hypabolic-trajectory is a Python package that converts unstructured transcripts from coding agents into standardized, deterministic Trajectory contract formats. It is designed for observability, evaluation, and reproducible testing of autonomous coding agents. The library outputs clean JSONL data and is available under the MIT license on PyPI and GitHub.
In the LLM eval & observability space, hypabolic-trajectory takes a focused approach. Inconsistent and hard-to-analyze transcripts from AI coding agents. It is built as an open-source project for developers building and evaluating AI coding agents. The project is open source (MIT). It runs on the command line.
Behind hypabolic-trajectory is Hypabolic, and it first shipped in 2026. Development happens publicly on GitHub with 197 commits in the last 90 days. Key capabilities include transcript normalization, JSONL output, and deterministic contracts.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do