1. Insufficient Context Is the Key Constraint on AI Agent Adoption The quality of an Agent’s work depends both on model capability and on the environmental context it can reach. For development and operations, the harder part is that the environment is often fragmented: logs live on production, docs in a knowledge base, code in a Git repository.

1. Business Bypasses the Middle Platform At the moment I work on Infra at a fairly large AI middle-platform team. After a department meeting early this year, I started wondering whether the middle platform would disappear. OpenClaw was very popular at the time. Business colleagues using OpenClaw with a large model could already get a great many things done without cooperating with other teams — the division of labor disappeared.

1. Starting the Container Set the image 1 export IMAGE=nousresearch/hermes-agent:v2026.6.5 Set directory permissions 1 2 mkdir -p hermes-agent-home chmod -R 777 hermes-agent-home Set environment variables 1 2 3 cat <<EOF > hermes-agent-home/.env GATEWAY_ALLOW_ALL_USERS=true EOF Start hermes-agent 1 2 3 4 5 6 7 8 9 10 nerdctl run -d \

1. Architecture 1 2 3 4 5 6 7 ┌──────────────────────┐ A2A/JSON-RPC ┌───────────────

1. Production Cases Cleaning up a node Restarting a node Deleting an abnormal Pod Inspecting the cluster 2. Two Steps to Get Configured Step one: configure MCP. Hand this configuration to OpenClaw and it will set it up for you. 1 2 3 4 5 6 7 8 { "mcpServers": { "ops-mcp-server": { "baseUrl": "http://ops-mcp-server/mcp", "headers": { "Authorization": "Bearer xxx" } } } } Step two: install skills.