Today we're releasing Cordum v0.1.0, the first public version of our open-source AI agent orchestration platform. After months of development and internal testing, we're ready to share it with the world.
Why Now?
AI agents have reached an inflection point. They can write code, manage infrastructure, respond to incidents, and automate complex business processes. But there's a problem: most organizations can't deploy them in production.
The gap isn't capability—it's trust. Without governance, audit trails, and human oversight for risky operations, autonomous agents remain stuck in demo mode. Cordum bridges this gap.
What's in v0.1.0
Safety Kernel
Policy-before-dispatch evaluation with four decision types: ALLOW, DENY, REQUIRE_APPROVAL, ALLOW_WITH_CONSTRAINTS
Workflow Engine
DAG-based execution with step types for workers, approvals, delays, notifications, and conditions
Pack System
Installable overlays that extend the platform without touching core code
MCP Native
Model Context Protocol support for Claude, GPT, and any compatible AI agent
Getting Started
The fastest way to try Cordum is with Docker Compose:
git clone https://github.com/cordum-io/cordum.git
cd cordum
docker compose up -dThe dashboard will be available at localhost:8082. Check out our quickstart guide for a full walkthrough.
Open Source
Cordum is released under the Business Source License 1.1 (BUSL-1.1), which converts to Apache 2.0 after 4 years. You can use it freely for development, testing, and internal production use. The source code is available on GitHub.
What's Next
This is just the beginning. Our roadmap includes:
- More pre-built packs for common use cases (incident response, infrastructure automation)
- Enhanced MCP integrations
- Policy simulation and testing tools
- Expanded documentation and tutorials
We'd love your feedback. Join us on GitHub, open issues, contribute PRs, or just star the repo if you find it useful.
Thanks for reading. Let's build the future of AI agent orchestration together.