Your Personal Memory,
Across |
Your agents forget context between sessions. memU gives every agent you use one shared, inspectable memory layer with source-linked recall.
We are rebuilding memU's installation flow and cross-agent experience. Updated access is coming soon.
Project preferences
The durable constraints every agent should know before it starts.
Summary
- Keep the existing memU visual language
- Lead with personal memory across agents
- Prefer concise, product-first explanations
Source
- Original project conversation
- Launch brief
Updated
- Today
Related
- launch-decisions.md
- things-to-avoid.md
Launch decisions
Why the product story changed and what should stay consistent.
Decisions
- Position memU as one personal memory layer
- Show Codex, Claude, Gemini, OpenClaw, and Hermes
- Replace repeated long prompts with small context packs
- Keep every memory record inspectable
Source
- Product launch brief
- Website review
Related
- project-preferences.md
- tool-patterns.md
Coding habits
Patterns learned from code sessions and review history.
Habits
- Read the repository before editing
- Reuse existing components and local helpers
- Run lint and focused tests after changes
- Keep unrelated files untouched
Source
- Codex sessions
- Code review history
Related
- tool-patterns.md
Tool patterns
How each agent should retrieve and use personal memory.
Before a task
- Retrieve only records related to the current request
- Prefer recent decisions over stale assumptions
- Keep source links attached to the context pack
After a task
- Memorize durable decisions and preferences
- Skip temporary details and duplicated text
Related
- coding-habits.md
- things-to-avoid.md
Things to avoid
Repeated mistakes that should not follow the user into another agent.
Avoid
- Asking for project background that is already in memory
- Pasting full conversation histories into every prompt
- Hiding where a remembered fact came from
- Changing the established visual style without approval
Source
- User feedback
- Previous revisions
Related
- project-preferences.md
- launch-decisions.md
One Personal Memory Layer Across Every Agent
Chats, documents, and code logs become readable memory records. Every agent retrieves a small, source-linked context pack from the same layer.
Connect memU to every agent
# Paste into a new Codex session
Read memu.pro/skill.md, install memU, then use it to memorize and retrieve memory.
# Codex can now retrieve
# project preferences, launch decisions,
# coding habits, and tool patternsEnterprise-grade AI solutions for your business needs
Powerful tools and dedicated support to scale your AI applications with confidence
Commercial License
Full proprietary features, commercial usage rights, and white-labeling options for your enterprise needs
Custom Development
SSO/RBAC integration and dedicated algorithm team for scenario-specific optimization
Intelligence & Analytics
User behavior analysis, real-time monitoring, and automated agent optimization tools
Premium Support
24/7 dedicated support team, custom SLAs, and professional implementation services
Ready to scale your AI applications?
Contact our enterprise team ([email protected]) to discuss your specific requirements and get a custom solution.
Contact salesPower Your AI Systems with Long-Term Memory in Any Scenario
Latest from the MemU blog
Stay updated with the latest news and stories.
Anthropic Agent Skills Turn Markdown into Reusable Claude Playbooks — But Packaged Skills Are Not Company-Wide Memory
Claude Code Evaluation Harnesses Score Agent PRs and Diffs — But Harness Metrics Without Memory Retest the Same Edge Cases
Claude Projects Keep Long Chats Scoped — But Project Context Is Not a Shared Agent Memory Layer
Join the MemU community
Engage with developers shaping memory-first AI. Share insights to advance the ecosystem.
Join DiscordYour Personal Memory,
Across Every Agent
Install memU once. Retrieve the right context in Codex, Claude, Gemini, OpenClaw, Hermes, and more.
Keep every memory inspectable and linked to its source.