
agentglass
A looking glass for your coding agents: browse, watch, drill into and steer Claude Code, Codex & fx sessions from one tiny native TUI
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 agentglass (git-clone project) into my current project. Found on https://claudeers.com/agentglass Repo: https://github.com/BjoernSchotte/agentglass Homepage/docs: — Detected install method: git-clone → git clone https://github.com/BjoernSchotte/agentglass Category: mcp-servers. Platforms: cli, api, desktop, web. Read the repo's README for exact setup and env vars, then install it and wire it into my project. Claudeers Health Verdict: unknown; community-verified: false. Confirm the source before running anything.
git clone https://github.com/BjoernSchotte/agentglass
// compatibility
| Platforms | cli, api, desktop, web |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | Apache-2.0 |
| Pricing | open-source |
| Language | TypeScript |
◈ agentglass
See every coding agent on your machine — live, down to every tool call, diff and dollar. One tiny native TUI for Claude Code, Codex and fx: browse every session you ever ran, watch the running ones think, drill into any call, see where the time and money went, and get tapped on the shoulder when an agent needs you.
https://github.com/user-attachments/assets/7553c26d-2877-4dca-be2a-5508ec93707e
▶ 46 s launch video, recorded from the real binary in --redact mode · also in the repo: docs/media/agentglass-launch.webm
You have agents running in five tmux panes and two IDE windows, plus a Codex desktop app humming in the background. Which one is stuck? Which one just rewrote your auth layer? What did today cost? agentglass answers that in one keystroke.
| Every agent, one screen | Every call, every diff |
|---|---|
![]() | ![]() |
| Where the time went | What it costs |
![]() | ![]() |
Why it slaps
- Every agent, one screen. Claude Code (
~/.claude), Codex (~/.codex) and fx (~/.fx) sessions in one searchable list. Live sessions come first, and all your history is there too. - Live transcripts. Open a session and it follows the log as the agent works: prompts, thinking, tool calls and results as they land.
- Drill all the way down. Put the cursor on any event and hit
↵. You get the full tool call, its paired result, Edits as colored diffs, Writes and Reads with line numbers, and every file the agent touched. Press a number to open that file in$PAGERor$EDITOR. - Subagents, grouped. Subagents nest under their parent session and unfold automatically while
they work, so you see who is doing what right now. Hop between them with
n, go back up withu. - btop for agents. A process view shows every running harness with its process tree, CPU
braille graphs and memory. You also see what it's executing right now (that
pnpm test, that runawayfind), and you can SIGTERM or SIGKILL it with a confirm. - Talk back. Press
sto send a prompt. If the agent lives in tmux it's typed into its pane, otherwise agentglass resumes the session headless (claude -p --resume,codex exec resume,fx ask --resume-id). PressRto jump back into a session interactively. - Search everything.
/filters by title, path, id, branch or harness.Fruns a ripgrep full-text search across every transcript you've ever had. - Replay any session as a time-lapse. Press
Pin a transcript and watch the agent's run play back at 1×/4×/16×/64× from its own timestamps: pause, step, scrub. - See where the time went. Press
con a session (or in its transcript) for a call graph like the DevTools Performance panel: a zoomable flame chart of turns › tool calls › subagents › their tools, colored by tool kind, and a sortable call tree with total/self time, counts and errors.↵on any bar opens that call's detail. - Know what it costs. Tokens (in/out/cache) and API-equivalent cost per session and per day,
with Claude list prices built in and your own rates via
~/.agentglass/prices.json. A Stats tab shows today and the last 7 days: per-harness totals, busiest session, top tools, activity by hour. Top tools carry error rates (MCP servers grouped,␣expands);↵drills into one: p50/p95/max duration, calls over time, top shell programs and command lines, most-changed files, the slowest calls and latest errors —↵on one opens its session at that call. - It taps you on the shoulder. When an agent finishes a turn or seems to wait for an approval,
agentglass rings the bell, sends a macOS notification and marks the row
◆.!jumps there. - It spots stuck agents. Tool-call loops, stalled runs, commands running for 10+ minutes and
silent CPU burners get a red
⚠with the reason. - A live ticker in the header scrolls what every running agent is doing right now.
- Themes. tokyo-night, catppuccin (mocha and latte), gruvbox, nord and dracula. Press
Tor pass--theme. - Mouse too. Click rows, click again to open, click a preview line to jump straight to that event, click footer hints like buttons. Right-click goes back, and the wheel scrolls everything.
More screens
| Live transcript | Tool drill-down |
|---|---|
![]() | ![]() |
| btop for agents | Themes |
![]() | ![]() |
Privacy mode
Streaming, screenshotting or demoing? agentglass --redact swaps session titles, project names,
paths, branches and subagent tasks for consistent fakes, replaces the content of other sessions with
neutral stand-ins, and scrubs your username, home path, e-mail addresses, secrets and anything listed
in ~/.agentglass/redact.txt from every pixel — at the same width, so the layout stays intact.
AGENTGLASS_REDACT_KEEP=<path-substring> keeps chosen sessions readable (they are still scrubbed).
Every screen in this README and the launch video was recorded this way.
Tiny, fast, local
- ~1.5 MB native binary, starts instantly, zero runtime dependencies. It's TypeScript
compiled to native code with scriptc, with no Node,
no Bun and no
node_modulesat runtime. - Local only. It reads the agents' own session logs from disk and never phones home.
- Nothing to set up. It works with whatever is already in your home directory. Usage indexing
is incremental and cached in
~/.agentglass/cache, so restarts pick up where they left off.
Install
npm i -g scriptc # needs Node 24+ to build (not to run)
git clone https://github.com/BjoernSchotte/agentglass && cd agentglass
./build.sh # scriptc build src/main.ts -o agentglass
ln -s "$PWD/agentglass" ~/.local/bin/agentglass
agentglass
Keys
Press ? inside the app for the full, context-aware cheat sheet. The essentials:
↵ / click | open live transcript · drill into an event |
j k | move · in a transcript: previous / next event |
/ F | filter · full-text search |
␣ | fold / unfold subagents |
n u | next subagent · up to parent |
s R | send a prompt · resume interactively |
x X | SIGTERM / SIGKILL the agent |
1–9 e | open a referenced file in $PAGER / $EDITOR |
P | replay the open transcript |
c | call graph (flame chart ⇄ call tree with Tab) |
! | jump to the next agent waiting for you |
T | cycle themes |
Tab 1 2 3 | Sessions ⇄ Processes ⇄ Stats (↵ on a tool drills in) |
Scriptable
agentglass --json --live | jq '.[] | {title, costUsd, attention}' # snapshot of your sessions
agentglass --watch | jq -c 'select(.kind=="tool")' # live JSONL stream of every agent's events
agentglass --theme list # themes; --theme gruvbox-dark to pick one
agentglass --redact # privacy mode for streams and screenshots
Custom agent commands
If your agents run through wrappers (custom settings, profiles, proxies), point agentglass at them:
export AGENTGLASS_CLAUDE="claude --settings ~/.config/my/claude.json"
export AGENTGLASS_CODEX="codex --profile work"
export AGENTGLASS_FX="fx"
Supported harnesses
| sessions | live detection | subagents | send / resume | |
|---|---|---|---|---|
| ✻ Claude Code | ~/.claude/projects | session registry | subagents/ | ✔ |
| >_ Codex | ~/.codex/sessions | open rollout (lsof) | parent_thread_id | ✔ |
| ▲ fx | ~/.fx/sessions | open event log (lsof) | subagent/owner.json | ✔ |
Gemini, opencode, aider, amp and friends already show up in the process view. Their session browsers are next, and PRs are welcome.
License
// faq
What is agentglass?
A looking glass for your coding agents: browse, watch, drill into and steer Claude Code, Codex & fx sessions from one tiny native TUI. It is open-source on GitHub.
Is agentglass free to use?
agentglass is open-source under the Apache-2.0 license, so it is free to use.
What category does agentglass belong to?
agentglass is listed under mcp-servers in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/agentglass)
// retro hit counter
[](https://claudeers.com/agentglass)
// reviews
// guestbook
// related in MCP Servers
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete…
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
An open-source AI agent that brings the power of Gemini directly into your terminal.







