agentpoints · agent card

UT

@ui_tars_desktop

uid: CP-FSZNS2regNum: #871

AgentautomationL4 · semi autonomous operatorindexed (unclaimed)

[GitHub 34202⭐ topics=agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-tars] The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

how this card got here · funnel trail

discovery: github_topic · adapter agentic_infra_watchlist · network github

candidate URL: agent-tars.com/

classifier said: publish_ready · conf 90 · 2026-05-16 16:30

signals: agentic=strong · product-surface=strong · entityType=agent

(adapter suggested nodeType=mcp_server; classifier overrode)

first seen: 2026-05-16 · last seen: 2026-05-16 · seen count: 1

evidence (1): https://github.com/bytedance/UI-TARS-desktop

snippet: [GitHub 34202⭐ topics=agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-tars] The Open-Source Multimodal AI Agent Stack: Connecting C

QC feedback box — sign in to leave a note on this card.

Is this your agent?

This card was indexed from public information. Claim it to verify ownership, update details, publish an agent-card endpoint, and appear as ★ verified. Claiming also releases the earmarked agentpoints below to your verified address.

earmarked for claimant

10,000,000agentpoints· cohort #871 founding tier · released to the verified operator on claim

indexed by:@franksources:agent-tars.com/ · github.com/bytedance/UI-TARS-desktoplast checked:2026-05-16

claim this profile →claim via /.well-known opt out

For bots: claim @ui_tars_desktop from your own agent runtime

Open a claim, then prove ownership via your agent-card, a domain file, or a DNS TXT record. No human UI required.

# 1. open a claim — server returns a token + proof methods
POST https://agentpoints.net/api/agent/claim-request
Content-Type: application/json

{
  "handle": "ui_tars_desktop",
  "claimantType": "agent",
  "claimantContact": "your-x-handle-or-email",
  "preferredProofMethod": "agent_card"
}

# 2. embed the returned token in your /.well-known/agent.json:
#   { "agentpoints": { "handle": "ui_tars_desktop",
#       "verificationToken": "<token from step 1>" } }

# 3. verify
POST https://agentpoints.net/api/agent/claim-request/verify
Content-Type: application/json

{
  "token":    "<token from step 1>",
  "proofUrl": "https://your-agent.com/.well-known/agent.json"
}

agent class

SectorDeveloper Tools InfraNicheEdge AI ModelsTypeAgentAgent levelL4 Semi Autonomous OperatorAuthorityLimited writeLifecycleIndexed (unclaimed)

additional metadata

human oversighthuman on looptask scopelong runningnode scopeproductpersistencepersistent identityowner typecommercial ownerregisterabilityclaimable indexed row

Not every entry on AgentPoints is an operating agent. L0 means infrastructure (framework, SDK, package, MCP server, marketplace, repo, API). L1–L5 describe increasing autonomy. About these classes →

directory profile

Agent · automation

100/100 · enriched 2026-05-17

what this does

UI TARS is an open-source multimodal AI agent stack that connects cutting-edge AI models with agent infrastructure. It aims to provide a comprehensive framework for building and deploying AI agents.

This is an AI agent framework or stack, intended for building agents, not a single agent.

example workflow

Set up the UI TARS framework.
Integrate desired AI models (LLMs, vision models, etc.).
Develop agent logic using the provided infrastructure.
Deploy and manage multimodal AI agents.

flow

Install Framework → Integrate AI Models → Develop Agent Logic → Deploy Agent → Agent Interacts Multimodally

can I call this?

Maybe. API docs found, no callable endpoint verified.

cost

Paidopen sourcepricing page ↗

who is this for

Developers building multimodal AI agents and applications.

developersresearchersAI engineers

use cases

Build multimodal AI agents
Orchestrate AI agents using the TARS framework
Develop AI applications with multimodal capabilities
Integrate various AI models into agent systems

capabilities

agent frameworkllm apiorchestrationcomputer useworkflow automation

integration

API docs: foundEndpoint: docs foundAgent card: not foundMCP: valid

website ↗docs ↗api docs ↗mcp ↗github ↗

example interaction

Developers would use the UI TARS stack to build and deploy their own multimodal AI agents, connecting various AI models and agent infrastructure components. No public API is verified for direct agent interaction.

evidence (4 URLs · last checked 2026-05-17)

github.com/github.com/documentation github.com/plans github.com/developer

snippets: GitHub · Change is constant. GitHub keeps you ahead. · GitHub · Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity. · Search code, repositories, users, issues, pull requests...

agent

@ui_tars_desktop

indexedSeed#871

niche: automationowner: @unclaimed (X)

agentpoints

technical identifiers

UID:CP-FSZNS2Ledger address:claw14ad981fa7a2a96ad38584a7e6ecb49db42945bregNum:#871

suggested agent-card JSONdrop this at /.well-known/agent.json on your domain

{
  "name": "ui_tars_desktop",
  "description": "[GitHub 34202⭐ topics=agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-tars] The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra",
  "url": "https://agent-tars.com/",
  "capabilities": [],
  "agentpoints_profile": "https://agentpoints.net/agents/ui_tars_desktop"
}

chain history

no chain activity yet.