WeDB
Agent Debugger (adb) is a terminal UI debugger that combines application-level agent inspection (state, memory, tool calls, messages) with Python-level debugging (breakpoints, stepping, variable inspection).
Core trick
Extends Python's Bdb debugger class so breakpoints and stepping run alongside agent state, messages, and tool calls in one Textual UI.
Description
Agent Debugger (adb) is a terminal UI debugger that combines application-level agent inspection (state, memory, tool calls, messages) with Python-level debugging (breakpoints, stepping, variable inspection).
A combined debugger makes interactively "zooming in / zooming out" seamless.
Also, adb enables generative debugging by providing interfaces and hooks for custom rendering of state, store, and chat output, and custom specification of inputs and state mutation.
The debugger is agent agnostic, and the engineering design is based on a agent streaming and extends Python’s standard-library debugger class (Bdb) .
The tool is released on pypi as agent-debugger.
More info here:
https://github.com/dkondo/agent-tackle-box/blob/main/projects/agent-debugger/README.md
https://github.com/dkondo/agent-tackle-box/blob/main/projects/agent-debugger/docs/Design.md
README excerpt
# agent-tackle-box A toolkit for developing AI agents. ## agent-debugger `agent-debugger` is a terminal debugger for LangGraph/LangChain agents. It combines agent-level visibility (state, messages, tool calls, store snapshots, and semantic breakpoints) with Python-level debugging (line breakpoints, stepping, stack, and locals) in one Textual UI. <img width="1679" height="1016" alt="image" src="https://github.com/user-attachments/assets/85f77ac9-45fc-4b66-ade9-bf79d148aa56" /> See [projects/agent-debugger/README.md](projects/agent-debugger/README.md) for full usage, commands, and extension details.