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

@axon-ai/cli

v1.0.12

Published

CLI tool for Axon - Monitor LangChain agents in real-time

Readme

@axon-ai/cli

The Axon CLI runs a local, OpenTelemetry-native LLM-observability stack — backend and dashboard on a single URL. Point any OTEL/OpenLLMetry exporter at it and watch your LLM/agent traces in real time. No Axon-specific SDK needed.

Install

npm install -g @axon-ai/cli

Quick start

axon start
#   ✔ Axon running at http://localhost:4000

Then send standard OpenTelemetry spans to http://localhost:4000. With OpenLLMetry (Node):

import * as traceloop from "@traceloop/node-server-sdk";
traceloop.initialize({ baseUrl: "http://localhost:4000" });
// use LangChain / OpenAI / Anthropic / LlamaIndex normally — traces appear in Axon

Or with a raw OTEL SDK: OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4000.

Open http://localhost:4000 (on Windows use http://127.0.0.1:4000 if localhost won't connect). Traces are stored per project under ./.axon-ai/traces.db.

Commands

axon start

Start Axon (backend + dashboard on one URL).

  • -p, --port <port> — port to serve on (default: 4000)
  • --no-open — don't open the browser automatically
  • --project <name> — project name for organizing traces

axon status

Report whether Axon is running and on which port.

axon stop

Stop Axon.

axon version

Print the CLI version.

axon, axon-ai, and agent-trace are aliases for the same CLI.

The dashboard

Each trace offers four views:

  • Transcript (default) — the run as a chat dialogue (user → model → tool → result).
  • Tree — the span hierarchy with inline duration bars.
  • Waterfall — duration bars on a shared time axis.
  • Raw — the verbatim OTEL span JSON, with a copy button.

Plus a per-trace cost-by-model breakdown.

Troubleshooting

Port already in use — start on another port: axon start --port 5000, or stop the process holding 4000.

localhost won't connect (Windows) — open http://127.0.0.1:4000 instead; localhost may resolve to IPv6 while the server binds IPv4.

Migrating from the old tracer packages

@axon-ai/langchain-tracer and @axon-ai/openai-tracer are deprecated. Use standard OTEL instrumentation (OpenLLMetry / OpenInference) pointed at http://localhost:4000 instead.

License

MIT — see LICENSE.