cokodo-agent is a CLI and convention directory that facilitates AI collaboration by managing project assets related to AI's memory and rules. It provides tools for versioning, syncing, and checking project states.
From the registry: Serve .agent/ project context, references, and collaborations to MCP-compatible IDEs.
$ pipx install cokodo-agenthttps://pypi.org/project/cokodo-agent/Please install the `cokodo-agent` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install cokodo-agent** — Install the CLI via pipx or pip. Run: `pipx install cokodo-agent` (https://pypi.org/project/cokodo-agent/)
Canonical MCP server config (stdio transport):
- command: `co`
- args: ["serve"]
Note: Run 'co init' in your project to create .agent/ directory first. Use 'co serve --workspace' to serve multiple project directories.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.