Call4Agents 0.6 released as agent action retry library
Understand this story
Salah Eddine Makboul has released an early version of Call4Agents 0.6, aimed at making Python agent actions safely retryable. The library provides mechanisms such as one-shot actions, approvals bound to exact parameters, revocation and idempotency keys, and can integrate with LangGraph, Pydantic AI, OpenAI Agents SDK, MCP server or plain Python. This version depends only on the standard library with zero dependencies, with optional PostgreSQL for multi-machine scenarios. The author says it is still experimental, has no real users yet, and its API may change; it has been tested on Linux, macOS and Windows as a standalone process and with local PostgreSQL, but not yet on real networks or in production.
AI overview based on source reports · Updated 11 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Replay three AI agent approval failures in five seconds, in Python
Call4Agents is a zero-dependency Python library that adds once-only actions, approvals bound to exact arguments, undo, idempotency keys and record/replay/diff to existing agents built on LangGraph, Pydantic AI, the OpenAI Agents SDK, MCP or plain Python. Its `call4agents incident` and `call4agents quickstart` commands reproduce crash-and-resume double actions (e.g. 2 emails without the kit, 1 with it) in real processes, and version 0.6 is Apache-2.0 with an optional PostgreSQL backend for multiple machines.
Activity for this story
- Current comparable activity
- 7
- Peak comparable activity
- 10Nov 6 04:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.