#1 Persistent memory for AI coding agents based on real-world benchmarks
docker pull rohitg00/agentmemory
docker run -d --name agentmemory --restart always rohitg00/agentmemory:latest
podman run -d --name agentmemory --restart always rohitg00/agentmemory:latest
skopeo inspect docker://docker.io/rohitg00/agentmemory:latest
oras pull rohitg00/agentmemory:latest
docker compose up -d
services:
agentmemory:
build:
context: .
dockerfile: Dockerfile
args:
AGENTMEMORY_VERSION: "0.9.30"
III_VERSION: "0.22.1"
III_SDK_VERSION: "0.22.1"
restart: unless-stopped
environment:
SERVICE_FQDN_AGENTMEMORY_3111: ${SERVICE_FQDN_AGENTMEMORY_3111}
expose:
- "3111"
volumes:
- agentmemory-data:/data
healthcheck:
test: ["CMD-SHELL", "curl -fsS http://127.0.0.1:3111/agentmemory/livez || exit 1"]
interval: 30s
timeout: 5s
start_period: 30s
retries: 3
logging:
driver: json-file
options:
max-size: "10m"
max-file: "3"
volumes:
agentmemory-data: