Agents Observe
Real-time observability dashboard for Claude Code agents.
Includes powerful filtering, searching, and visualization of multi-agent sessions.
The server and dashboard run locally or remotely, allowing multiple Claude Code instances to log full session data using hooks.
Hooks are used instead of OTEL to capture the full picture of agent actions.
Plugin Installation
Prerequisites
Install
-
Add the marketplace:
claude plugin marketplace add simple10/agents-observe -
Install the plugin:
claude plugin install agents-observe -
Restart Claude Code.
That's it. On your next session, the server auto-starts as a Docker container and hooks begin capturing events. Open http://localhost:4981 to see the dashboard.
Plugin Skills
| Skill | Description |
|---|---|
/observe | Open the dashboard URL and check if the server is running |
/observe status | Check server health and show dashboard URL |
Why observability matters
When Claude Code runs autonomously — spawning subagents, calling tools, reading files, executing commands — you have no visibility into what's actually happening. The terminal shows a fraction of the activity. Subagents are invisible. Tool calls blur together. And when something goes wrong three agents deep in a parallel execution, you're left reading through logs after the fact.
Claude Observe captures every hook event as it happens and streams it to a live dashboard. You see exactly what each agent is doing, which tools it's calling, what files it's touching, and how subagents relate to their parents. In real time.
This matters because:
- Multi-agent work is opaque. A coordinator spawns a code reviewer, a test runner, and a documentation agent in parallel. Without observability, you only see the final result. With it, you watch each agent work and catch problems as they happen.
- Tool calls are the ground truth. The assistant's text output is a summary. The actual tool calls — the Bash commands, file reads, edits, grep patterns — tell you what Claude is really doing. Claude Observe shows you both.
- Debugging is time travel. When a subagent makes a bad edit or runs a destructive command, you need to trace back through the exact sequence of events. The event stream gives you that timeline with full payloads.
- Sessions are ephemeral, but patterns aren't. By capturing events across sessions, you can see how agents behave over time, which tools they favor, and where they get stuck.
What you can do
- Watch tool calls stream in as they happen (PreToolUse → PostToolUse with results)
- See the full agent hierarchy — which subagent was spawned by which parent
- Filter by agent, tool type, or search across all events
- Expand any event to see the full payload, command, and result
- Click timeline icons to jump to specific events in the stream
- Browse historical sessions with human-readable names (e.g., "twinkly-hugging-dragon")
Architecture
Claude Code Hooks → observe_cli.mjs → API Server (SQLite) → React Dashboard
(dumb pipe) (HTTP POST) (parse + store) (WebSocket live)
The hook script is a dumb pipe — it reads the raw event from stdin, adds the project name, and POSTs it to the server. The server parses events, stores agent metadata (name, type, parentage), and forwards events to subscribed WebSocket clients. The React dashboard derives all agent state (status, event counts, timing) from the event stream — the server is a dumb store.
Standalone Installation
For development or running without the plugin. If you installed via the plugin above, skip this section.
1. Clone and install dependencies
git clone https://github.com/simple10/agents-observe.git agents-observe
cd agents-observe
# Install just if needed
brew install just
# Start the docker container
just start
# Or start local dev servers
just install
just dev
See justfile for additional commands.
2. Configure Claude Code hooks
Generate the hooks config for your project:
just setup-hooks my-project