Back to directory

Swival

A small, open-source Python CLI coding agent designed to work as well with local and small open models as with large hosted ones, with built-in note-taking, goal tracking and a review step.

Swival

Swival is a coding agent that treats local models (via LM Studio or similar) and online services through the same tool, without needing to change agents when switching models. It keeps working notes on what it has learned and what remains to be done so an interrupted session can resume, and a goal-setting option keeps it working toward a stated objective across a long task.

An optional review step has Swival check its own work and retry when problems are found, or hand review to a different model; a built-in security audit checks existing code for bugs. For hosted services, secret encryption can hide supported API keys and tokens before they reach the model, and filters can strip other private details such as customer names and internal URLs. It installs with uv tool install or Homebrew and is written in Python, so it can also run as part of a Python program.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.