Sold by: Bansir LLC
Deployed on AWS
This product has additional charges applied for the use of a preconfigured solution which contains: CUDA 13, Docker with NVIDIA Toolkit, Ollama with llama3.2:3b, llama3.1:8b and nomic-embed-text, Python 3.12, LangGraph 1.2, CrewAI 1.15, FastAPI and Open WebUI. Multi-agent orchestration 100% self-hosted on Tesla T4 GPU.
Overview
This product has additional charges applied for the use of a preconfigured solution. Agentic AI Runtime Server is a complete, production-ready platform for building, deploying, and orchestrating autonomous AI agents on AWS. This solution eliminates weeks of infrastructure setup by delivering a fully configured multi-agent runtime from the first boot. It includes Docker with NVIDIA Container Toolkit, Ollama runtime with three preinstalled models (llama3.2:3b for fast routing, llama3.1:8b for general reasoning, and nomic-embed-text for semantic search and RAG), Python 3.12 in an isolated virtual environment, LangGraph 1.2 for stateful orchestration with persistent SQLite checkpoints, CrewAI 1.15 with a preconfigured research crew, FastAPI with documented REST endpoints, and Open WebUI for a ChatGPT-style chat interface. All components are managed by systemd services with auto-start on boot, and an anti-suspension policy is applied at the kernel and systemd levels to guarantee 24/7 availability. Optimized for NVIDIA Tesla T4 GPUs on EC2 g4dn instances.
The platform delivers three core benefits. First, complete privacy: every inference runs locally on your own infrastructure no data leaves the instance, no external API calls, making it ideal for legal, healthcare, finance, government, and any organization with strict data residency or compliance requirements such as HIPAA, GDPR, or SOC 2. Second, true multi-agent orchestration: unlike single-model chatbots, this runtime coordinates multiple specialized agents that plan, research, critique, and write in sequence, producing structured deliverables such as research reports, competitive analyses, and technical documentation in minutes instead of hours. Third, dual access interfaces: developers consume the REST API programmatically via FastAPI endpoints (/agents/run, /crews/run, /health, /models) with auto-generated Swagger documentation, while non-technical users interact through Open WebUI's intuitive chat interface no coding required.
Key use cases include legal document analysis and contract review for law firms, clinical note summarization and patient history retrieval for hospitals, competitive intelligence and market research for consulting firms, academic literature review and personalized tutoring for universities, and technical assistant and predictive maintenance for industrial operations. The solution is fully customizable: users can modify LangGraph state machines, adjust CrewAI agent roles and prompts, download additional Ollama models, and extend FastAPI with new endpoints. Perfect for enterprises, startups, research institutions, and government agencies seeking a private, self-hosted, GPU-accelerated AI agent platform on AWS without vendor lock-in, per-token billing, or data privacy concerns.
Highlights
- Complete preconfigured runtime with CUDA 13, Ollama, LangGraph 1.2, CrewAI 1.15, FastAPI, and Open WebUI. Deploy multi-agent AI in minutes instead of weeks no manual setup, no dependency conflicts, production-ready from first boot with systemd auto-start and anti-suspension policies.
- True multi-agent orchestration powered by LangGraph stateful workflows with persistent SQLite checkpoints and CrewAI role-based agents. Dual access via REST API with Swagger documentation for developers and Open WebUI chat interface for non-technical users all on a single GPU-accelerated instance.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 26.04
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 actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g4dn.2xlarge Recommended | $2.40 |
g4dn.metal | $2.40 |
g4dn.16xlarge | $6.40 |
g4dn.12xlarge | $6.40 |
g4dn.8xlarge | $3.20 |
g4dn.4xlarge | $2.40 |
g4dn.xlarge | $1.60 |
Vendor refund policy
For this offering, Bansir does not offer refund, you may cancel at anytime.
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
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
ver 2026
Additional details
Usage instructions
================================================================ AGENTIC AI RUNTIME SERVER - USAGE INSTRUCTIONS Ubuntu 26.04 LTS with CUDA 13 and Multi-Agent Orchestration
This AMI is fully preconfigured. No installation required. Full documentation: https://bansir-img.s3.us-east-1.amazonaws.com/Guide+Agentic+AI+Runtime+Server.html
STEP 1 - LAUNCH THE INSTANCE
Subscribe to the AMI and launch on g4dn.2xlarge (recommended). Open these ports in the Security Group:
- 22 (SSH) administration
- 3000 (WebUI) chat interface
- 8000 (API) REST API
Restrict ports 3000 and 8000 to your IP for security.
STEP 2 - VERIFY SERVICES
SSH as user "ubuntu" and verify: sudo systemctl status agentic-api open-webui ollama
All three services should be "active (running)".
Health check: curl -s http://localhost:8000/health
STEP 3 - USE THE CHAT INTERFACE
Open in your browser: http://<INSTANCE_PUBLIC_IP>:3000
Register the first account (becomes admin automatically). Select llama3.1:8b and start chatting.
Disable public signups after setup: Avatar > Admin Panel > Settings > General
Disable "Enable New Sign Ups"
STEP 4 - USE THE REST API
Swagger docs: http://<INSTANCE_PUBLIC_IP>:8000/docs
Endpoints: GET /health Health check GET /models List Ollama models POST /agents/run LangGraph research agent POST /crews/run CrewAI research crew
Example:
curl -X POST http://<IP>:8000/agents/run
-H "Content-Type: application/json"
-d '{"query":"Explain LangGraph","thread_id":"demo1"}'
STEP 5 - MONITOR AND CUSTOMIZE
Logs: sudo journalctl -u agentic-api -f GPU monitor: nvidia-smi / watch -n 2 nvidia-smi Runtime dir: /opt/agentic-runtime/ Docs: /opt/agentic-runtime/README.md
After any config change: sudo systemctl restart agentic-api
Full usage guide : https://bansir-img.s3.us-east-1.amazonaws.com/Guide+Agentic+AI+Runtime+Server.html
Resources
Vendor resources
Support
Vendor support
Remote support support@bansircloud.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
AI Refinery™ is an AI foundation platform, created by Accenture and built to leverage NVIDIA technology to help companies turn raw AI technology into useful business solutions.
o Agents - Build agents and create an autonomous network that works together to accomplish goals.
o Knowledge - Collect and organize enterprise data and knowledge to power AI applications and agents.
o Models - Customize pre-built foundation models using proprietary data, and flex between models based on key performance factors.
o Governance - Manage all AI components across an enterprise, with an eye on cost, accuracy, security, responsible use, and more.
Built for an era where AI defines new processes, workflows, and software, AI Refinery™ puts AI into the hands of an organization's entire workforce to continuously reinvent the highest value enterprise capabilities.
Launch AI agents in minutes. Pre-configured with Claude Code, Codex, OpenCode, OpenClaw, Docker, Playwright, and Caddy on Ubuntu 24.04. Onboarding starts on boot.
This product has charges associated with it for seller support. Jumpstart your AI Agent development with a ready-to-use platform powered by CrewAI Studio, JupyterHub & NVIDIA GPU support.
SquadForge is a serverless, AWS-native platform that empowers organisations to design, build, and orchestrate AI agents tailored to their operational workflows. Users can create single agents or multi-agent systems, connect MCP tools, ingest documents, and integrate with enterprise systems all within a secure and observable environment. With its modular architecture and rapid deployment model, SquadForge enables teams to experiment, automate, and scale agentic workflows with speed, precision, and full governance.
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.