
agent-monitor
Visualize your Codex and Claude Code subagents. Advanced traces view, tokens breakdown, and cost usage is also supported.
Install with your AI
Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.
Install and set up agent-monitor (git-clone project) into my current project. Found on https://claudeers.com/agent-monitor Repo: https://github.com/donvito/agent-monitor Homepage/docs: — Detected install method: git-clone → git clone https://github.com/donvito/agent-monitor Category: devtools. Platforms: api. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: active; community-verified: false. Confirm the source before running anything.
git clone https://github.com/donvito/agent-monitor
// compatibility
| Platforms | api |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | — |
| Pricing | open-source |
| Language | TypeScript |
Agent Monitor
A local dashboard for Codex, Claude Code, Pi, and Hermes. Explore agent trees, read traces, and track token usage and estimated costs. Traces stay on your machine.

Download
Get the latest macOS, Windows, and Linux builds from Releases. The builds are not code-signed yet; the release notes explain how to open them.
Run from source
Requires Node.js 22.12+ and npm.
git clone https://github.com/donvito/agent-monitor.git
cd agent-monitor
npm install
npm run dev
Select a run from the sidebar to load its agents. Click an agent to inspect its trace, or use the icon on its node to open the trace in a tab. Click Details next to the token totals for the full breakdown.
Default sources:
| Provider | Local source |
|---|---|
| Codex | $CODEX_HOME/sessions or ~/.codex/sessions |
| Claude Code | $CLAUDE_CONFIG_DIR/projects or ~/.claude/projects |
| Pi | $PI_CODING_AGENT_DIR/sessions or ~/.pi/agent/sessions |
| Hermes | $HERMES_HOME/state.db, session-exports/traces, and sessions, defaulting to ~/.hermes |
Trace view
Open any agent in a tab to read its conversation, tool calls, and results, with links to its parent and subagents.

Token breakdown
Token totals and estimated API cost per agent, with usage charts over time.

Switch to By model to see tokens and cost grouped by model.

Screenshots use synthetic demo sessions.
More
// faq
What is agent-monitor?
Visualize your Codex and Claude Code subagents. Advanced traces view, tokens breakdown, and cost usage is also supported.. It is open-source on GitHub.
Is agent-monitor free to use?
agent-monitor is open-source, so it is free to use.
What category does agent-monitor belong to?
agent-monitor is listed under devtools in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/agent-monitor)
// retro hit counter
[](https://claudeers.com/agent-monitor)
// reviews
// guestbook
// related in Developer Tools
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Curs…
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…