GraphCanon updated 3w · GitHub synced 3w
Decision brief
Dstack offers infrastructure for running AI workloads in Trusted Execution Environments ensuring privacy and security.
Good fit when
- When you need to run confidential AI computations that require Intel TDX or NVIDIA GPUs to ensure data and code are protected from potential threats at runtime
- If your project involves sensitive data processing where privacy guarantees provided by trusted execution environments are crucial
Avoid when
- Avoid if your AI workloads do not benefit from confidential computing features as the overhead of using Intel TDX may not provide any advantage and can add complexity
- Not suitable for hardware setups that do not support Intel TDX or AMD SEV-SNP, limiting flexibility compared to broader hardware support offered by competitors
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
cargo add dstackSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Provides infrastructure to run AI workloads in Trusted Execution Environments (TEEs) using Intel TDX and NVIDIA GPUs, ensuring privacy and security.
Capability facts
- Languages
- rust
Source: github.language · Aug 2, 2026
Categories
Tags
README
Getting Started
Try it now: Chat with LLMs running in TEE at chat.redpill.ai. Click the shield icon to verify attestations from Intel TDX and NVIDIA GPUs.
Deploy your own:
---
# docker-compose.yaml
services:
vllm:
image: vllm/vllm-openai:latest
runtime: nvidia
command: --model Qwen/Qwen2.5-7B-Instruct
ports:
- "8000:8000"
Deploy to a self-hosted TDX machine with the dstackup install -> dstack deploy workflow, or use Phala Cloud for managed infrastructure. AMD SEV-SNP hosts use the same workflow when the selected guest image includes digest.txt.
Setting up dstack on your own hardware? Start with the self-hosted quick onboarding guide
Building or customizing the guest OS itself? Follow the guest-OS build guide.
Developing without TEE hardware? Use a development image with no-TEE mode and swtpm.
License
The dstack-owned source, SDKs, documentation, tools, guest OS backend, and
image-assembly code are Apache-2.0. Embedded and third-party components retain
their own license declarations and notices. See file-level SPDX declarations
and REUSE.toml for the exact scope.
For agents
This page has a .md twin and JSON over the API.