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

oh-my-trace

v0.1.0

Published

CLI package for local AI agent history collection and AI-friendly export.

Downloads

18

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Maintainers

crispebblecrispebble

Keywords

aiagenttracemcpcodexclaudegeminicopilot

Readme

oh-my-trace

oh-my-trace installs the omt CLI. It collects local AI-agent history into a local SQLite store and exports AI-friendly context packs.

It does not generate retrospectives or summaries. Its job is to make local agent history safely searchable and readable by other AI tools.

Install

npm install -g oh-my-trace
omt init

The default home directory is:

~/.omt

Commands

omt init
omt doctor
omt ingest --since 2026-04-01 --source codex,claude,gemini,copilot-cli
omt status
omt query --since 2026-04-01 --format md
omt query --source codex --limit 20 --order desc --format md
omt query --source codex --since 2026-04-01 --until 2026-04-07 --limit 20 --order desc --format md
omt session <session-id> --format json
omt export --since 2026-04-01 --format context-pack
omt mcp

omt mcp prints installation guidance for the separate MCP package. Install the server with:

npm install -g oh-my-trace-mcp

Supported Agents

Supported by default:

  • codex
  • claude
  • gemini
  • copilot-cli

Experimental and disabled by default:

  • copilot-vscode
  • copilot-jetbrains
  • cursor
  • gemini-antigravity

Use omt agents or omt --help to view this list from the installed CLI.

omt query defaults to newest-first ordering. Use --order asc when you need oldest-first output.

omt status includes per-source collection counts and the latest ingest runs, so an operator can check what was collected for each agent/source.

Re-running omt ingest is idempotent for normalized events. Event IDs are deterministic and stored as primary keys, so duplicate events are ignored; the eventsInserted value reports only newly inserted events.

Use --home <path> in tests or isolated runs.

v1 Sources

  • Codex: ~/.codex/sessions/YYYY/MM/DD/*.jsonl
  • Claude Code: ~/.claude/projects/*/*.jsonl, ~/.claude/transcripts/*.jsonl
  • Gemini JSON: ~/.gemini/tmp/*/chats/session-*.json, logs.json
  • Copilot CLI: ~/.copilot/session-state/*/events.jsonl

Experimental sources are listed in config but disabled by default.

Safety

  • Source files are never modified.
  • Database-like sources must be copied/read-only before deeper parsing.
  • Credential-like content is redacted before persistence and export.
  • Auth/token/cookie storage paths are excluded.