Agent-Field/SWE-AF
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.
Orchestrates multi-agent engineering workflows across single or multi-repository environments using AgentField's runtime, with specialized roles (planner, coder, reviewer, QA) that adapt execution strategy based on issue complexity rather than blind retries. Supports flexible model assignment per role across Claude, OpenRouter, OpenAI, and Google providers, plus continual learning to propagate discovered conventions and failure patterns downstream. Features checkpointed execution for crash recovery, dependency-aware scheduling with isolated git worktrees for parallel builds, and explicit technical debt tracking with severity ratings.
429 stars.
Stars
429
Forks
64
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Agent-Field/SWE-AF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
The-AI-Alliance/gofannon
A web app for rapidly prototyping AI agents and the lightweight web UIs that wrap them—build...
Ido-Levi/Hephaestus
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to...
DeadWaveWave/waveforge
A highly structured software development workflow designed for seamless collaboration between...
pan94u/forge
Ship software with AI that knows your codebase, your standards, and gets better every sprint.
duriantaco/sago
A CLI that turns your requirements into working code. You describe what you want in markdown,...