edwinkys/phantasm
Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.
This tool helps business operations teams oversee and manage tasks performed by AI agents, especially for critical decisions where accuracy is paramount. It creates a human review layer where AI-proposed actions, like scheduling meetings, are sent to a person for approval or modification. The output is an AI agent whose actions are confirmed or corrected by a human before execution.
189 stars. No commits in the last 6 months.
Use this if you need to add a human review and approval step for AI agent actions that have high stakes or require human judgment, preventing costly mistakes.
Not ideal if your AI agent's actions are low-risk, highly autonomous, or do not require any human oversight.
Stars
189
Forks
7
Language
Svelte
License
GPL-3.0
Category
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.
Higher-rated alternatives
asklokesh/loki-mode
Multi-agent provider agnostic Autonomous system & framework that WORKS..!
ShunsukeHayashi/Miyabi
🤖 First open-source, economically-governed, beginner-friendly autonomous development framework...
jmagly/aiwg
Cognitive architecture for AI-augmented software development. Specialized agents, structured...
GaiaNet-AI/docs
The official documentation of Gaia. Learn how to run nodes, deploy nodes to domains, find...
GaiaNet-AI/node-configs
Find node configurations to easily setup your Gaia nodes on your machine with open source models...