ReskPoints: AI Agent Logging with Sampling, Masking, and Multi-Export

ReskPoints, a new Python library from Resk Security, provides purpose-built logging for AI agent loops with features like sampling, masking, and multi-export to console, Datadog, Prometheus, and OpenTelemetry. The library captures every agent action with context, including tool calls, latency, and token counts, and requires Python 3.13+ with zero required dependencies beyond the chosen exporters.

ReskPoints makes every agent action observable. Console, Datadog, Prometheus, OpenTelemetry — one install, all exporters. Links: A typical AI agent orchestrator makes dozens of tool calls per user request. Each call has request parameters a response latency and a success or failure state. When something goes wrong you need to replay what the agent was thinking and doing. Standard Python logging gives you raw text. Datadog APM gives you traces but not the agent intent layer. You need a purpose-built logger that captures the agent loop not just the HTTP calls. ReskPoints is a Python library that hooks into your agent loop and records every action with context. Here is the core API: python from reskpoints import AgentLogger logger = AgentLogger service="my-agent", sampling rate=0.1, keep 10 percent of actions exporters= "console", "datadog", "prometheus" , masks= "api key", "user.email" Inside your agent loop logger.log action action="tool call", tool="search docs", input={"query": user input}, output=result, duration ms=340, token count=1200 The library works with Python 3.13+ and has zero required dependencies beyond the exporters you use. pip install reskpoints Then add one AgentLogger instance to your agent loop and wire your exporters. Full docs on GitHub. https://github.com/Resk-Security/ReskPoints https://github.com/Resk-Security/ReskPoints What logging setup do you use for your AI agents?