Alimenter votre agent
Installation de l'éditeur. Ce n'est pas un endpoint PlugMCP.
Host a copy with our keys and logs.
Pas encore de version packagée dans le registre. Suivez le README du dépôt.
URL distante ou commande sur votre machine ? Ce qui distingue les deux installations
Exécuter sur PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LancerGolemCore Bot is the agent platform for AI-native companies building on the GolemCore ecosystem.
Use it to run channel-connected agents, extend them with skills, plugins, and MCP servers, and operate them with memory, delayed follow-ups, trace inspection, and Hive-connected control flows.
Use it in two ways:
docker pull ghcr.io/alexk-dev/golemcore-bot:latest
docker run -d \
--name golemcore-bot \
--shm-size=256m \
--cap-add=SYS_ADMIN \
-e STORAGE_PATH=/app/workspace \
-e TOOLS_WORKSPACE=/app/sandbox \
-v golemcore-bot-data:/app/workspace \
-v golemcore-bot-sandbox:/app/sandbox \
-p 8080:8080 \
--restart unless-stopped \
ghcr.io/alexk-dev/golemcore-bot:latest
docker logs -f golemcore-bot
# Health probe:
# curl http://localhost:8080/api/system/health
#
# Compatibility: Docker CMD overrides may still pass Spring Boot args directly:
# docker run ... ghcr.io/alexk-dev/golemcore-bot:latest --server.port=9090
# Open http://localhost:8080/dashboard
# On first start, check logs for the temporary admin password.
Open http://localhost:8080/dashboard, sign in with the temporary admin password from the logs, then configure your LLM providers in Settings.
Why the extra Docker flags?
--shm-size=256m and --cap-add=SYS_ADMIN are needed for the Browser tool (Playwright/Chromium) in containers.
See Configuration → Browser Tool.Need a local build, Compose setup, or production deployment path? See Quick Start and Deployment.
Besides Docker and the plain executable JAR, the release workflow now also publishes a local app-image bundle for the current OS/architecture.
./mvnw clean package -DskipTests -DskipGitHooks=true
npx golemcore-bot-local-build-native-dist
This produces an archive in:
target/native-dist/golemcore-bot-<version>-<platform>-<arch>.tar.gz
The app-image contains:
jpackagelib/runtime/So the startup order becomes:
updates/current.txt, unless the bundled runtime jar is newerThe native launcher uses picocli, so it has first-class help and a small set of launcher-specific flags.
Show help:
./golemcore-bot/bin/golemcore-bot --help
Common options:
web — required command that starts the bundled Spring Boot runtimeweb --port=<port> — forwards -Dserver.port=<port> to the spawned runtimeweb --hostname=<address> — forwards -Dserver.address=<address> to the spawned runtime--storage-path=<path> / web --storage-path=<path> — forwards -Dbot.storage.local.base-path=<path>--updates-path=<path> / web --updates-path=<path> — forwards -Dbot.update.updates-path=<path>--bundled-jar=<path> — overrides the bundled runtime jar pathweb -J=<jvm-option> / web --java-option=<jvm-option> — forwards extra JVM options to the spawned runtimeThe native package starts the Spring runtime with the prod profile by default.
Examples:
./golemcore-bot/bin/golemcore-bot web --port=8080 --hostname=0.0.0.0
./golemcore-bot/bin/golemcore-bot web -J=-Xmx1g --port=9090
./golemcore-bot/bin/golemcore-bot --storage-path=/srv/golemcore/workspace web --updates-path=/srv/golemcore/updates
Unknown arguments are forwarded to Spring Boot unchanged, so existing application arguments continue to work:
./golemcore-bot/bin/golemcore-bot web --server.port=9090
./golemcore-bot/bin/golemcore-bot web --spring.main.banner-mode=off
./golemcore-bot/bin/golemcore-bot web -Dlogging.level.root=INFO
If you want to make the split explicit, you can also use -- before Spring arguments:
./golemcore-bot/bin/golemcore-bot web --port=9090 -- --spring.main.banner-mode=off
This keeps the existing self-update model based on:
updates/current.txtupdates/jars/while also letting the bot start cleanly from a native local bundle with documented launcher parameters.
For runtime config details, storage layout, and browser or sandbox notes, see Configuration.
Documentation site: https://docs.golemcore.me/
The source docs below are kept in this repo for local and offline reference:
⭐ Star this repo if you find it useful!
Made with ☕ and 🤖
Agent Platform for AI-Native Companies
Outils
Pas encore de liste d'outils. Les serveurs distants en obtiennent une après le premier contrôle d'état.
FAQ
Copiez sur cette page la configuration stdio pour Cursor, Claude Desktop, Claude Code ou VS Code. Elle utilise l'installation de l'éditeur, pas un proxy PlugMCP.
Aucune variable d'environnement requise n'est indiquée sur cette fiche.
Golemcore Bot s'exécute en local via stdio.
Dernière vérification : 2026-10-27. Agent Platform for AI-Native Companies