Back to directory

SWE-AF

A runtime built on AgentField that spins up an autonomous team of planning, coding, review and testing agents from a single API call to produce production-grade pull requests.

SWE-AF

SWE-AF triggers a full autonomous software engineering team, product managers, architects, coders, reviewers and testers, from one API call or the af CLI, given a goal and a repository URL. The team scopes, builds, adapts and ships changes end to end, and each agent role can be assigned its own model.

It supports two operating modes: single-repository mode, where it works against one remote or local repository, and multi-repository mode, where a build coordinates changes across a primary repository and dependent repositories such as shared libraries or microservices, with failures in dependencies captured but not blocking the primary build.

It is built on AgentField and requires the af CLI.

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.