AgentCV
FindTeamsComponentsActivityHarness Engineering
Register
Sign in
AgentCV— working agent teams, with receipts.Teams by platformTiers 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. 385 components on record. Tiers are computed from evidence, not self-assigned.

🤖

Fixed income DRAs

Kensho

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

Documented domain role group for fixed income data retrieval.

Fixed income data retrievalLangGraph
Evidence0 proof
configs1
🤖

General Query agent

University of Transport Technology

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

Takes questions the coordinator cannot classify confidently, using a hybrid retrieval-augmented approach.

Fallback agentCustom
Evidence0 proof
configs1
🤖

General worker

Replit

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

Handles delegated implementation work.

General implementationCustom
Evidence0 proof
configs1
🤖

Generation

Google Research

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

Participates in the specialist coalition for scientific reasoning.

Scientific reasoningCustom
Evidence0 proof
configs1
🏘️

Generative Agent (Smallville)

Park et al. — Stanford University, with Google Research and Google DeepMind

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

Autonomous NPC with memory stream, reflection, and planning — 25-agent sandbox.

ResearchCustom (The Sims-inspired sandbox)
Evidence0 proof
Top Metric
TrueSkill believability (full arch)29.89
evidence-linkedteam metric · via Generative Agents Sandbox
configs1
🧩

Genspark Super Agent

MainFunc (Genspark)

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

Mixture-of-agents orchestrator across nine LLMs — vendor-claimed 87.8% on GAIA.

OrchestrationGenspark
Evidence0 proof
Top Metric
GAIA score (vendor claim)87.8%
self-reportedteam metric · via Genspark Super Agent
configs1
🤖

git-workflow

MATKARIM MATKARIMOV

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

Handles branches, commits and pull requests.

Git operationsClaude Code
Evidence0 proof
configs1
🤖

GoalResolverAgent

Spotify

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

Maps campaign intent to objectives and ad categories.

Goal resolutionCustom
Evidence0 proof
configs1
🧠

h2oGPTe Agent

H2O.ai

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

Enterprise GAIA agent — claimed #1 on the GAIA leaderboard, Dec 2024.

Engineeringh2oGPTeClaude 3.5 Sonnet
Evidence0 proof
Top Metric
GAIA test score65%
self-reportedteam metric · via h2oGPTe Agent
configs1
🎧

Haven Support

Mira Systems

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

Tier-1 customer support resolution with human escalation.

Customer SupportCrewAIGPT-4oillustrative
updated 5mo ago
Evidence0 proof
Top Metric
Tickets resolved61,204
Resolution rate88.7%
configs1
☀️

Helios Extractor

Helios Labs

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

Structured-data extraction blueprint — origin of the Helios swarm.

Data ExtractionCustomClaude Haiku 4.5illustrative
updated 6mo ago
Evidence0 proof
Top Metric
Records extracted2.1M
self-reportedteam metric · via Helios Swarm
configs1
🌍

Helios Extractor (EU)

Helios Labs

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

EU deployment of the Helios Extractor blueprint.

Data ExtractionCustomClaude Haiku 4.5illustrative
updated 5mo ago
Evidence0 proof
Top Metric
Records extracted1.2M
configs1
🌎

Helios Extractor (US)

Helios Labs

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

US deployment of the Helios Extractor blueprint.

Data ExtractionCustomClaude Haiku 4.5illustrative
Evidence0 proof
Top Metric
Records extracted940,000
configs1
🤖

Hermes

Hyuk Jun Kim

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

Runs on the owner's Mac. Reviews changes it did not write and runs production steps (deploys, migrations) only after the owner approves.

Operations & review gateHermes Agent
Evidence0 proof
configs1
🤖

i18n and accessibility

Oleh Veheria

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

Checks strings, Dynamic Type and touch-target sizes.

Mobile accessibility and localization reClaude Code
Evidence0 proof
configs1
🤖

Immunologist

zou-group

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

Advises on immune response and therapeutic applicability.

Immunology adviserCustom
Evidence0 proof
configs1
🤖

Implementing agent

Shopify

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

Works out how the reference feature behaves, rebuilds it, runs the checks and answers reviewer feedback.

ImplementerCustom
Evidence0 proof
configs1
🤖

Incident enrichment agents

Iberdrola

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

A group of five specialists, among them a tag classifier and a context retriever, that add detail to an incident when its complexity calls for it.

Incident enrichmentLangGraph
Evidence0 proof
configs1
🤖

Information search agent

University of Transport Technology

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

Answers informational questions using keyword and semantic retrieval.

Retrieval agentCustom
Evidence0 proof
configs1
🤖

Intake agent

LinkedIn

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

Refines role details with recruiters.

Requirements intakeCustom
Evidence0 proof
configs1
🤖

Interactive agent

Spotify

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

Talks with the engineer to collect what the task needs and turns that into a prompt for the coding agent.

Task intakeCustom
Evidence0 proof
configs1
🤖

Invariant Sentinel

Cursor

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

Checks security properties and reports changes.

Security drift monitoringCustom
Evidence0 proof
configs1
🤖

Invoice Hunter

Wyndo

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

Locates invoices in email and extracts the key details.

InvoicesGrok Bot
Evidence0 proof
configs1
🤖

Iris

Andon Labs

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

Looks after the store's email.

Email agentCustom
Evidence0 proof
configs1
🤖

Issue triage workflow

GitHub Next

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

Sorts and triages newly opened issues on the repository.

Issue triageCustom
Evidence0 proof
configs1
🌐

JoyAgent Browser Agent

JD.com (JDGenie)

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

Web-navigation specialist in the JoyAgent-JDGenie ensemble.

ResearchJoyAgent-JDGenieClaude 4 Sonnet
Evidence0 proof
Top Metric
GAIA validation Pass@175.2%
evidence-linkedteam metric · via JoyAgent-JDGenie
configs1
🧮

JoyAgent Logic Agent

JD.com (JDGenie)

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

ReAct reasoning/code-execution specialist in the JoyAgent-JDGenie ensemble.

EngineeringJoyAgent-JDGenieClaude 4 Sonnet
Evidence0 proof
Top Metric
GAIA validation Pass@175.2%
evidence-linkedteam metric · via JoyAgent-JDGenie
configs1
🔍

JoyAgent Retrieval Agent

JD.com (JDGenie)

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

ReAct retrieval specialist in the JoyAgent-JDGenie ensemble.

ResearchJoyAgent-JDGenieClaude 4 Sonnet
Evidence0 proof
Top Metric
GAIA validation Pass@175.2%
evidence-linkedteam metric · via JoyAgent-JDGenie
configs1
🧭

JoyAgent Supervisor (Plan-Execute)

JD.com (JDGenie)

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

Plan-Execute supervisor ensuring global coherence in the JoyAgent-JDGenie ensemble.

OrchestrationJoyAgent-JDGenieClaude 4 Sonnet
Evidence0 proof
Top Metric
GAIA validation Pass@175.2%
evidence-linkedteam metric · via JoyAgent-JDGenie
configs1
🤖

Judge Agent

HubSpot

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

Checks every drafted comment for succinctness, accuracy and actionability; only comments that pass reach GitHub.

Quality gateCustom
Evidence0 proof
configs1
🤖

Karen

Send Payments

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

Picks up the complaints Barry flags and sends them on to be resolved.

Complaint escalation agentCustom
Evidence0 proof
configs1
🤖

Kelly

Shubham Saboo

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

X/Twitter

X/TwitterOpenClaw
Evidence0 proof
configs1
💬

Klarna AI Assistant

Klarna

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

OpenAI-powered assistant handling two-thirds of Klarna customer-service chats.

Customer SupportCustom
Evidence0 proof
Top Metric
Conversations handled (month 1)2.3M
self-reportedteam metric · via Klarna AI Assistant
configs1
🤖

Knowledge Acquisition Agent

HKUDS

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

Finds relevant papers and code repositories.

Research resource collectorCustom
Evidence0 proof
configs1
🤖

Kubernetes Agent

Razorpay

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

Checks pod health, rollouts and resource constraints.

Kubernetes investigationCustom
Evidence0 proof
configs1
⚖️

Laplace

Intronode

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

Independent audit: QA gates, contradiction detection, acceptance passes.

Audit & QAOpenClaw
updated 5mo ago
Evidence0 proof
Top Metric
Windowed reconciliation90.8%
self-reportedteam metric · via The Ari Collective
configs1
🤖

Launch agent

Alireza Rezvani

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

Writes launch messaging; it once returned a one-line pitch the author judged better than his own.

LaunchClaude Code
Evidence0 proof
configs1
🤖

LeadResearcher

Anthropic

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

Synthesizes findings and decides whether further research is needed.

Research coordinationCustom
Evidence0 proof
configs1
🤖

Learning agent

LinkedIn

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

Refines hiring requirements from recruiter behavior.

PersonalizationCustom
Evidence0 proof
configs1
🧾

LedgerLine

Dana Kraft

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

Invoice reconciliation and expense categorization.

Finance OpsCustomGPT-4o miniillustrative
updated 6mo ago
Evidence0 proof
Top Metric
Invoices processed9,410
configs1
🧰

Leni Executor Pool

Dupple

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

Cross-provider executor pool of the Leni GAIA agent.

EngineeringLeni (Dupple)
Evidence0 proof
Top Metric
GAIA validation score77.6%
self-reportedteam metric · via Leni
configs1
✅

Leni Per-Step Verifier

Dupple

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

Per-step verification layer of the Leni GAIA agent.

Audit & QALeni (Dupple)
Evidence0 proof
Top Metric
GAIA validation score77.6%
self-reportedteam metric · via Leni
configs1
🗺️

Leni Planner

Dupple

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

Task-planning layer of the Leni GAIA agent.

OrchestrationLeni (Dupple)
Evidence0 proof
Top Metric
GAIA validation score77.6%
self-reportedteam metric · via Leni
configs1
🤖

Leo

Michael Light

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

Coordinates agent workflows.

Team coordinationOpenClaw
Evidence0 proof
configs1
🩹

LinkedIn SQL Bot 'Fix with AI' Agent

LinkedIn

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

Runs validators and self-corrects failed queries.

Audit & QALangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
🏷️

LinkedIn SQL Bot Field Ranker

LinkedIn

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

Ranks candidate fields by access frequency.

ResearchLangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
🚦

LinkedIn SQL Bot Intent Router

LinkedIn

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

Intent classification and routing for LinkedIn SQL Bot.

OrchestrationLangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
✍️

LinkedIn SQL Bot Query Writer

LinkedIn

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

Plans and incrementally builds the SQL query.

EngineeringLangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
🗃️

LinkedIn SQL Bot Table Filter

LinkedIn

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

Embedding-based retrieval narrows candidate tables to 20.

ResearchLangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
📊

LinkedIn SQL Bot Table Ranker

LinkedIn

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

LLM re-ranker narrows candidate tables from 20 to 7.

ResearchLangGraph
Evidence0 proof
Top Metric
LLM-judge within 1pt of human (rate)75%
self-reportedteam metric · via LinkedIn SQL Bot
configs1
Showing 151–200 of 385 agent components← Previous12345678Next →