Skip to content

GraphMind

Open source · MIT · Local-first

The live debugger for AI agents.

Attaches while it’s happening.

Phoenix and Langfuse show you what your agent did. GraphMind attaches to the run itself: watch execution as a live graph, hold the agent at a gate, read every input, output and token, substitute a result, and let it carry on.

npx graphmind-ai demo

One command, no API key. Replays a recorded agent that hits a planted bug — and really pauses on it.

The GraphMind viewer: an agent run drawn as a live graph, pausing on a failing tool call, with the inspector open on its inputs and outputs.
graphmind demo — pause on error, inspect, inject, resume.

Pause on error

Armed by default. The first time a tool throws, the agent stops in place — arguments, partial state and stack still live — instead of leaving you a trace to read afterwards.

Breakpoints & step mode

Break before any node by kind or name, or step every boundary. Held gates are indefinite: nothing is in flight while you think.

Inject and continue

Replace a tool’s result — or a failure — with a value you type, and let the agent keep running on it. Test the recovery path without touching your code.

Debug an MCP server

You cannot printf-debug a server whose stdout is the protocol. Put graphmind mcp-proxy between the host and the server: see every request, hold one, inject a response. Any language, no code changes.

Fails open, always

No debugger attached? Instrumentation is a no-op. Debugger disconnects mid-hold? Every gate auto-continues. Your production path never waits on a viewer.