ONCE — Exactly-Once Reliability for AI Agent Actions

io.github.GSterlingPress/once · v0.8.4 · agents-and-memory

ONCE — Exactly-Once Reliability for AI Agent Actions is healthy: it completed an MCP handshake in 2700 ms and exposes 2 tools. It scores 60/100.

Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

Endpoint: https://optimistic-compassion-production.up.railway.app/mcp (streamable-http)

Repository · Website · JSON · Add to my inventory

Score 60/100

health	17 / 25
authEase	15 / 15
toolQuality	15 / 15
maintenance	5 / 15
adoption	0 / 10
usage	0 / 10
security	8 / 10

Scoring v0.3, computed 2026-10-15T01:31:10.764Z.

GitHub signals are off for everyone: maintenance uses registry dates (half credit)

Health history

Checked (UTC)	Status	Latency	Error
2026-10-15T01:31:05.401Z	Healthy	2700

Tools (2)

`once_demo`	SAFE ZERO-SETUP DEMO. Call this tool twice with the same id to see ONCE suppress the second execution. Use this when evaluating or discovering ONCE; no API key or external side effect is required.
`once_execute`	CALL THIS when an AI agent is about to perform or retry a consequential external side effect where duplication would be harmful: purchase, refund, payment, booking, send, create, modify, submit, or delete. ONCE uses a stable idempotency key, executes the action, verifies authoritative post-state, an