Memorix is a cross-agent memory bridge that prevents AI assistants from losing context across sessions and different development environments. It offers persistent local memory, workspace synchronization, and auto-generated project skills to enhance developer productivity.

Is memorix open source?

Yes, licensed under Apache-2.0.

memorix: A cross-agent memory bridge that prevents AI assistants from losing… (★ 560, Apache-2.0)

Features

01Smart memory system with token-efficient progressive disclosure and hybrid search (BM25 + vector).

02Cross-agent workspace synchronization for configs, rules, skills, and workflows across multiple IDEs.

03Persistent knowledge graph with 9 observation types, compatible with MCP Official Memory Server.

04Interactive web-based Visual Dashboard with D3.js knowledge graph, observation browser, and retention panel.

05Auto-memory hooks for automatically capturing decisions, gotchas, and problem-solutions from coding sessions.

Why choose it

+Smart memory system with token-efficient progressive disclosure and hybrid search (BM25 + vector).

+Ensuring AI remembers past architectural decisions and conversations across sessions.

+Covers 9 supported environments or platforms, which is helpful for broader deployment needs.

+Ships with a public repository and a Apache-2.0 license, which makes adoption and review easier.

Trade-offs

!There are at least 8 related tools in the same category, so the best choice is easier to make after side-by-side comparison.

Compatibility

Cursor

AI Agent

Verified via docs

Windsurf

AI Agent

Verified via docs

Claude Code

AI Agent

Verified via docs

Codex

AI Agent

Verified via docs

VS Code Copilot

AI Agent

Verified via docs

Kiro

AI Agent

Verified via docs

Quick start

$ npx -y memorix@latest serve

Use cases

↳Ensuring AI remembers past architectural decisions and conversations across sessions.

↳Facilitating seamless knowledge transfer and collaboration between different AI agents/IDEs.

↳Preventing recurring bugs and pitfalls by automatically injecting 'gotchas' into AI context.

↳Synchronizing AI assistant configurations, rules, and skills across various development environments.

↳Automatically generating project skills and documentation for faster onboarding of new team members or agents.

How it compares

≈memorix sits in the Vision / Multimodal category, so it makes more sense to evaluate it alongside tools like ragflow instead of in isolation.

≈If your main need is closer to "Ensuring AI remembers past architectural decisions and conversations across sessions.", that use case is a better lens for comparison than broad feature checklists alone.

≈memorix uses a Apache-2.0 license, and community traction are both easier to judge in category context.

Alternatives

ragflow★ 85.4k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

vs →

n8n★ 197.1k

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

vs →

headroom★ 60.2k

Comments

?
usr_seed_0251May 15, 2026
Used to maintain context across Cursor and Claude Code sessions on the same project
?
usr_seed_0621Mar 18, 2026
The cross-agent design means memory accumulated in one tool is available in others
?
usr_seed_0469Mar 18, 2026
Persistent memory that works across different AI coding tools is genuinely rare
?
usr_seed_0699Mar 3, 2026
Cross-agent memory bridge for Cursor, Claude Code, and other tools solves real fragmentation

memorix

Features

Why choose it

Trade-offs

Compatibility

Quick start

Use cases

How it compares

Alternatives

Related searches

Comments

Deploy on DigitalOcean — Get $200 Free Credit