mori
Active·★ 32·AGPL-3.0·Updated 2026-10-20
Mori is a shared memory layer for AI coding agents that allows multiple instances to learn from each other, ensuring coherence and preventing 'cold starts'. It distills session activity into durable knowledge, enabling agents to start informed and benefit from collective intelligence.
#AI Agents#Shared Memory#Knowledge Base#Collaboration#LLM#Context Management#Docker#Developer Tools
01
Features
01Multi-Instance Coherence: Shared memory ensures all AI agent instances are informed by others' decisions.
02Dream Pipeline: Automatically distills session events into structured memories.
03Universal Ingestion: Feed various data types (PDFs, images, git history) into the memory store.
04Strategic Consultation: Provides LLM guidance grounded in project context and team standards.
05Inter-Agent Messaging: Enables agents to send tasks, questions, and decisions across the network.
02
Compatibility
OpenAI API
LLM Provider
Verified via docs
Docker Compose
Deployment
Verified via docs
Claude Code
Client Agent
Verified via docs
Cursor
Client Agent
Verified via docs
SQLite
Database
Verified via docs
PostgreSQL
Database
Verified via docs
03
Quick start
1
$ git clone https://github.com/fjwood69/mori.git
2
$ cd mori
3
$ cp deploy/homelab/.env.example deploy/homelab/.env
4
$ docker compose -f deploy/homelab/docker-compose.yml up -d
04
Use cases
↳Enabling AI coding agents across different machines or teams to share learned knowledge and maintain consistency.
↳Onboarding new AI agents or team members by rapidly bootstrapping the memory store with existing project documentation and history.
↳Obtaining context-aware strategic advice and reviews (e.g., architecture, security) from LLMs based on project specifics.
↳Orchestrating complex tasks by delegating work and sharing decisions among multiple AI agent instances.
↳Persistent knowledge base for AI development projects, preventing repetitive learning and ensuring continuity.
05
Alternatives
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
agents-remember★ 29
`Agents Remember` is a Drift-aware repository memory for coding agents in complex codebases. Captures what code can't say on its own! Retrieves memory by path, semantic search, and relationship (code-graph).
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
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.
mex★ 1.8k
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
Comments
Log in to leave a comment
No comments yet. Be the first!