npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

agenticreplay

v0.1.11

Published

Record and inspect AI agent API traffic and activity

Readme

AgenticReplay

English · 简体中文 · 日本語 · 한국어 · Deutsch · Français · Español · العربية

AgenticReplay logs AI API traffic to help debug and improve AI harnesses. It captures requests and responses from supported clients, including reasoning/thinking content or summaries returned by the API. It also records tool, shell, MCP and filesystem activity that helps explain an agent run.

Browse the timeline, inspect the causal graph, and export a self-contained HTML report to find where a run went wrong.

Install

Requires Node.js 24+, Git, and a configured AI harness.

git clone https://github.com/askdkc/AgenticReplay.git
cd AgenticReplay
npm ci
npm run build
npm install -g .
agenticreplay doctor

Use

Run these commands in the project you want to investigate:

agenticreplay record claude -- -p "Investigate the failing test"
agenticreplay show last
agenticreplay export last -o run.html

Record the harness process that sends the API requests, such as Claude Code. Logs are stored in .agenticreplay/runs/ in that project; last selects the newest recording. Open run.html in a browser to inspect the trace.

Capture directories use YYYYMMDDHHmmss-agent-title-id (UTC). Names contain only lowercase ASCII letters, digits and hyphens: at most 255 characters, with titles capped at 80. Titles come from the session or, if unavailable, the first user prompt; they are redacted and transliterated to ASCII. The final name is applied when recording closes. Existing run_<id> directories and commands using a run ID remain supported.

For a custom harness that reads OPENAI_BASE_URL, replace node agent.js with its launch command:

agenticreplay record generic-openai -- node agent.js

For Codex with a ChatGPT subscription, use TLS interception:

agenticreplay record exec --tls-intercept -- codex

Recording runs the harness and may incur API charges. Redaction is best-effort: traces may still contain sensitive data. Review them before sharing.

See integrations for other harnesses and debugging a failing run for an example.

License

Apache-2.0. Trace specification: CC BY 4.0.