llm-coding-agent 0.1a0

Release: llm-coding-agent 0.1a0

Simon Willison has published a new Python library built on his evolving LLM library. This project serves as an experiment in creating a simple coding agent.

The developer started a new Python library using his python-lib-template-repository GitHub template repository. He then ran two prompts (here’s the Claude Code for web transcript):

Write a spec.md for this project - it will depend on the latest "llm" alpha from PyPI and implement a Claude code style coding agent complete with tools for reading and editing files and executing commands

Then:

Commit the spec, then build it using red/green TDD in a series of sensible commits (each with passing tests and updated docs) - occasionally manually test it using the OpenAI API key in your environment

Here’s the resulting README file and the sequence of commits.

Willison has shipped a slop-alpha to PyPI, so you can run the new agent like this:

uvx --prerelease=allow --with llm-coding-agent llm code

It’s pretty good for a first attempt. The README lists recipes like llm code --yolo and llm code --allow "pytest*" --allow "git diff*".

The tool also presents a Python API based around a CodingAgent(model="gpt-5.5", root="/path", approve=True).run("Fix the failing test in tests/test_parser.py") class which Willison did not ask for but he is delighted to see implemented.

Here’s the suite of tools it implemented, listed using uvx ... llm tools:

CodingTools_edit_file(path: str, old_string: str, new_string: str, replace_all: bool = False) -> str

Replace an exact string in a file.

old_string must match the file contents exactly (including whitespace) and must identify a unique location unless replace_all is true. Returns a diff of the change so it can be verified.

CodingTools_execute_command(command: str, timeout: int = 120) -> str

Run a shell command in the session root directory.

Returns combined stdout and stderr followed by an Exit code line. timeout is in seconds (maximum 600); on timeout the whole process tree is killed.

CodingTools_list_files(pattern: str = '**/*', path: str = '.') -> str

List files matching a glob pattern, newest first.

Skips hidden directories, node_modules, __pycache__ and (in a git repository) anything covered by .gitignore. Returns at most 200 paths relative to the searched directory.

CodingTools_read_file(path: str, offset: int = 0, limit: int = 2000) -> str

Read a text file, returning numbered lines like cat -n.

Paths are relative to the session root. Use offset (0-based first line) and limit (max lines) to page through files too large to read in one call.

CodingTools_search_files(pattern: str, path: str = '.', glob: str = None, max_results: int = 100) -> str

Search file contents for a regular expression.

Returns matches as path:line_number:line, capped at max_results. Use glob (e.g. “*.py”) to restrict which files are searched.

CodingTools_write_file(path: str, content: str) -> str

Create or overwrite a file with the given content.

Parent directories are created as needed. Prefer edit_file for modifying existing files.

What it means

Developers can now run a coding agent directly from the command line or via a Python class. The agent handles file editing, command execution, and code searching with specific constraints like timeouts and file skipping. It operates on a local environment rather than a remote server.

Tags: projects, ai, generative-ai, llm, llm-tool-use, coding-agents, claude-code, claude-mythos