1X NEO Hand: 25 DoF, Tendon Drive and Tactile Sensing
A source-checked guide to 1X NEO hand, covering how it works, verified evidence, comparison methods, failure modes, practical uses and missing data.
Introduction
1X publishes more current mechanical detail for NEO's hand than most home-humanoid companies: 25 degrees of freedom including the wrist, 22 fully actuated finger and palm axes, tendon transmission and tactile and shear sensing. The NEO hand is a compliant, tendon-driven humanoid end-effector enclosed by a soft outer body for domestic use. Its published joint count describes an integrated hand and wrist system. Those specifications do not by themselves establish success across laundry, cookware, doors or other unstructured home tasks. This article explains the mechanisms behind 1X NEO hand, compares documented systems, separates real-robot evidence from claims and identifies the measurements that remain missing. The analysis treats kinematics, sensing, actuation and demonstrated task performance as separate layers. It avoids ranking hands by appearance or joint count alone.
Key findings
- 1X states 25 total DoF including wrist and 22 fully actuated finger and palm DoF.
- Route motors away from the fingers through tendons to reduce distal mass.
- Tendon tension and friction can change with wear.
- Compliant grasping around people, pets and fragile objects.
- Published force and lifecycle figures are manufacturer claims.
1X NEO Hand: 25 DoF, Tendon Drive and Tactile Sensing — evidence comparison
The table records what each source establishes and keeps missing data visible.
| System or method | What the evidence establishes | Evidence class | Main unresolved point |
|---|---|---|---|
| Published kinematics | 1X states 25 total DoF including wrist and 22 fully actuated finger and palm DoF. | Officially documented | Published force and lifecycle figures are manufacturer claims. |
| Published force figures | The company reports 45 N distal finger flexion and 17.75 Nm wrist torque. | Company measurement | Independent reliability, contamination and long-duration household tests are unavailable. |
| Domestic demonstrations | NEO has been shown handling household objects, while the commercial model still includes human expert assistance for unsupported tasks. | Human-in-the-loop product evidence | The share of autonomous versus remotely assisted hand use is task-dependent. |
Definition and design boundary
The NEO hand is a compliant, tendon-driven humanoid end-effector enclosed by a soft outer body for domestic use. Its published joint count describes an integrated hand and wrist system. Those specifications do not by themselves establish success across laundry, cookware, doors or other unstructured home tasks. The scope used here excludes adjacent systems that share vocabulary with 1X NEO hand but do not perform the same function. The boundary prevents a perception model, simulation result, component price, historical prototype or edited demonstration from being presented as evidence for a complete deployed system.
How the hand architecture works
Route motors away from the fingers through tendons to reduce distal mass. Use low transmission ratios and compliant structure to limit impact energy. Estimate contact and shear across the hand skin. Coordinate thumb opposition, palm shaping and wrist pose. Combine autonomous policies with remote expert assistance when a task exceeds current capability. The pipeline remains closed loop: sensing updates the state estimate, the controller selects or constrains an action, the robot executes it and new observations determine whether to continue, correct or stop. Latency, calibration and safety limits can change the result even when the high-level model remains the same.
What public evidence shows
Published kinematics: 1X states 25 total DoF including wrist and 22 fully actuated finger and palm DoF. This is classified as officially documented. The classification records what the source establishes and leaves unstated fields as not publicly disclosed. It should not be extended to different robot versions, sites or tasks without new evidence.
Published force figures: The company reports 45 N distal finger flexion and 17.75 Nm wrist torque. This is classified as company measurement. The classification records what the source establishes and leaves unstated fields as not publicly disclosed. It should not be extended to different robot versions, sites or tasks without new evidence.
Domestic demonstrations: NEO has been shown handling household objects, while the commercial model still includes human expert assistance for unsupported tasks. This is classified as human-in-the-loop product evidence. The classification records what the source establishes and leaves unstated fields as not publicly disclosed. It should not be extended to different robot versions, sites or tasks without new evidence.
How to compare dexterity claims
The analysis treats kinematics, sensing, actuation and demonstrated task performance as separate layers. It avoids ranking hands by appearance or joint count alone. A defensible comparison records the exact system version, task, environment, control mode, trial count and source date. Published numbers are retained only when the source defines what was measured. Missing fields remain marked as not reported rather than estimated.
Failure modes during manipulation
The main failure modes are concrete: Tendon tension and friction can change with wear. A soft cover improves contact safety but can reduce visual access for maintenance. Home objects vary in size, moisture, compliance and placement. Remote assistance introduces privacy, latency and connectivity constraints. A useful evaluation records the state before the failure, the intervention required, the recovery time and whether the same failure repeats after a reset.
Credible applications today
Credible applications include Compliant grasping around people, pets and fragile objects, Household data collection and task execution under supervision and Bimanual manipulation where human-like reach and hand shape help. These applications should be described with the robot, task boundary, operator role and environmental constraints. Experimental capability, commercial availability and routine deployment are reported as separate statuses.
Questions buyers and researchers should ask
A buyer, developer or researcher should ask for the exact hardware and software version, raw trial counts, intervention logs, control frequency, safety limits, maintenance requirements and licensing terms. The answer should identify which results were obtained in simulation, on one physical robot, across several embodiments or in an operational site. A missing answer is itself useful evidence about maturity.
Limitations and missing information
- Published force and lifecycle figures are manufacturer claims.
- Independent reliability, contamination and long-duration household tests are unavailable.
- The share of autonomous versus remotely assisted hand use is task-dependent.
- Specifications, prices, repositories and deployment status can change after publication.
- Benchmarks from different robots or environments are not directly comparable.
Conclusion
The strongest conclusion about 1X NEO hand comes from the evidence boundary, not the most impressive clip. 1X states 25 total DoF including wrist and 22 fully actuated finger and palm DoF. At the same time, published force and lifecycle figures are manufacturer claims. Practical value is clearest in compliant grasping around people, pets and fragile objects, household data collection and task execution under supervision. Deployment or adoption should therefore depend on repeated task results, disclosed intervention, safe fallback behavior and a complete cost or maintenance model. Where sources omit a number, the article leaves it undisclosed rather than converting a claim, target or partial test into a precise fact.
Frequently asked questions
What does 1X NEO hand mean?
The NEO hand is a compliant, tendon-driven humanoid end-effector enclosed by a soft outer body for domestic use. Its published joint count describes an integrated hand and wrist system. Those specifications do not by themselves establish success across laundry, cookware, doors or other unstructured home tasks. The article uses this definition to exclude neighboring technologies or claims that do not meet the same evidence threshold.
How should 1X NEO hand be evaluated?
It is evaluated by recording Route motors away from the fingers through tendons to reduce distal mass, Use low transmission ratios and compliant structure to limit impact energy, Estimate contact and shear across the hand skin. The system version, environment, control mode, trial count, intervention rate and failure recovery must be disclosed before results can be compared.
What real-world evidence is available?
Public evidence includes Published kinematics, where 1x states 25 total dof including wrist and 22 fully actuated finger and palm dof. It also includes Published force figures, where the company reports 45 n distal finger flexion and 17.75 nm wrist torque. Each result remains limited to the published robot, task and conditions.
What information is still missing?
The largest limitations are published force and lifecycle figures are manufacturer claims, independent reliability, contamination and long-duration household tests are unavailable, the share of autonomous versus remotely assisted hand use is task-dependent. These gaps prevent a precise universal ranking and can change the engineering or commercial conclusion for a specific robot, country, task or workplace.
Is the technology ready for practical use?
Current credible uses include compliant grasping around people, pets and fragile objects, household data collection and task execution under supervision, bimanual manipulation where human-like reach and hand shape help. Readiness depends on repeated real-world performance, safety controls, human intervention, maintenance and cost. A single successful demonstration is insufficient evidence of routine deployment.
Sources and methodology
The analysis treats kinematics, sensing, actuation and demonstrated task performance as separate layers. It avoids ranking hands by appearance or joint count alone.
Sources were checked on July 11, 2026. Official product pages, research papers, repositories, standards and customer documents were prioritized. Company metrics remain labeled as company-reported unless an independent source establishes the same result.
- NEO hands — 1X Technologies · July 9, 2026
- NEO product page — 1X Technologies · accessed July 11, 2026
- NEO Factory — 1X Technologies · accessed July 11, 2026
- Introducing Figure 03 — Figure AI · October 9, 2025
- Unitree Dex3-1 — Unitree Robotics · Accessed July 11, 2026
- Shadow Dexterous Hand series — Shadow Robot Company · Accessed July 11, 2026
Related TechniaHQ guides
Official image recommendations
- Official visual directly related to 1X NEO Hand: 25 DoF, Tendon Drive and Tactile Sensing.
1X NEO Hand: 25 DoF, Tendon Drive and Tactile Sensing shown in the official project context — 1X Technologies - Second official system or method used in the 1X NEO hand comparison.
Documented example used to compare 1X NEO hand — 1X Technologies - TechniaHQ evidence matrix for 1X NEO hand.
Table comparing evidence, limits and status for 1X NEO hand — TechniaHQ original visualization using cited primary sources - Evidence maturity chart separating claims, simulation, real-robot tests and deployment.
Evidence maturity chart for 1X NEO hand — TechniaHQ original chart using cited primary sources - Inputs, processing, control or decision stages and outputs for 1X NEO hand.
Simplified technical architecture of 1X NEO hand — TechniaHQ original architecture based on cited documentation
Fact-check report
Verified: July 11, 2026
Confirmed
- 1X states 25 total DoF including wrist and 22 fully actuated finger and palm DoF.
- The company reports 45 N distal finger flexion and 17.75 Nm wrist torque.
Not confirmed or incomplete
- Published force and lifecycle figures are manufacturer claims.
- Independent reliability, contamination and long-duration household tests are unavailable.
- The share of autonomous versus remotely assisted hand use is task-dependent.
Fast-changing information
- Commercial availability, prices, model versions and software access.
- Deployment counts, company partnerships and repository maintenance status.