AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
SWE-AF
SWE-AF logo

SWE-AF

Active·★ 1.1k·Apache-2.0·Updated 2026-11-12

SWE-AF is an autonomous engineering team runtime built on AgentField that coordinates planning, coding, review and testing. Builds can target one or several repositories, with role-specific models, isolated Git worktrees and checkpoint-based resumption.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
Apache-2.0
Latest release
No GitHub releases
Last commit
2026-11-12
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
Contributors
18
Forks
186
Open issues and PRs
28
First published
2026-02-04

Source: GitHub, npm and PyPI public APIs.

#agent-factory#agent-framework#agentfield#agentic-ai#ai-agents#ai-factory#autonomous-agents#claude-code
↗ Visit site★ GitHub
01

Features

01Starts engineering builds through the af CLI or an asynchronous HTTP API.
02Coordinates primary and dependency repositories in a single build.
03Schedules dependent work with isolated Git worktrees and role-specific models.
04Resumes interrupted builds from checkpoints.
02

Why choose it

+
+
+
+
03

Trade-offs

!
!
!
!
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-12
Commits, last 90 days
93
Releases, last 90 days
0
Latest release
—
Open issues
21
Recent issues with at least one comment
4/21
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 0, 4, 0, 18, 0, 4, 0, 21, 4, 5, 3

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Use cases

↳Implement a feature that spans an application and its shared SDK.
↳Coordinate coding, review and QA for a multi-issue engineering goal.
↳Resume a long-running engineering build after an interruption.
06

Alternatives

⚡Top VS:
VSGenAI_Agents★25.0k→VSmunder-difflin★9.6k→VSagentes-chat★1.7k→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Use cases06Alternatives

Most discussed open issues

  • #163 Run-level wall-clock threshold, and three prompt fixes for test volume and unrequested code1 comments · 2026-10-22
  • #135 furrow: inbound workspaces — push a local directory to a node and build against it1 comments · 2026-08-12
  • #189 run_git_init commits a .gitignore edit onto the feature branch, so every pull request carries it0 comments · 2026-11-12
  • #176 Reasoner timeout defaults (2h) are shorter than a normal feature build (observed 7h27m)0 comments · 2026-11-04
  • #175 Coding loop records a reviewer infrastructure failure as approved=True0 comments · 2026-11-04

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

VS
cezar
★1.1k
→
GenAI_Agents logo
GenAI_Agents★ 25.0k
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
VSCompare→
munder-difflin logo
munder-difflin★ 9.6k
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
VSCompare→
agentes-chat logo
agentes-chat★ 1.7k
Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and browser, routines, memory and approvals. Web, desktop and phone apps. Docker Compose + Postgres. AGPL-3.0.
VSCompare→
cezar logo
cezar★ 1.1k
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
VSCompare→
agentos logo
agentos★ 691
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.
SoduWork logo
SoduWork★ 1.7k
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
oh-my-agent logo
oh-my-agent★ 1.5k
Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.
VSCompare→
agenticos logo
agenticos★ 409
Sovereign Agentic AI Layer: your company's AI agents on your servers, models and rules. Skills, context files, 5700+ MCP servers, budgets, approvals and an audit trail. Apache-2.0, built on Pydantic AI.
VSCompare→
See all alternatives →
Agent-Field /
SWE-AF
↗

Autonomous software engineering factory runtime built on AgentField orchestrating full-lifecycle development teams

1.1k186Apache-2.0
Last commit6d ago
StatusActive
CategoryMulti-Agent
Contributors18
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit