Built a macOS debugger for AI agents — visualize LLM call chains in real time
Summary
Tether is a local proxy for macOS that captures every LLM call and visualizes them as a live node graph, enabling time-travel debugging.
Similar Articles
@zxlzr: Introducing MemTrace: Making LLM Memory Systems Finally Debuggable Memory is becoming a core component of AI agents. Bu…
MemTrace is a new tool that makes LLM memory systems debuggable by tracing memory operations across multiple turns, addressing the black-box nature of current memory-augmented agents.
Proxy for LLMs to learn how Agents works?
User seeks an open-source proxy to intercept and debug API calls from AI agents to understand their internal workings, after finding LiteLLM too enterprise-focused.
How to setup a local coding agent on macOS
A detailed tutorial on setting up a local coding agent on macOS using Gemma 4 with MTP draft model and llama.cpp, achieving ~24% speed improvement through speculative decoding.
@benhylak: we built the first sane way to debug your agent locally. you can see your traces. codex/claude code can too. this lets …
A new open source tool enables local debugging of AI agents by viewing traces, allowing automated eval writing and testing with tools like codex and Claude code.
@svpino: Open-source always finds a way! This is an open-source, local-first memory layer for LLM agents. It's for Mac users. Th…
An open-source, local-first memory layer for LLM agents on macOS that captures user activity and saves it as Markdown files.