Local UIs
Find and open locally running web interfaces
Antreas Antoniou
@antreasantoniou
Install
$ openclaw skills install @antreasantoniou/local-uisLocal UIs
Discover what is serving now instead of relying on a hard-coded port list.
Run
python3 scan_uis.py
Use --no-open to create the launcher without opening it, or --json for machine-readable results.
The scanner:
- reads TCP listeners with
lsof; - limits probes to services reachable through
127.0.0.1; - performs short HTTP probes in parallel;
- records response status, page title, process name, and PID;
- writes
~/.local/state/local-uis/dashboard.html.
Interpret results
- 2xx and 3xx responses are available.
- 401 and 403 responses show a live service that requires authentication.
- Other 4xx and 5xx responses are reachable but unhealthy or not serving a root page.
- The dashboard is a snapshot. Re-run the scan before making a current-state claim.
Safety
- The tool does not probe other hosts or non-loopback addresses.
- A service bound to all interfaces may still be externally reachable; this scanner does not establish network isolation.
- Page titles and process metadata can be sensitive. Do not publish the generated dashboard without review.
- Do not treat an HTTP response as proof that the application behind it is healthy.
On macOS the dashboard opens with open; on Linux it uses xdg-open when available.
Top skills in this category
self-improving agent
@pskoettCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
Skill Vetter
@spclaudehomeSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Self-Improving + Proactive Agent
@ivangdavilaSelf-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Proactive Agent
@halthelobsterTransform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack ๐ฆ
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection