme_chart)
Direct SVG Link ↗
Option 2: Verified Shields Badges Shields.io Style

Compact Shields-style badges for your README header. Shows real-time stars and global ranking.

Featured badge Stars badge Rank badge
markdown (badge trio)
[![Featured on GitHubRepo.cloud](https://githubrepo.cloud/badge/Lyellr88/marm-memory.svg?metric=featured)](https://githubrepo.cloud/repo/Lyellr88/marm-memory?utm_source=readme_badge) [![GitHubRepo Stars](https://githubrepo.cloud/badge/Lyellr88/marm-memory.svg?metric=stars)](https://githubrepo.cloud/repo/Lyellr88/marm-memory?utm_source=readme_badge) [![Global Rank](https://githubrepo.cloud/badge/Lyellr88/marm-memory.svg?metric=rank)](https://githubrepo.cloud/repo/Lyellr88/marm-memory?utm_source=readme_badge)

Momentum

+10

STARS · LAST 30 DAYS

1

PER DAY

#967

MOST-STARRED Python

Window7 days30 days90 days
Stars gained+2+10+90
Per day111
Forks gained+1+3+10

marm-memory gained 10 stars in the last 30 days, about 1 a day, and now has 409. It is about 1 year old and has averaged roughly 409 stars a year. It ranks #967 among Python repositories and #7,736 across all languages on GitHubRepo.

Trending Record

marm-memory has maintained a continuous presence across global trending indexes, peaking at #2918. Below is the 30-day activity profile:

💡 Overview

marm-memory is an open-source project written in Python: 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 swarms.

Engineered for speed, consistency, and developer ease, it solves common hurdles in agent-memory, ai-agents, ai-memory. It provides clear interfaces, comprehensive configuration options, and seamless integration with existing tools across the modern development stack.

⚡ Key Features

1

Optimized execution pipeline written in Python for predictable speed.

2

Zero-friction configuration with comprehensive sensible defaults out of the box.

3

Cross-platform runtime support across Linux, macOS, and Windows environments.

4

Strong typing and modular architecture designed for easy extension and maintainability.

5

Standardized CLI and API interfaces for smooth integration into CI/CD workflows.

6

Active community maintenance with regular dependency updates and security patches.

📥 Installation

terminal
$ pip install marm-memory

⚙ System Requirements

Platforms

  • • macOS
  • • Linux
  • • Windows

Runtime & Dependencies

Python >= 3.9, pip, virtualenv

Architecture

x86_64, ARM64 (Apple Silicon & Graviton)

🧠 How It Works

marm-memory coordinates its core functionality through a modular Python pipeline. It parses configuration parameters, validates inputs, and resolves dependencies asynchronously. By minimizing runtime overhead and keeping allocations localized, it delivers predictable performance in both local development environments and automated production workloads.

🎯 Production Use Cases

Autonomous AI Agents

Orchestrate intelligent workflows and tool-calling routines with marm-memory.

Model Inference & Prompting

Integrate fast, local or cloud-hosted generative AI models directly into production code.

Context Memory & RAG

Augment language models with dynamic vector retrieval and structured project memory.

Developer Productivity

Automate repetitive engineering tasks, code generation, and test creation using AI agents.

🚀 Getting Started

1

Install marm-memory using your package manager: `pip install marm-memory`

2

Initialize your project workspace or configuration file for marm-memory.

3

Import marm-memory into your codebase or invoke it directly from your terminal.

4

Execute your test suite or run `marm-memory --help` to verify successful setup.

👍 Strengths

Active community backing with 407 GitHub stars and verified adoption.
Permissive open-source distribution under the Apache-2.0 license.
Built in Python for high execution speed and developer familiarity.
Cross-platform compatibility across modern Linux, macOS, and Windows environments.
Clean modular design allowing flexible configuration and pipeline integration.

⚠️ Considerations

Requires familiarity with Python and modern CLI workflows.
Ecosystem extensions may require manual configuration depending on environment constraints.
Active development roadmap means breaking API changes may occur across major versions.

⇄ Alternatives & Direct Competitors

P
public-apis/public-apis ★ 485.9K Python

A collective list of free APIs

Compare ↗
F

:books: Freely available programming books

Compare ↗
P

Curated list of project-based tutorials

Compare ↗
H
NousResearch/hermes-agent ★ 250.4K Python

The agent that grows with you

Compare ↗

👥 Who Should Use This

Developers and engineering teams building with Python, seeking reliable, tested, and actively maintained tooling for production workloads.

🏆 Nearby in the Rankings

Lyellr88/marm-memory is currently ranked #7,736 by stars across every repository tracked on GitHubRepo. These are adjacent projects:

RankRepositoryLanguageStarsAction
#7,727 open-policy-agent/regal Go ★ 410 Compare ↗
#7,727 increments/qiita-markdown Ruby ★ 410 Compare ↗
#7,727 hiero-ledger/hiero-consensus-node Java ★ 410 Compare ↗
#7,727 charlie12345/ROCmFPX C++ ★ 410 Compare ↗
#7,727 openwong2kim/wmux TypeScript ★ 410 Compare ↗
#7,736 Lyellr88/marm-memory This Project Python ★ 409
#7,736 basecamp/hey-cli Go ★ 409 Compare ↗
#7,736 ryohsuke1231/liquid-glass TypeScript ★ 409 Compare ↗
#7,736 256lights/zb Go ★ 409 Compare ↗
#7,736 toastdriven/itty Python ★ 409 Compare ↗
#7,736 ooc-lang/rock ooc ★ 409 Compare ↗

Frequently Asked Questions

What does marm-memory do? +

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 swarms.

What language is marm-memory written in? +

The primary language is Python. Topics include: agent-memory, ai-agents, ai-memory, claude-code, codex-cli.

Is marm-memory actively maintained? +

Yes, the last recorded push was on Oct 2, 2026 with 17 open issues being tracked.

How many stars does marm-memory have? +

marm-memory has 409 stars and 86 forks on GitHub.

How does marm-memory rank among GitHub repositories? +

With 409 stars, Lyellr88/marm-memory is ranked #7,736 globally across all repositories tracked on GitHubRepo and #967 among Python projects.

What license is marm-memory distributed under? +

The repository reports a Apache-2.0 license. Always verify the repository LICENSE file for legal terms.

From our network
FOR MAINTAINERS

Built something? Put it in front of millions of developers.

We make a short reel about your project and post it across YouTube, Instagram, Threads, and X. Send a link, we do the rest.