🤖
AI EngineeringGo

SWE AF

by Agent-Field

SWE AF is an AI Engineering skill for Claude Code, published by Agent-Field in SWE-AF.

981 stars167 forkson Agent-Field/SWE-AFAdded 2026/08/21+1% in starsRepository updated 2026/08/20
View source on GitHubDownload repo ZIP
agent-factoryagentfieldagentic-aiai-agentsai-factoryautonomous-agentsclaude-codecode-generationcodexcoding-agentdeveloper-toolsgemini-clillmmulti-agentopenroutersoftware-engineeringsoftware-factory
Install in seconds
Install SWE AF
Copy SWE AF into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Agent-Field/SWE-AF/tree/main/docs ~/.claude/skills/docs

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Agent-Field/SWE-AF.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
docs/SKILL.md in Agent-Field/SWE-AF
Installs to
~/.claude/skills/docs
Collection
One of 2 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What SWE AF does

SWE AF creates coordinated AI agent teams to plan, code, review, test, and merge software changes. Use it to run autonomous builds from a local path or a GitHub URL, including multi-repo workflows.

SWE AF is cataloged under AI Engineering on DirSkills. SWE AF comes from a repository tagged agent-factory, agentfield, agentic-ai, ai-agents and ai-factory.

Documentation

README

SWE-AF Usage Guide

Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.

What It Does

SWE-AF creates a coordinated team of AI agents (planning, coding, review, QA, merge, verification) that execute in parallel based on DAG dependencies. Issues with no dependencies run simultaneously; dependent issues run sequentially.

Installation

python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Running

Terminal 1 — Control Plane:

af                  # starts AgentField on port 8080

Terminal 2 — Register Node:

python -m swe_af    # registers the swe-planner node

Triggering a Build

This is the opening of the README. Read the full README on GitHub.

Frequently asked about SWE AF

  • What else does Agent-Field publish alongside SWE AF?

    SWE AF is one of 2 skills that DirSkills catalogs from Agent-Field/SWE-AF, the repository it ships in. Its siblings there include Delegate Issue. Each one is a separate skill with its own page in this directory, installs the same way SWE AF does, and is maintained by Agent-Field in that same repository. The rest of the collection is listed on the Agent-Field/SWE-AF page.

  • How does SWE AF compare to other AI Engineering skills?

    SWE AF ranks #1381 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of SWE AF against them. Open each page to compare what they document and how they install.

More from Agent-Field/SWE-AF

SWE AF is one of 2 skills cataloged on DirSkills from Agent-Field/SWE-AF.

See all 2 skills →
🤝
1w ago

Delegate Issue

Delegate Issue sends a fully specified coding issue to a SWE-AF node as a separate branch for implementation. Use it to offload independent tasks, then review and merge the returned branch.
AI Engineering
981167

More AI Engineering skills

SWE AF is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1381 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K