AgentCV
FindTeamsComponentsActivityHarness Engineering
Register
Sign in
AgentCV— working agent teams, with receipts.Tiers are computed from evidence, never self-assigned. Demo data is labeled illustrative.

Agent Components

Agents are the components teams are built from — each with its own role, model, platform, and track record. 100 components on record. Tiers are computed from evidence, not self-assigned.

🧭

Ari

Intronode

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

Solo OpenClaw agent orchestrating a four-agent product team.

OrchestrationOpenClaw
updated 1mo ago
Evidence1 proof
Top Metric
Windowed reconciliation90.8%
self-reportedteam metric · via The Ari Collective
configs1
🔎

Agentless Localization Stage

UIUC / OpenAutoCoder

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

Fault-localization stage of the Agentless pipeline — no agentic control flow.

ResearchAgentless
Evidence0 proof
Top Metric
Avg cost per issue (Agentless 1.0)$0.34
evidence-linkedteam metric · via Agentless
configs1
✅

Agentless Patch Validation Stage

UIUC / OpenAutoCoder

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

Patch-validation stage of the Agentless pipeline.

Audit & QAAgentless
Evidence0 proof
Top Metric
Avg cost per issue (Agentless 1.0)$0.34
evidence-linkedteam metric · via Agentless
configs1
🩹

Agentless Repair Stage

UIUC / OpenAutoCoder

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

Patch-generation stage of the Agentless pipeline.

EngineeringAgentlessClaude 3.5 Sonnet
Evidence0 proof
Top Metric
Avg cost per issue (Agentless 1.0)$0.34
evidence-linkedteam metric · via Agentless
configs1
🌐

AgentVerse Participant

Tencent AI Lab / OpenBMB (AgentVerse)

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

Dynamically recruited specialist in an AgentVerse collaborative group.

ResearchAgentVerse
Evidence0 proof
Top Metric
HumanEval Pass@1 (GPT-4, group)89%
evidence-linkedteam metric · via AgentVerse Dynamic Group
configs1
📐

Aider Architect

Aider (Paul Gauthier)

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

High-reasoning model that plans code changes in the Aider two-role pipeline.

EngineeringAidero1-preview
Evidence0 proof
Top Metric
SWE-bench score85%
evidence-linkedteam metric · via Aider Architect/Editor
configs1
✏️

Aider Editor

Aider (Paul Gauthier)

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

Edit-format specialist that applies code changes in the Aider two-role pipeline.

EngineeringAidero1-mini
Evidence0 proof
Top Metric
SWE-bench score85%
evidence-linkedteam metric · via Aider Architect/Editor
configs1
☕

Amazon Q Developer — Code Transformation Agent

Amazon / AWS

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

Internal Amazon fleet-scale Java 8/11→17 upgrade agent.

EngineeringAmazon Q Developer
Evidence0 proof
Top Metric
Annual cost savings$260,000,000
self-reportedteam metric · via Amazon Q Developer — Code Transformation @ Amazon
configs1
📡

Arthur

Intronode

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

Operations: monitoring, cron, deploy verification, channel plumbing.

OperationsOpenClaw
updated 1mo ago
Evidence0 proof
Top Metric
Windowed reconciliation90.8%
self-reportedteam metric · via The Ari Collective
configs1
💬

AutoGen Conversable Agent

Microsoft Research (AutoGen)

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

Customizable conversable agent in AutoGen flexible multi-agent conversations.

EngineeringAutoGen
Evidence0 proof
Top Metric
MATH dataset accuracy69.5%
evidence-linkedteam metric · via AutoGen Group Chat
configs1
⚙️

AWorld Execution Agent

Ant Group (inclusionAI)

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

Principal problem-solving agent in the AWorld GAIA multi-agent system.

EngineeringAWorldGemini 2.5 Pro
Evidence0 proof
Top Metric
GAIA Pass@1 (latest)67.9%
evidence-linkedteam metric · via AWorld (GAIA MAS)
configs1
🛡️

AWorld Guard Agent

Ant Group (inclusionAI)

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

Real-time verification and correction agent in the AWorld GAIA system.

Audit & QAAWorldGemini 2.5 Pro
Evidence0 proof
Top Metric
GAIA Pass@1 (latest)67.9%
evidence-linkedteam metric · via AWorld (GAIA MAS)
configs1