Sold by: BOSICLOUD
Deployed on AWS
Self-hosted AI Agent runtime on Amazon EKS. Deploy production agents with durable state, pluggable Sandbox execution, AgentCore hardware isolation, and multi-channel support in under five minutes.
Overview
We built this platform to solve a specific problem: running AI Agents in production without the operational headaches that come with serverless glue code and third-party orchestration layers.
The runtime sits directly on Amazon EKS. Messages from end users hit the Pod through an in-process Channel Manager. No Lambda hops, no SQS detours, just a straight path from ingress to the Agent loop. This keeps latency predictable and makes the whole request lifecycle visible in a single trace.
The orchestration engine is ours, not a wrapper around LangChain or AutoGen. It manages tool dispatch, memory retrieval, and LLM calls in one tight loop. Conversation history, Agent configuration, and working memory all land in PostgreSQL on every turn. If the Pod dies mid-response, you pick up exactly where you left off.
Execution is cleanly separated from orchestration through a pluggable Sandbox architecture. The default Sandbox spins up Docker containers with sub-second cold starts. For workloads that need hard isolation (multi-tenant or regulated environments), AgentCore provides Firecracker-backed micro-VMs with hardware-level isolation. Sandboxes are created lazily on the first tool call and automatically reclaimed after idle timeout. Pure-chat workloads consume zero Sandbox resources, and workspace state is persisted to S3 between sessions. The executor itself is roughly 200 lines of Go, small enough to audit in one sitting.
Concurrency is handled per-Pod with database-level session isolation keyed on agentID, accountID, and chatID. Sub-Agent delegation works out of the box, with cascading cancellation and timeout enforcement so runaway tasks do not pile up.
On the integration side, we support Telegram, Discord, Slack, LINE, WeChat, Feishu, and WeCom. Connect a channel, point it at your Agent, and you are live. Most teams get their first Agent into production in under five minutes.
Self-hosted, open source, no phone-home telemetry. If you need to own your Agent infrastructure end to end, this is the stack.
Highlights
- Runs AI Agents directly on Amazon EKS Pods. Messages go from channel ingress to the Agent loop in two hops, no Lambda or queue layers. Pod state is fully externalized to PostgreSQL, so Pods stay stateless, restarts lose nothing, and horizontal scaling is just adding replicas.
- Pluggable Sandbox architecture with two isolation tiers. Docker containers spin up in sub-second for standard workloads. AgentCore delivers Firecracker-backed micro-VM isolation for multi-tenant or regulated environments.Sandboxes are lazily created and auto-reclaimed on idle. You pay only for actual execution.
- Ship your first Agent in under five minutes. Connect any supported channel (Telegram, Discord, Slack, LINE, WeChat, Feishu, WeCom), configure your Agent, and go live. Sub-Agent task delegation, cascading timeout enforcement, and unified in-process tracing are included out of the box.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
AmazonLinux 2023
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/month |
|---|---|---|
AgentCopilot User Seats | Number of licensed user seats for your AgentCopilot private deployment. Each unit includes 50 user seats. Each seat authorizes one user to access the self-hosted AgentCopilot environment. | $500.00 |
Additional User Seat | Additional user seat license for AgentCopilot. Each unit extends your deployment authorization by one user beyond the base 50 seats. | $10.00 |
Vendor refund policy
All sales are final. No refunds are provided for contract-based purchases. If you experience technical issues or believe you were charged in error, please contact us at zhangyingting@hzcloud.com.cn within 30 days of purchase and we will review your case individually.
Custom pricing options
Request a private offer to receive a custom quote.
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
Initial release.
Runtime: 1.Runs on Amazon EKS, messages route from channel ingress to Pod in 2 hops 2.No Lambda, no SQS, no external orchestration framework dependencies 3.Orchestration engine manages the full LLM call loop, tool dispatch, and memory retrieval internally
State: 1.All conversation history, Agent config, and working memory persisted to PostgreSQL on every turn 2.Pods are stateless, restarts and scaling events lose nothing 3.Session isolation at DB level: agentID + accountID + chatID
Execution: 1.SandboxExecutor interface with two backends 2.Docker: default, sub-second cold start 3.Firecracker: hard tenant isolation for regulated environments 4.Executor is ~200 lines, single responsibility (exec/file)
Multi-Agent: 1.Sub-Agent task delegation with automatic cascading cancellation 2.Timeout enforcement per delegated task
Channels: 1.WeChat, WeCom, Feishu
Tracing: 1.In-process unified logs, no sidecar or external collector required
Additional details
Usage instructions
- Launch the instance using the recommended instance type
- SSH into the instance: ssh -i your-key.pem ec2-user@<public-ip>
- Access the web interface at http://<public-ip>:18080
- Create an admin account on first visit to start using the application
Support
Vendor support
AgentCopilot support is available via email at zhangyingting@hzcloud.com.cn . Our team provides assistance with onboarding, configuration, and technical issues. Enterprise customers receive priority support with dedicated response times. Documentation and guides are available at our support portal.
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-powered contact center copilot for insurers that enhances agent productivity, automates claims intake, and delivers real-time insights using AWS generative AI services.
One of the most persistent challenges in modern software engineering is identifying and resolving bugs early in the development lifecycle.
As AI begins writing a lot more code, traditional QA and code review pipelines will not scale, leading to production failures, wasted developer hours, and delayed releases.
GoML's modular and scalable agentic AI accelerator solves that. The multi-agent agentic AI accelerator includes 4 AI agents to automate the software testing lifecycle. These purpose-built AI agents for software testing integrate and autonomously interact with four of the most popular developer tools - Git, Jira, GitHub, and SonarQube - to enable early detection, consistent quality enforcement, and faster resolution cycles.
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.