Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
# docker-compose.yml for ai-memory.
#
# Run from this directory:
# docker compose up -d
# Attach Claude Code (or any MCP HTTP client) at
# http://localhost:49374/mcp
# State persists in the `ai-memory-data` volume. Use `ai-memory backup`
# for an online snapshot, or stop the container before copying the volume.
# See docs/backup.md for moving a backup to another host.
services:
ai-memory:
image: ai-memory:local
build:
context: ..
dockerfile: docker/Dockerfile
container_name: ai-memory
restart: unless-stopped
user: "1000:1000"
volumes:
- ai-memory-data:/data
ports:
# Bind to loopback by default; flip to 0.0.0.0:49374 when serving
# the homelab LAN. Keep behind a reverse proxy if you do.
- "127.0.0.1:49374:49374"
env_file:
- path: .env
required: false
environment:
- RUST_LOG=ai_memory=info,ai_memory_store=info,ai_memory_wiki=info,ai_memory_mcp=info,tracing_appender=warn
# LLM provider configured via docker/.env (gitignored). Options:
# anthropic | openai | openai-oauth | anthropic-oauth | copilot |
# gemini | openai-compat | opencode
# See .env.production.example for the full reference.
#
# Extra headers on every LLM chat request, for a gateway that requires
# a caller-identifying one. Comma-separated `Name=Value` entries; the
# default `User-Agent: ai-memory/<version>` needs no configuration.
# - AI_MEMORY_LLM_HEADERS=x-opencode-session=homelab-01
healthcheck:
test: ["CMD", "/usr/local/bin/ai-memory", "status"]
interval: 30s
timeout: 5s
retries: 3
start_period: 5s
volumes:
ai-memory-data:
name: ai-memory-data