Daemon OS
Daemon OS provides AI agents with the ability to see and operate every application on macOS by reading the native accessibility tree rather than relying on screenshot-based pixel guessing. It exposes 20 tools covering perception (inspecting UI elements, reading text, capturing screenshots), actions (clicking, typing, scrolling, keyboard shortcuts), window management, and a wait system for synchronization. The recipe engine allows workflows to be captured as transparent JSON files, so a frontier model figures out the process once and a smaller model can replay it reliably. Distributed via Homebrew and written in Swift, it runs entirely locally with no data leaving the machine.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/hammadxcm/daemon-os
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Daemon OS from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.