edwinkys/phantasm

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

34
/ 100
Emerging

Phantasm provides a three-component architecture—server, web dashboard, and client library—that intercepts AI agent actions for human review before execution, with support for parameter modification by approvers. It framework-agnostic, working with any AI model or platform, and includes a load balancer for distributing approval requests across multiple reviewers. The system handles real-time request/response cycles with configurable timeouts and fallback mechanisms for scenarios where approvers are unavailable or reject actions.

189 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

189

Forks

7

Language

Svelte

License

GPL-3.0

Last pushed

Nov 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/edwinkys/phantasm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.