← All use cases

Use case

AI agent teams for bug fixing and issue resolution

Teams whose listed work includes fixing bugs, debugging or resolving reported issues.

13

teams on record

0

real

13

curated

0

illustrative

live from the registry

2 operated · 11 reference designs

A team is listed when its task kinds include bug-fixing, github-issue-resolution or distributed-debugging.

Teams

Operated teams first (real, then curated), then reference designs, then illustrative demos. Every card is labeled.

Next.js Maintainer Agent

Next.js

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

Independent agents the Next.js maintainers use to research, reproduce, verify and fix GitHub issues; they helped cut the backlog by 1,462 closed issues in about three weeks.

updated 2mo ago

Orchestrator–Worker7 listed membersCustom

Issue research agent· GPT-5.6 LunaReproduction agentVerification agentEnd-to-end test agent+3 more

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

Rob Hunter's Coder and PM Agent Pair

Rob Hunter

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.Curated

A product-manager agent and a coder agent, built from the author's own Bobbo agent code, that take turns running his MCP deals server.

updated 7mo ago

Other2 listed membersCustom

EngineerProduct manager

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind github-issue-resolution

MAGIS

co-evolve-lab

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 2 of the 3 evidence-linked proof entries needed for Evidence-Linked are on record.CuratedReference design

Agents coordinating repository changes for software evolution.

updated 19d ago

Orchestrator–Worker4 listed membersCustom

Process coordinatorRepository navigatorCode implementerCode reviewer

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

OpenHands (OpenDevin)

All Hands AI (OpenHands)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 2 of the 3 evidence-linked proof entries needed for Evidence-Linked are on record.CuratedReference design

Open-source AI software developer with sandboxed runtime — ICLR 2025.

Solo + Tools1 agentOpenHands

software-delivery

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

Agentless

OpenAutoCoder

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Non-agentic 3-stage pipeline — 40.7% Lite / 50.8% Verified with Claude 3.5 Sonnet.

Pipeline3 listed membersAgentless

LocalizationRepair· Claude 3.5 SonnetPatch Validation

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind github-issue-resolution

Aider Architect/Editor

Aider (Paul Gauthier)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Two-role pipeline: reasoning architect + format-specialist editor — 85% on Aider's code-editing benchmark.

Pipeline2 agentsAider

Architect· o1-previewEditor· o1-mini

software-delivery

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

Claude Code Agent Teams (Experimental)

Anthropic

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Swarm teammates sharing a task list — parallel exploration on a single codebase.

Swarm3 listed membersClaude Code

Teammate ATeam leadTeammate (from a subagent definition)

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind distributed-debugging

Claude SWE-Bench Team

Anthropic

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Single-agent software engineer achieving 49% on SWE-bench Verified.

Solo + Tools1 agentClaude API

Software Engineer· Claude 3.5 Sonnet

software-delivery

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

CodeR

Huawei Cloud + CAS + SMU + PKU (CodeR)

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

5-agent supervised pipeline — 28.33% SWE-bench Lite, $3.09/issue.

Supervisor5 agentsCodeR

Manager· GPT-4-preview-1106Reproducer· GPT-4-preview-1106Fault Localizer· GPT-4-preview-1106Editor· GPT-4-preview-1106+1 more

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind github-issue-resolution

MarsCode Agent

ByteDance SE Lab

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

39.33% on SWE-bench Lite (lab-page claim).

Pipeline5 agentsMarsCode Agent

PlannerReproducerFault LocalizerPatch Generator+1 more

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind github-issue-resolution

mini-SWE-agent

Princeton NLP / SWE-bench authors

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Minimal bash-only agent — reference floor on SWE-bench Verified.

Solo + Tools1 agentmini-SWE-agent

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind github-issue-resolution

Refact.ai Agent

Refact.ai

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Solo agent, multi-model orchestration — 70.4% on SWE-bench Verified.

Solo + Tools1 agentRefact.ai

Solo Agent· Claude 3.7 Sonnet (multi-model orchestration)

software-delivery

Outcome[unknown]

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

SWE-agent (Princeton ACI)

Princeton NLP / SWE-bench authors

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported. 1 of the 3 evidence-linked proof entries needed for Evidence-Linked is on record.CuratedReference design

Solo software agent with custom ACI — 12.5% SWE-bench, 87.7% HumanEvalFix.

Solo + Tools1 agentCustom ACI (Docker)

Software Engineer

software-delivery

Economics[unknown] · deliberate

Listed for: task kind bug-fixing

Roles seen in these teams

Editor×2
Fault Localizer×2
Reproducer×2
Software Engineer×2
Solo Agent×2
AI Developer×1
Architect×1
Code implementer×1

From 36 listed members of the 13 real and curated teams above. Illustrative demo teams are not counted.