AgiBot (AGIBOT Innovation (Shanghai) Technology Co., Ltd., known in Chinese as Zhiyuan Robotics / 智元机器人) is a Shanghai-based embodied-intelligence company founded in 2023 that designs and mass-produces humanoid and wheeled service robots — the Expedition A2/A3 full-size humanoids, the X1/X2 open-source bipeds, the Genie G1/G2 and D1 series, the C5, and the OmniHand dexterous hands. Its developer surface is not a public web API but a robotics contract stack: AimRT, an in-house C++20 runtime and middleware compatible with ROS 2, gRPC, HTTP, MQTT, Zenoh and Iceoryx; Link-U OS, an open-source embodied operating system; and the AimDK protocol, a first-party Protocol Buffers definition of the robot itself — hardware abstraction (hands, arms, audio, lights, neck, battery management, cameras, temperature, emergency stop), motion control, kinematics, force control, teleoperation and a health-and-diagnostics service. AgiBot also publishes the AgiBot World dataset, the Genie Sim simulation platform, and runs an online store that implements the Universal Commerce Protocol with a live hosted MCP endpoint for agent-driven purchasing.
AgiBot is listed with 3 APIs on the APIs.io network. Tagged areas include Company, Robotics, Humanoid Robots, Embodied AI, and Artificial Intelligence.
AgiBot’s developer surface includes documentation, API reference, getting-started guide, engineering blog, support, pricing, authentication, and 28 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for
this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero:
never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and
several others — scorable at all.
The six quality facets above are damped to 85 points between them,
because the conditional facet above carries the other
15. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 85% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/agibot/"><img src="https://apis.io/badge/agibot/card.svg" alt="AgiBot on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card+8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
The AimDK protocol is AgiBot's first-party Protocol Buffers definition of its robots' interfaces, published as the aimrt_protocol repository of Link-U OS. It defines 33 gRPC ser...
AimDK_X2 is the published secondary-development SDK for the AgiBot X2 humanoid. It exposes the robot to Python and C++ programs through five documented interface modules — a con...
The AGIBOT online store implements the Universal Commerce Protocol (UCP) for agent-driven commerce and exposes a live, anonymous, hosted Model Context Protocol endpoint. A JSON-...
aid: agibot
name: AgiBot
description: 'AgiBot (AGIBOT Innovation (Shanghai) Technology Co., Ltd., known in Chinese as Zhiyuan Robotics / 智元机器人) is
a Shanghai-based embodied-intelligence company founded in 2023 that designs and mass-produces humanoid and wheeled service
robots — the Expedition A2/A3 full-size humanoids, the X1/X2 open-source bipeds, the Genie G1/G2 and D1 series, the C5,
and the OmniHand dexterous hands. Its developer surface is not a public web API but a robotics contract stack: AimRT, an
in-house C++20 runtime and middleware compatible with ROS 2, gRPC, HTTP, MQTT, Zenoh and Iceoryx; Link-U OS, an open-source
embodied operating system; and the AimDK protocol, a first-party Protocol Buffers definition of the robot itself — hardware
abstraction (hands, arms, audio, lights, neck, battery management, cameras, temperature, emergency stop), motion control,
kinematics, force control, teleoperation and a health-and-diagnostics service. AgiBot also publishes the AgiBot World dataset,
the Genie Sim simulation platform, and runs an online store that implements the Universal Commerce Protocol with a live
hosted MCP endpoint for agent-driven purchasing.'
url: https://raw.githubusercontent.com/api-evangelist/agibot/refs/heads/main/apis.yml
deliveryModel:
model: saas
license_evidence:
not_product:
- link-u-os/aimrt_protocol
open_source: unknown
commercial: true
callable_host: false
label: Hosted service · you call their endpoint
confidence: low
source:
- pricing
- repository-not-product
generated: '2026-09-25'
method: derived
accessModel:
pricing: paid
onboarding: open
trial: false
try_now: false
public: true
gated: none
gated_source:
- onboarding
label: Paid · Open access
confidence: high
source:
- plans
- authentication
- scopes
- rate-limits
- security
- sandbox
generated: '2026-11-06'
method: derived
image: https://www.agibot.com/favicon.ico
x-type: company
x-source: harvest:secondary-market
x-tier: profiled
x-tier-reason: enrichment-pipeline
specificationVersion: '0.23'
created: '2026-08-06'
modified: '2026-08-06'
tags:
- Company
- Robotics
- Humanoid Robots
- Embodied AI
- Artificial Intelligence
- Manufacturing
- Hardware
- Middleware
- ROS 2
- gRPC
- Protocol Buffers
- Simulation
- Machine Learning
- Open Source
- MCP
- Agentic Commerce
- China
tags_raw:
- Company
- Robotics
- Humanoid Robots
- Embodied AI
- Artificial Intelligence
- Manufacturing
- Hardware
- Middleware
- ROS 2
- gRPC
- Protocol Buffers
- Simulation
- Machine Learning
- Open Source
- Model Context Protocol
- Agentic Commerce
- China
- Machine-Learning
- Open-Source
apis:
- aid: agibot:aimdk-protocol
name: AimDK Protocol (Link-U OS Robot Interface)
description: 'The AimDK protocol is AgiBot''s first-party Protocol Buffers definition of its robots'' interfaces, published
as the aimrt_protocol repository of Link-U OS. It defines 33 gRPC services and 175 RPCs across four domains: hal/ (hardware
abstraction — hands and grippers including the OmniHand O10 and AgiClaw, arms, audio, RGB/fill/strip lighting, neck, battery
management, temperature, emergency stop, operation mode, RealSense cameras, camera intrinsics and snapshots, MCU fault
clearing), mc/ (motion control — locomotion, walking and standing, joint and servo control, forward and inverse kinematics,
force primitives, collision and safety, action sequences, planning, simulation and teleoperation from AimMaster, Quest
Pro controllers and universal gamepads), hds/ (health and diagnostics — alerts with levels and solutions, module exceptions,
process heartbeat and health, system status, fallback), and common/ (SE(2)/SE(3) poses, velocities, accelerations and
trajectories, quaternions, RPY, twists, wrenches, joints, odometry, images, timestamps and the shared RPC request/response
headers). The same repository also ships 14 ROS 2 .msg and 19 .srv definitions, so the contract is consumable both as
native protobuf/gRPC and as ROS 2 interfaces. Endpoints are served by the robot itself over the AimRT runtime on the local
network; there is no public cloud host.'
humanURL: https://github.com/Link-U-OS/aimrt_protocol
x-endpoint-pattern: on-robot / LAN — AimRT serves the AimDK services from the robot over its configured RPC backend (gRPC,
HTTP, ROS 2, Zenoh, Iceoryx or shared memory); no public internet base URL is published.
tags:
- Robotics
- gRPC
- Protocol Buffers
- ROS 2
- Motion Control
- Hardware Abstraction
- Diagnostics
properties:
- type: Protobuf
url: grpc/aimdk/protocol/mc/mc_service.proto
- type: SourceCode
url: https://github.com/Link-U-OS/aimrt_protocol
- type: Documentation
url: https://github.com/Link-U-OS/aimrt_protocol/blob/main/document/en/index.md
- type: GettingStarted
url: https://github.com/Link-U-OS/Link-U-OS/blob/main/document/cn/index.md
- aid: agibot:aimdk-x2
name: AimDK_X2 SDK
description: AimDK_X2 is the published secondary-development SDK for the AgiBot X2 humanoid. It exposes the robot to Python
and C++ programs through five documented interface modules — a control module (motion modes, locomotion, joint control,
end effectors and preset motions), an interaction module (voice, screen and LED control), a hardware abstraction layer
(LiDAR, RGB-D, IMU and touch sensors), a perception module (SLAM and vision) and a system-management module (developer
mode and power management) — and ships more than 30 runnable example programs per language covering motion, gripper operation,
sensor reads, audio/video and SLAM. It is built on ROS 2 and documented with an interface reference, an SDK data-structures
reference and an SDK state-transition reference.
humanURL: https://x2-aimdk.agibot.com/en/latest/index.html
x-endpoint-pattern: on-robot / LAN — the SDK connects to the X2 over the network connection described in the documentation
prerequisites; no public internet base URL is published.
tags:
- Robotics
- SDK
- Python
- C++
- ROS 2
- SLAM
- Motion Control
properties:
- type: Documentation
url: https://x2-aimdk.agibot.com/en/latest/index.html
- type: APIReference
url: https://x2-aimdk.agibot.com/en/latest/Interface/index.html
- type: GettingStarted
url: https://x2-aimdk.agibot.com/en/latest/quick_start/index.html
- type: Examples
url: https://x2-aimdk.agibot.com/en/latest/example/Python.html
- type: SDKs
url: packages/agibot-packages.yml
- aid: agibot:store-commerce
name: AGIBOT Store Agent Commerce API (UCP / MCP)
description: 'The AGIBOT online store implements the Universal Commerce Protocol (UCP) for agent-driven commerce and exposes
a live, anonymous, hosted Model Context Protocol endpoint. A JSON-RPC 2.0 tools/list call returns 13 real tools with full
JSON Schema inputs: search_catalog, lookup_catalog and get_product for discovery; create_cart, get_cart, update_cart and
cancel_cart for cart state; create_checkout, get_checkout, update_checkout, complete_checkout and cancel_checkout for
purchase; and get_order for order status. A UCP merchant profile at /.well-known/ucp declares the supported protocol versions,
the shopping service endpoints, the checkout, cart, fulfillment, discount, order and catalog capabilities, and the Google
Pay and Shopify card payment handlers. Customer-scoped calls authenticate through an OAuth 2.0 / OpenID Connect authorization
server with PKCE. The store publishes both /llms.txt and /agents.md describing the agent contract, and requires contemporaneous
human approval before any payment is completed.'
humanURL: https://store.agibot.com/
baseURL: https://store.agibot.com/api/ucp/mcp
tags:
- Commerce
- MCP
- Universal Commerce Protocol
- Agentic Commerce
- OAuth
- OpenID Connect
- Robotics
- Authentication
tags_raw:
- Commerce
- Model Context Protocol
- Universal Commerce Protocol
- Agentic Commerce
- OAuth
- OpenID Connect
- Robotics
- Authentication
properties:
- type: MCPServer
url: mcp/agibot-mcp.yml
- type: LLMsTxt
url: llms/agibot-llms.txt
- type: WellKnown
url: well-known/agibot-well-known.yml
- type: Authentication
url: authentication/agibot-authentication.yml
- type: OAuthScopes
url: scopes/agibot-scopes.yml
- type: Documentation
url: https://store.agibot.com/llms.txt
- type: TermsOfService
url: https://store.agibot.com/policies/terms-of-service
- type: PrivacyPolicy
url: https://store.agibot.com/policies/privacy-policy
x-surface: platform-generated
x-platform: shopify
x-platform-surface: ucp
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
- FN: APIs.json
email: info@apis.io
common:
- type: Plans
url: plans/agibot-plans-pricing.yml
- type: IssueTracker
url: https://github.com/Link-U-OS/aimrt_protocol/issues
- type: DomainSecurity
url: security/agibot-domain-security.yml
- type: Website
url: https://www.agibot.com/
- type: DeveloperPortal
url: https://www.agibot.com/DOCS/OS
- type: Documentation
url: https://www.agibot.com/filepage/282.html
- type: APIReference
url: https://x2-aimdk.agibot.com/en/latest/Interface/index.html
- type: GettingStarted
url: https://x2-aimdk.agibot.com/en/latest/quick_start/index.html
- type: GitHubOrganization
url: https://github.com/AgibotTech
- type: Blog
url: https://www.agibot.com/news
- type: Support
url: https://www.agibot.com/Contact/Business
- type: Pricing
url: https://store.agibot.com/collections/all
- type: Login
url: https://store-account.agibot.com/authentication/oauth/authorize
- type: TermsOfService
url: https://store.agibot.com/policies/terms-of-service
- type: PrivacyPolicy
url: https://www.agibot.com/AGIBOT%20Website%20Privacy%20Policy.pdf
- type: Protobuf
url: grpc/agibot-aimdk-protocol-index.yml
- type: Packages
url: packages/agibot-packages.yml
- type: SDKs
url: packages/agibot-packages.yml
- type: MCPServer
url: mcp/agibot-mcp.yml
- type: LLMsTxt
url: llms/agibot-llms.txt
- type: WellKnown
url: well-known/agibot-well-known.yml
- type: Authentication
url: authentication/agibot-authentication.yml
- type: OAuthScopes
url: scopes/agibot-scopes.yml
- type: Conformance
url: conformance/agibot-conformance.yml
- type: ErrorCatalog
url: errors/agibot-problem-types.yml
- type: Conventions
url: conventions/agibot-conventions.yml
- type: Lifecycle
url: lifecycle/agibot-lifecycle.yml
- type: Deprecation
url: lifecycle/agibot-lifecycle.yml
- type: ChangeLog
url: changelog/agibot-changelog.yml
- type: VulnerabilityDisclosure
url: security/agibot-vulnerability-disclosure.yml
- type: Security
url: security/agibot-vulnerability-disclosure.yml
- type: RateLimits
url: rate-limits/agibot-rate-limits.yml
- type: Sandbox
url: sandbox/agibot-sandbox.yml
- type: CLI
url: cli/agibot-cli.yml
- type: AgentSkill
url: skills/_index.yml
x-enrichment:
date: '2026-08-06'
status: enriched
artifacts_added: 26
pass: local-v1
AgiBot API — frequently asked questions
Does AgiBot have an API?
Yes. APIs.io lists 3 APIs from AgiBot, including AimDK Protocol (Link-U OS Robot Interface), AimDK_X2 SDK and AGIBOT Store Agent Commerce API (UCP / MCP).
How do I authenticate with the AgiBot API?
AgiBot documents its authentication (0 schemes). The details are profiled on APIs.io as Agibot Authentication.
How much does the AgiBot API cost?
AgiBot publishes its prices; its AGIBOT A2 Lite plan is Sale price $44,560.00 USD as of 2026-10-07. APIs.io lists 7 pricing plans for AgiBot, with each plan's price, limits and inclusions under Pricing on this page.
Does AgiBot have an MCP server?
Yes. APIs.io lists 1 MCP server for AgiBot: Remote MCP server at store.agibot.com over HTTP; 13 tools listed.
Is the AgiBot API ready for AI agents?
AgiBot has a Kin Score of 55.0 out of 100 (strong) and an Agent Readiness score of 35.8 (agent-ready), scored by API Evangelist on 2026-11-06.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: