Software delivery teams

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

3 proof

🙌

OpenHands (OpenDevin)

All Hands AI (OpenHands)

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

Solo + Tools1 agentOpenHands

AI Developer

Outcome26%

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

2 proof

🧵

Agentless

UIUC / OpenAutoCoder

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

Pipeline3 agentsAgentless

LocalizationRepair· Claude 3.5 SonnetPatch Validation

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

📐

Aider Architect/Editor

Aider (Paul Gauthier)

Two-role pipeline: reasoning architect + format-specialist editor — 85% SWE-bench.

Architect· o1-previewEditor· o1-mini

Pipeline2 agentsAider

Outcome85%

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

🔀

Anthropic Orchestrator-Workers Pattern

Anthropic

Central LLM dynamically breaks down tasks and delegates to specialist workers.

Orchestrator–Worker2 agentsClaude API

OrchestratorWorker

software-deliveryresearchdata-extraction

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

💬

AutoGen Group Chat

Microsoft Research (AutoGen)

Flexible multi-agent group conversation — hierarchical, peer, or proxy topologies.

updated 3y ago

Supervisor3 agentsAutoGen

ConversableAgent

software-deliveryresearchdata-extraction

Outcome69.5%

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

💬

ChatDev Communicative Pipeline

Academic / Open-Source (ChatDev & MetaGPT)

5-role sequential pipeline — 22,949 tokens, 148s per software task.

updated 3y ago

Pipeline5 agentsChatDev

CEOCTOProgrammerReviewer+1 more

Claude Code Agent Teams (Experimental)

Anthropic

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

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

Teammate ATeammate BTeammate C

Swarm3 agentsClaude Code

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

🔱

Claude Code Sub-agents Pattern

Anthropic

Lead agent spawns specialist subagents in isolated context windows.

Orchestrator–Worker2 agentsClaude Code

LeadSubagent

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

🏆

Claude SWE-Bench Team

Anthropic

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

Solo + Tools1 agentClaude API

Software Engineer· Claude 3.5 Sonnet

Outcome49%

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

🗂️

CodeR

Huawei Cloud + CAS + SMU + PKU (CodeR)

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

updated 2y ago

Supervisor5 agentsCodeR

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

Self-ReportedAll claims are the subject's own. No external evidence is on record yet.Curated

🤖

Factory Droid

Factory AI

#1 on Terminal-Bench Core v0.1.1 (58.75%) — model-agnostic harness.

updated 11mo ago

Solo + Tools1 agentDroid (Factory AI)

Solo Agent