Sequa · GripSim
Sequa logo

Sequa

Agentic skill API that sequences and recovers grasps into tasks.

Overview

What Sequa does

A managed agentic API that sequences Dextra grasp skills into multi-step tasks, monitors execution through Tactyl's predictions, and autonomously re-plans and recovers when a grasp fails.

  • Agentic planner
  • Failure recovery
  • Skill library
  • Grounded in feedback
Key features

Inside Sequa

Built to be GPU-essential, NVIDIA-aligned, and production-ready.

Agentic planner

An LLM-grounded planner turns grasps into multi-step tasks.

Failure recovery

Detects slip or miss and re-plans a recovery grasp automatically.

Skill library

Compose reusable manipulation skills into task graphs.

Grounded in feedback

Reasoning is anchored in real Tactyl contact signals.

Managed API

Call it from your stack — no scripting every contingency.

Task-graph interface

Design and monitor workflows visually.

Specs

Technical specifications

TypeAgentic skill/task API
ReasoningNVIDIA NeMo LLM
ServingTriton + NIM microservices
SchedulingNVIDIA cuOpt
EdgeJetson Thor grounded execution
DeliveryNVIDIA AI Enterprise
Gallery

Sequa in action

Live grasp telemetry
Success rate & cycle time
Domain-randomized scenes
Use cases

Where Sequa fits

  • Multi-step machine tending
  • Order kitting and fulfillment
  • Assembly sequences
  • Recoverable service-robot tasks
Pricing

Ways to deploy Sequa

Start free. Scale to a fleet. Pricing shown is indicative, pre-launch.

Pilot

Project

Paid pilot to prove value on your hardware

  • Scoped pilot
  • Engineer support
  • Benchmark report
Get started

Enterprise

Custom

For large fleets and custom needs

  • Custom SLAs
  • On-site support
  • Roadmap input
Get started
FAQ

Sequa questions

Does it require NVIDIA hardware?
Yes — Sequa is GPU-essential; see the specs above for the exact stack.
Can I use it standalone?
Yes, Sequa works on its own and integrates with the rest of the GripSim stack.
How do I get started?
Talk to our team for a scoped pilot tailored to your robot and task.
Related

Explore the rest of the stack

Dextra logo

Dextra

Cross-embodiment VLA manipulation foundation model + fine-tuning toolkit.

Explore Dextra →
Tactyl logo

Tactyl

Tactile-and-vision contact world model that predicts grasp outcomes.

Explore Tactyl →
Why GripSim

Built for production robotics

The manipulation layer teams ship with, not a research demo.

Cross-embodiment by design

One policy runs across many grippers and hands — no per-robot rewrite.

Closed-loop with touch

Tactyl predicts slip and force so grasps react before they fail.

Runs on the robot

Reflex executes on Jetson at control-loop latency, with safety limits.

A moat that compounds

Every deployment feeds the shared model through the data flywheel.

Stay in the loop

Manipulation research, in your inbox

Benchmarks, sim-to-real notes, and product updates. No hype, no spam.

Put Sequa to work

Tell us your robot and task — we'll scope a pilot.