Sold by: Klastrovanie Co., Ltd.
Deployed on AWS
AgileTaskHeron ranks who or what should do each task next, across mixed robot fleets and human teams. It returns an ordered recommendation with the evidence behind each candidate, alternative candidates for comparison, and a close-call flag, and it integrates with your MES. For human assignments it is decision support only: the final assignment is made and recorded by a person, in line with human-oversight expectations such as the EU AI Act.
Overview
Image
AgileTaskHeron. Robot Orchestration for MES
Image
A ranked recommendation, decided by your team.
Video
Product video
AgileTaskHeron turns your tasks, skills, and resources into a graph and ranks the best candidate for each task by graph contribution (weighted PageRank over the whole input). It works for mixed robot fleets on a manufacturing line and for human teams, and it integrates with your MES to decide what to run next.
Every result is explainable and built for review. For each task it returns an ordered list of candidates, the links and matched skills that produced each ranking, up to N alternative candidates outside the top bundle for comparison, and a decision_support block with the recommended choice, the runner-up, the score gap, and a close_call flag when the gap is small. Request fields such as max_alternatives and close_call_margin let reviewers tune how much comparison they see.
For human task assignment, AgileTaskHeron is decision support only. It produces a recommendation with evidence and alternatives; the final assignment must be made and recorded by a person. This keeps a qualified human in control of decisions about people, in line with human-oversight requirements such as EU AI Act Article 14. CPU and GPU container editions return tasks in the same order and run in your own AWS account.
Highlights
- Optimal plus alternatives. For each task, an ordered recommendation by graph contribution, with up to N alternative candidates and a close-call flag so reviewers can compare, not just accept.
- Explainable, review-ready. Every candidate carries the links and matched skills behind its ranking. For people it is decision support only, with the final assignment made and recorded by a person (EU AI Act Article 14).
- Robots and people, with MES. One graph engine for mixed robot fleets and human teams, integrated with your MES, in CPU and GPU editions that run in your own AWS account.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
CPU Edition
GPU Edition
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
Production Line License | License for one production line, HR team, or project team. | $9,000.00 |
Factory Site Standard License | License for one factory site, HR branch, or business unit. | $27,000.00 |
Enterprise License | License for all factory sites or HR units in one organization. | $135,000.00 |
Dimensions summary
You choose a license based on how widely you deploy the software. All three options bill as annual contracts, priced per unit. The Production Line License covers one production line. The Factory Site Standard License covers a single factory site. The Enterprise License covers all factory sites within one organization. Pricing scales by deployment scope: from one line, to one full site, to your entire organization. Pick the license that matches how broadly you plan to run robot orchestration across your operations.
Top-of-mind questions for buyers
One production line is a single manufacturing line where the robot orchestration software runs. You buy one unit per line. If you operate several lines at the same site, each line needs its own license under this option.
The Factory Site Standard License covers one factory site, including all lines at that location. The Enterprise License covers every factory site within one organization. Choose Site if you deploy at a single location. Choose Enterprise if you deploy across multiple sites organization-wide.
No. Each license covers a defined deployment scope. Adding a line beyond your licensed Production Line count means buying another unit. Site and Enterprise licenses already cover added lines within their scope. Confirm scaling details with the vendor at contact@klastrovanie.com.
www.klastrovanie.com
Helpful?
Vendor refund policy
Refunds are evaluated case-by-case. Customers may request a refund within 14 days of purchase if the software has not been deployed to production. Contract-based licenses (Production Line License, Factory Site License) are non-refundable once deployed to production or after 30 days from the contract start date, except as required by law. To request a refund, contact support@klastrovanie.com with your AWS account ID and order details. We respond within 3 business days.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
CPU Edition
Supported services: Learn more
- Amazon ECS
- Amazon EKS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Version 1.0.4
Human task-assignment output (/analyze/human, /examples/human) now includes decision-support information. Existing request formats keep working.
New
- Evidence per candidate: direct task link, required-skill links (person vs. task level), skills matched, and the person's other task links.
- alternative_people: up to N people outside the bundle who are linked to the task or its skills, shown for comparison.
- decision_support per task: recommended and runner-up, score gap, and a close_call flag when the gap is below a set margin.
- New optional request fields: max_alternatives (default 3) and close_call_margin (default 0.10).
Changed
- Tasks are now ordered by task score, and priority numbers follow that order. CPU and GPU editions return tasks in the same order.
- Candidates within each task are listed in ranked order.
Output is a recommendation; the final assignment is made by a person.
Additional details
Usage instructions
Container listens on port 8080. No environment variables required to start.
Health check: GET /health Root/identity check: GET / (returns {"backend": "cpu"})
Endpoints: POST /analyze/human - task/skill/person graph analysis. Returns ranked candidates with evidence, alternatives, and a close_call flag. Optional fields: max_alternatives (default 3), close_call_margin (default 0.10). POST /analyze/robot - robot/task eligibility and bundling GET /examples/human - smoke test with built-in sample data (same optional query parameters) GET /examples/robot - smoke test with built-in sample data
ECS task definition: map containerPort 8080, set healthCheck command to ["CMD", "python3", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://localhost:8080/health ').status==200 else 1)"]. The image does not include curl.
EKS: set livenessProbe/readinessProbe httpGet path=/health port=8080.
Minimum: 1 vCPU / 1 GiB memory. Recommended: 2 vCPU / 2 GiB memory.
Resources
Vendor resources
Support
Vendor support
Technical support is available for AgileTaskHeron deployment, configuration, container operation, and basic integration with manufacturing or MES environments.
Support includes assistance with installation issues, container configuration, input data requirements, API usage, troubleshooting, and product-related technical questions.
Standard support is provided by email on business days. Enterprise customers and customers purchasing through a Private Offer may receive additional deployment and integration support according to the terms of their agreement.
Support email: contact@klastrovanie.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Connected Worker and Process Automation
Our in-house specialized product team will help with customized implementation of TaskWatch solutions.
DataRobot's Agent Workforce Platform lets enterprises build, operate, and govern fleets of production AI agents on AWS - and in hybrid, sovereign, and air-gapped environments - with the same governance layer in every one. Model-, framework-, and orchestration-neutral, with forward-deployed DataRobot engineers who build your first mission-critical agents alongside your team.
KABAM Robotics' Smart+ app is a cutting-edge robot management platform designed for security and facility management. It offers centralized control and real-time monitoring of your robot fleet, providing instant alerts, seamless integration with building infrastructure (CCTVs, IoT devices, lifts), and automated reports. Its user-friendly interface and video analytics empower efficient operations and faster incident response.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.