celiums-memory
Active·★ 23·Apache-2.0·Updated 2026-08-23
Celiums Memory is a cognitive memory engine designed to be embedded within other software like agents and assistants, providing persistent memory, journaling, and an auditable ethics engine. It speaks the Model Context Protocol (MCP) to offer these advanced cognitive capabilities without requiring developers to build them from scratch.
#Cognitive Memory Engine#Agent Memory#Journaling#Ethics Engine#MCP Protocol#Hybrid Retrieval#LLM Integration#Scalable Storage
01
Features
01Cognitive Memory with Hybrid Retrieval (vector + full-text + affective/PAD resonance)
02Append-Only Hash-Chained First-Person Agent Journal
03Auditable 4-Layer Ethics Engine for moral evaluation
04Per-User Biological Clock modulating arousal and recall
05Flexible Storage Adapters (SQLite for local/embedded, Postgres+Qdrant+Valkey for clustered)
02
Compatibility
Node.js
Runtime
Verified via docs
TypeScript
Language
Verified via docs
Docker
Deployment
Verified via docs
PostgreSQL
Database
Verified via docs
Qdrant
Vector DB
Verified via docs
Valkey
Cache
Verified via docs
03
Quick start
1
$ git clone https://github.com/terrizoaguimor/celiums-memory.git
2
$ cd celiums-memory
3
$ cp .env.example .env
4
$ pnpm docker:up
04
Use cases
↳Embedding into AI agents and assistants to provide persistent memory and context
↳Implementing auditable ethical guidance and decision-making for AI systems
↳Developing applications requiring first-person journaling and causal chain tracking for agents
↳Building scalable knowledge bases with hybrid retrieval capabilities for AI applications
↳Integrating advanced cognitive functions into any MCP-compatible client or custom software
05
Alternatives
sqlite-memory-mcp★ 18
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync
telemem★ 494
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.
AgentRecall-X★ 371
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
clarilayer★ 82
Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).
headroom★ 77.3k
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. Around 20% fewer tokens for coding agents and 60-95% fewer for JSON, with the same answers. Library, proxy, and MCP server.
fava-trails★ 26
🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
Comments
Log in to leave a comment
No comments yet. Be the first!