Open Source RoboticsRobots, software & learning

Intrinsic Core

Software

Local robotics runtime, SDK and real-time control framework with a documented machine-tending simulation route. [1]

Installation & first result →Official websiteGetting started

For
Robotics developers evaluating local industrial manipulation software [1]
Hardware
Documented lab_bb_01: UR3e / CAW enclosure without CNC or vise [5] [6] [7]
Source rights
Named licenses are documented by part. Review licenses
Unknowns
operating system not fully established. Review gaps

Source researched · Not tested by us
Sources checked · Research details

Licenses & related hardware
Ecosystem
ROS 2, Gazebo

Requirements · Research details and dates

On this page

Overview

Intrinsic Core combines a local runtime, development interfaces and real-time robot control. Its release 20261012.0 provides the foundation for OMTS, a separate machine-tending application. Start with that documented simulation route if you want to evaluate the stack before connecting industrial hardware. [1] [3] [10]

Is this for you?

Workflows
  • Deploy the OMTS scene in simulation
  • Inspect belief-world state in RViz or physics state in Gazebo
  • Configure and run the OMTS behavior tree after scene and pose-estimator setup

[3] [4] [5]

Known limitations
  • No installation or robot execution reproduced by this publication
  • ARM hosts are unsupported in the pinned guide
  • Perception requires dedicated NVIDIA compute and separately licensed model weights
  • A configured software cell does not establish a complete physical-cell BOM, delivered cost or commissioning result

Combination of explicit upstream requirements and stated limits of this source review.

[3] [5] · Editorial assessment

What you need

Dependencies
  • Git LFS
  • GitHub CLI
  • k3s/containerd
  • Bazelisk / Bazel 8.8.1
  • ROS 2 Lyrical for the documented RViz route

[3] [4] [9]

Host computer

x86-64 host; Intel required by the guide for real-time hardware control, AMD permitted for simulation; ARM unsupported.

[3]

Compute for the workload
  • Guide recommends 6 cores / 12 threads at 4.9 GHz or higher
  • 32 GiB RAM minimum; 64 GiB recommended; smaller setups need constrained builds
  • 1 TB NVMe SSD with at least 100 GB free
  • Integrated graphics for basic simulation; NVIDIA RTX 3060/4060 or higher for ML/vision and full OMTS simulation with perception
  • 2–3 Gigabit Ethernet ports recommended

[3]

Installation & first result

Open the upstream getting-started guide [3] · Project documentation [1]

  • Prepare the guide’s Ubuntu 26.04 x86-64 host with Git LFS.
  • Fetch Core 20261012.0 and record the OMTS tag selected separately by the guide.
  • Install k3s, deploy the runtime and inctl, and configure NVIDIA support for perception.
  • Follow the Bazelisk and LLVM/libxml setup steps.
  • Build //:omts_solution with --config=lab_bb_01 and --operation_mode=sim.
  • Inspect the scene using the documented RViz or Gazebo route.

[3] [4]

Installation

Follow the 20261012.0 guide: fetch Core at its explicit tag and record the separately selected OMTS release; install k3s, deploy the matching runtime/inctl and build the simulation with Bazelisk. Configure NVIDIA support for perception.

[3]

Hardware, models & data

Supported hardware
  • Documented lab_bb_01: UR3e / CAW enclosure without CNC or vise; configuration names Robotiq Hand-E and Orbbec camera
  • Default OMTS: UR5e / CNC enclosure / Schunk vise
  • Hardware adapters also document digital-I/O gripper and CNC machine interfaces

Specific source configuration and adapter evidence; not a claim of universal device compatibility or our hardware testing.

[5] [6] [7]

Interfaces
  • ROS 2 interoperability
  • inctl CLI
  • Local deployment endpoint on port 17080

[1] [3] [4]

Inputs and outputs

OMTS consumes a cell configuration, camera/perception results and machine I/O state; its behavior tree coordinates robot motion, gripping, CNC loading, machining handshake, unloading and return to infeed.

[5] [6] [7]

Project notes

The installation guide is narrower than the README

The pinned README lists Ubuntu 24.04 and 26.04, with 22.04 also described as supported. The Getting Started guide instead requires Ubuntu 26.04. We have not resolved that discrepancy through installation; use 26.04 for the route described here rather than assuming the older releases work. The guide excludes ARM hosts and requires Intel for real-time hardware control, while allowing AMD for simulation. [1] [3]

Plan for 32 GiB RAM, with 64 GiB recommended, and at least 100 GB free on the recommended 1 TB NVMe drive. Integrated graphics can cover basic simulation, but full OMTS simulation with perception requires a dedicated NVIDIA GPU; the guide names RTX 3060/4060 or better. Small 16 GiB systems may need constrained builds and separate visualization, so they are not the baseline configuration. [3]

A first result is a deployed simulated cell

The refreshed guide pins Core 20261012.0 but selects the latest OMTS release dynamically. Record both tags instead of assuming matching release numbers. It installs k3s, deploys the runtime archive and installs inctl. It then uses Bazelisk to build OMTS with --config=lab_bb_01 and explicitly selects --operation_mode=sim. Follow the linked guide for its GPU configuration and LLVM/libxml compatibility step. The repository pins Bazel 8.8.1. The separately reviewed September OMTS module still pins the older Core commit; its dependency declaration is not proof that the two October setup selections match. [3] [8] [9]

After deployment, RViz shows the software's believed scene state; Gazebo shows the physics simulation. The documented RViz route uses ROS 2 Lyrical and Zenoh. These views can differ, which is useful when checking scene configuration and perception before a physical trial. [4]

Open code and external models have different boundaries

The repository carries Apache-2.0. OMTS's FoundationPose weights are downloaded separately from NVIDIA under the NVIDIA Open Model License, according to OMTS's licensing section; they are not included under the repository's Apache license. A source archive alone also omits Git LFS payloads, which the setup guide requires for geometric models. [2] [3] [5]

The preserved Core archive contains 432 Git LFS pointer files; those payloads were not acquired. The new runtime/setup sources were checked on October 18, while the separately cited OMTS configuration remains the September snapshot. This is a source-researched setup assessment. We have not installed the runtime or measured control performance, and no complete hardware-cell cost has been established.

What we checked

Source-researched release profile. We have not installed this release, run its tests, commissioned a cell or measured performance. No affiliation or endorsement claimed.

Not yet established

  • Requirements: operating system

Updates

Upstream last updated
Oct 12, 2026 [10]
Latest release
Oct 12, 2026 [10]
Profile updated
Oct 18, 2026
Sources last checked
Oct 18, 2026
Next review
Nov 18, 2026
Reviewed revision
20261012.0 / a3bd4465a25ab7e388e469eb3d9b72b15c15c13f · software repository

Source files and licenses

Open software profile; external model weights, dependencies and physical devices have separate scope. No complete open hardware or tested deployment claim.

LayerAvailability / license
softwareavailable · Apache-2.0
Repository material under its root license; third-party artifacts and marks retain separate terms. [1] [2]
model weightsavailable · NVIDIA Open Model License (upstream OMTS declaration)
External FoundationPose weights downloaded by the build; absent from the reviewed repository and not covered by its Apache-2.0 license. This review records the upstream declaration, not a legal interpretation or verified download. [5]
documentationavailable · Apache-2.0
Repository material under its root license; third-party artifacts and marks retain separate terms. [1] [2]

No training dataset is being offered or reviewed in this runtime/application profile.

References

Each source links to the exact revision we read. “Used for” shows where this page relies on it.

Project sources

Videos

  • S011 Intrinsic (YouTube channel)
    The project’s own YouTube channel, linked from the project’s own documentation. Not reviewed by us for accuracy.
    Revision, date & where cited

    YouTube channel Intrinsic · youtube.com · Accessed Oct 4, 2026

Correction guidance · Discussion is not enabled · Profile format 0.7.0-draft.5

Change history

2026-09-30 — Initial source-researched profile of release 20260922.0; installation scope and external weight terms distinguished.

2026-10-04 — Added 1 YouTube reference(s) (S011): official channel or videos linked from the pinned upstream sources. Existing claims, source-check dates and evidence are unchanged.