924bf2244d
All checks were successful
Build and Push Agent / build (push) Successful in 4s
- Complete guide for accessing terminal web (claude.fuq.tv) - MCP endpoints usage examples - Typical workflow from task to PR - Troubleshooting section - MCP config template (for future use) Co-Authored-By: Claude Sonnet 4.5 (1M context) <noreply@anthropic.com>
AiWorker Agent
Claude Code agent running in Kubernetes pods to autonomously complete development tasks.
Architecture
The agent:
- Runs in K8s namespace
agents - Communicates with backend via MCP protocol
- Has access to Git repositories via Gitea
- Reports progress and status to backend API
Local Development
This is a containerized agent meant to run in Kubernetes. For local testing:
docker build -t aiworker-agent:local .
docker run -it --rm \
-e ANTHROPIC_API_KEY=your_key \
-e BACKEND_URL=http://localhost:3000 \
aiworker-agent:local \
/bin/bash
Deployment
See k8s/agents/README.md for deployment instructions.
MCP Tools
The agent uses these MCP tools to communicate with the backend:
get_next_task- Get next task from queueupdate_task_status- Update task statecreate_branch- Create Git branch for taskcreate_pull_request- Create PR when task is completeask_user_question- Request user input when needed
Environment Variables
ANTHROPIC_API_KEY- Claude API keyBACKEND_URL- Backend API URLMCP_SERVER_URL- MCP server URLGITEA_URL- Gitea URLGITEA_TOKEN- Gitea access tokenPOD_NAME- Pod name (auto-injected by K8s)NAMESPACE- Namespace (auto-injected by K8s)