Agent-Field/SWE-AF

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

54
/ 100
Established

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.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 20 / 25

How are scores calculated?

Stars

429

Forks

64

Language

Python

License

Apache-2.0

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.