About

I’m Liang Li, an engineer working on AI agent infrastructure.

I build and maintain a small but connected stack:

agent-go — a Go agent framework: builder API, tool calling, memory, multi-agent teams.
harness-rs — an agent framework in Rust.
miniagent — a pedagogical agent framework in Python.
eval-go — a native-Go eval framework that scores and runs agents, so the three above can be benchmarked side by side.

I care about the parts that don’t demo well: error recovery, loop robustness, honest evaluation.