{"data":{"slug":"dstack-tee-dstack","name":"dstack","tagline":"Open framework for confidential AI","github_url":"https://github.com/Dstack-TEE/dstack","owner":"Dstack-TEE","repo":"dstack","owner_avatar_url":"https://avatars.githubusercontent.com/u/187594727?v=4","primary_language":"Rust","stars":546,"forks":96,"topics":["confidential-ai","confidential-computing","intel-tdx","private-ai","safe-ai","secure-ai","tee","trusted-execution-environment"],"archived":false,"github_pushed_at":"2026-09-18T06:59:36+00:00","maintenance_label":"Very active","stars_delta_30d":27,"url":"https://www.graphcanon.com/tools/dstack-tee-dstack","markdown_url":"https://www.graphcanon.com/tools/dstack-tee-dstack.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dstack-tee-dstack","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dstack-tee-dstack","description":"Open framework for confidential AI","homepage_url":"https://dstack.org","license":"Apache-2.0","open_issues":79,"watchers":9,"ai_summary":"Dstack-TEE/dstack is an open-source framework for confidential AI, enabling secure execution environments using technologies like Intel TDX and AMD SEV-SNP.","readme_excerpt":"## Getting Started\n\n**Try it now:** Chat with LLMs running in TEE at [chat.redpill.ai](https://chat.redpill.ai). Click the shield icon to verify attestations from Intel TDX and NVIDIA GPUs.\n\n**Deploy your own:**\n\n```yaml\n\n---\n\n# docker-compose.yaml\nservices:\n  vllm:\n    image: vllm/vllm-openai:latest\n    runtime: nvidia\n    command: --model Qwen/Qwen2.5-7B-Instruct\n    ports:\n      - \"8000:8000\"\n```\n\nDeploy to a self-hosted TDX machine with the `dstackup install` -> `dstack deploy` workflow, or use [Phala Cloud](https://cloud.phala.network) for managed infrastructure. AMD SEV-SNP hosts use the same workflow when the selected guest image includes `digest.txt`.\n\nSetting up dstack on your own hardware? Start with the [self-hosted quick onboarding guide](./docs/onboarding.md)\n\nBuilding or customizing the guest OS itself? Follow the [guest-OS build guide](./docs/building-guest-os.md).\n\nDeveloping without TEE hardware? Use a development image with\n[no-TEE mode and swtpm](./docs/development-without-tee.md).\n\n---\n\n## License\n\nThe dstack-owned source, SDKs, documentation, tools, guest OS backend, and\nimage-assembly code are Apache-2.0. Embedded and third-party components retain\ntheir own license declarations and notices. See file-level SPDX declarations\nand [`REUSE.toml`](./REUSE.toml) for the exact scope.","github_created_at":"2024-09-13T03:25:07+00:00","created_at":"2026-07-11T23:13:54.894293+00:00","updated_at":"2026-09-20T04:30:11.718694+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"confidential-ai","name":"confidential-ai"},{"slug":"confidential-computing","name":"confidential-computing"},{"slug":"intel-tdx","name":"intel-tdx"},{"slug":"private-ai","name":"private-ai"},{"slug":"safe-ai","name":"safe-ai"},{"slug":"secure-ai","name":"secure-ai"},{"slug":"tee","name":"tee"},{"slug":"trusted-execution-environment","name":"trusted-execution-environment"}],"trust":{"provenance":{"is_fork":false,"github_id":856700396,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:21:41.970Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":11,"days_since_push":0,"last_release_at":"2026-09-15T07:18:57Z","stars_delta_30d":27,"open_issues_delta_30d":-99},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:21:43.576Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:21:40.838Z"},"languages":{"value":["rust"],"source":"github.language","observed_at":"2026-09-18T08:21:40.838Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:21:40.838Z"}},"decision_facts":{"hosting":{"model":"self_hosted","summary":"Supports self-hosted TDX machines and managed infrastructure via Phala Cloud."},"pricing":null,"requirements":{"notes":["Requires TEE hardware for full functionality, but offers a no-TEE mode for development."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"hosting_model":"self_hosted","requires_docker":true},"when_to_use":["When you need to ensure secure execution environments for AI models using Intel TDX or AMD SEV-SNP technologies.","If you are working with sensitive data and require a trusted execution environment to protect model confidentiality.","For deploying AI models in a self-hosted TDX machine or using managed infrastructure like Phala Cloud."],"when_not_to_use":["If your project does not require confidential computing and you are looking for a more general-purpose AI development tool.","When you do not have access to TEE hardware and are unwilling to use the no-TEE mode with swtpm for development.","If you prefer a framework that does not require setting up a secure execution environment and can operate without Intel TDX or AMD SEV-SNP."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:04:57.290Z"},"constraint_facets":{"min_ram_gb":null,"hosting_model":"self_hosted","requires_docker":true},"decision_summary":[{"label":"Hosting","value":"self hosted - Supports self-hosted TDX machines and managed infrastructure via Phala Cloud."},{"label":"Requirements","value":"Requires Docker; Requires TEE hardware for full functionality, but offers a no-TEE mode for development."},{"label":"Adopt for","value":"Dstack is an open-source framework for confidential AI, offering secure execution environments using Intel TDX and AMD SEV-SNP technologies."},{"label":"License detail","value":"Dstack is licensed under Apache-2.0, with embedded and third-party components retaining their own licenses."}]}}