Lars Nilse lars20070

• Freiburg, Germany

Pinned Loading

1. Evaluation framework for Pydantic AI agents

   Python 1

2. 1

   # Agent evaluations with `pytest-assay`

   3

   * [`pytest-assay`](https://github.com/lars20070/pytest-assay) was written to address two problems:

   4

       1. Limited access to agent responses, making flexible evaluation difficult

   5

       2. Lack of scoring evaluations — most frameworks only support binary pass/fail evaluations

3. MCP server for WolframScript

   Python

4. fully local web research and report writing assistant based on PydanticAI

   Python 8 4

5. 2

   FROM mcr.microsoft.com/devcontainers/python:${PYTHON_VERSION}-trixie

   4

   # Copy uv and uvx (latest version)

   5

   COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/

6. Forked from 1st1/lat.md

   Agent Lattice: a knowledge graph for your codebase, written in markdown.

   TypeScript