starnet
View on GitHubA living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
A local-first desktop harness for creating and running multi-agent teams with distinct workspaces, tools, permissions, memory, and schedules. Supports cloud providers, Ollama, MCP connectors, and messaging integrations; the pixel-art station reflects live runtime state.
Use Cases
Run multiple agents concurrently with separate workspaces and permissionsCreate capability-scoped agent teams and workflowsConnect agents to messaging platformsSchedule agents to work with logged, adjustable permissionsExtend agent capabilities with MCP servers and connectorsRun agents with cloud providers or local Ollama modelsImport agent personas and memory from OpenClaw or Hermes
Built With
- Language
- JavaScript
- Frameworks
- Tauri · Node.js · Ollama · OpenRouter · Model Context Protocol
Tags
multi-agent · agent-harness · desktop-app · local-first · BYOK · agent-tools · agent-skills · agent-scheduling · MCP · pixel-art