portal-tunnel
Enables secure, self-hosted connectivity between local development environments and autonomous AI agents.
Publishes localhost services to the agentic web through self-hostable, trustless relays.
- Expose local development services to external AI agents via secure relays
- Create trustless tunnels to connect localhost applications to the web
- Host your own relay server to maintain control over service access
Enables secure, self-hosted connectivity between local development environments and autonomous AI agents. This mitigates the security risks of exposing internal services while allowing agentic workflows to interact with private local resources.
DevOps engineers and AI researchers building secure integration layers between local services and agentic web protocols.
https://github.com/gosuda/portal-tunnel
By gosuda
How to Get It
claude plugins install gosuda/portal-tunnel
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me expose local development services to external AI agents via secure relays
Trust Signals Auto-scanned
Community Pulse Emerging
Discussed on Hacker News
- Show HN: Portal – Relay network to expose local services to public web endpoint — Hacker News · 2 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 291 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 291 GitHub stars; contributors unknown; last commit 0d ago; license MIT.