celiums/celiums-memory
by Various
Open-source cognitive engine for AI agents — persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biological clock, over MCP. Apache-2.0.
MCP
celiums/celiums-memory
Added 1 June 2026
Overview
Celiums Memory is an open-source cognitive engine for AI agents that provides persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biological clock over the Model Context Protocol (MCP). It is written in TypeScript and licensed under Apache-2.0.
Best for
Best for
Developers experimenting with persistent memory and ethics for AI agents
Use cases
- Give AI agents long-term memory across sessions
- Enforce ethical constraints with a multi-layer ethics engine
- Simulate time-aware agent behavior with a per-user biological clock
How to use
Tools exposed
DATABASE_URLSQLITE_PATHCELIUMS_API_KEYPORTQDRANT_URLVALKEY_URLPERSONALITYCELIUMS_LLM_API_KEYCELIUMS_LLM_BASE_URLCELIUMS_LLM_MODELKNOWLEDGE_API_URLKNOWLEDGE_API_KEYOPENSEARCH_URL
Tested with
Claude Code, Cursor, Continue, Cline, OpenCode
Example client config
{\n "mcpServers": {\n "celiums-memory": {\n "url": "http://localhost:3210/mcp",\n "headers": { "Authorization": "Bearer cmk_your_key_here" }\n }\n }\n} Notes
Celiums Memory is an open-source cognitive engine for AI agents that provides persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biological clock over the Model Context Protocol (MCP). It is written in TypeScript and licensed under Apache-2.0.
15 stars on GitHub. Last updated 2026-05-19. Licensed Apache-2.0.
Use cases
- Give AI agents long-term memory across sessions
- Enforce ethical constraints with a multi-layer ethics engine
- Simulate time-aware agent behavior with a per-user biological clock
Pros
- Open-source with permissive Apache-2.0 license
- Modular design with MCP integration for agent interoperability
- Includes unique features like a journal and biological clock
Cons
- Very early stage with only 15 GitHub stars
- Limited community adoption and documentation
- Unclear production readiness or maintenance cadence
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open-source with permissive Apache-2.0 license
- Modular design with MCP integration for agent interoperability
- Includes unique features like a journal and biological clock
Cons
- Very early stage with only 15 GitHub stars
- Limited community adoption and documentation
- Unclear production readiness or maintenance cadence
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Cline
Cline
Open-source autonomous coding agent that lives inside VS Code. BYO model key, watch it work.
Claude Code
Anthropic
Anthropic's terminal-native coding agent. Reads your repo, edits files, runs tests, ships PRs.
Continue
Continue.dev
Open-source AI code assistant for VS Code and JetBrains. Customisable, BYO model, built for enterprise.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.