--- title: "Foundry-Local vs claude-code-local" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-foundry-local-vs-nicedreamzapp-claude-code-local" tools: ["microsoft-foundry-local", "nicedreamzapp-claude-code-local"] --- # Foundry-Local vs claude-code-local *GraphCanon updated Aug 12, 2026* ## Verdict Pick Foundry-Local if foundry-Local offers SDK and CLI for local GPU-accelerated AI inference, focusing on speech-to-text models such as Whisper, using ONNX Runtime; pick claude-code-local if claude-code-local offers an MLX-native Anthropic-API server and support for running large models locally on Apple Silicon with high token throughput and privacy guarantees. [Foundry-Local](https://foundrylocal.ai) reports 2.5k GitHub stars, 348 forks, and 71 open issues, last pushed Jul 30, 2026. [claude-code-local](https://www.youtube.com/@nicedreamzapps) has 3.2k stars, 608 forks, and 1 open issues, last pushed Aug 11, 2026. Figures are from public GitHub metadata via [Foundry-Local's repository](https://github.com/microsoft/Foundry-Local) and [claude-code-local's repository](https://github.com/nicedreamzapp/claude-code-local). | | [Foundry-Local](/tools/microsoft-foundry-local.md) | [claude-code-local](/tools/nicedreamzapp-claude-code-local.md) | | --- | --- | --- | | Tagline | SDK and CLI for local AI inference with GPU acceleration, supporting speech-to-text models like Whisper. | Run Claude Code on-device using local AI models for privacy-sensitive workflows. | | Stars | 2,479 | 3,193 | | Forks | 348 | 608 | | Open issues | 71 | 1 | | Language | C++ | Python | | Adopt for | Foundry-Local offers SDK and CLI for local GPU-accelerated AI inference, focusing on speech-to-text models such as Whisper, using ONNX Runtime. | claude-code-local offers an MLX-native Anthropic-API server and support for running large models locally on Apple Silicon with high token throughput and privacy guarantees. | | Persona | - | - | | Runtime | - | - | | License | SDK is licensed under the MIT License. The CLI uses the Microsoft Software License Terms. Models available with Foundry-Local are individually licensed as per their documentation or download page. | MIT | | Categories | Inference & Serving, Speech & Audio | Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Foundry-Local](/tools/microsoft-foundry-local.md) | [claude-code-local](/tools/nicedreamzapp-claude-code-local.md) | | --- | --- | --- | | Open issues (now) | 71 | 1 | | Owner type | Organization | User | | Full report | [trust report](/tools/microsoft-foundry-local/trust.md) | [trust report](/tools/nicedreamzapp-claude-code-local/trust.md) | ## Decision facts: Foundry-Local - **Pricing:** freemium - Free to use SDK and CLI under MIT and Microsoft licenses, individual AI models subject to their own license terms. - **Adopt for:** Foundry-Local offers SDK and CLI for local GPU-accelerated AI inference, focusing on speech-to-text models such as Whisper, using ONNX Runtime. - **License detail:** SDK is licensed under the MIT License. The CLI uses the Microsoft Software License Terms. Models available with Foundry-Local are individually licensed as per their documentation or download page. ## Decision facts: claude-code-local - **Pricing:** freemium - Free to use under the MIT license; premium support or features may incur costs not detailed in the repository. - **Requirements:** - Needs Apple Silicon hardware.; - Compatible with Python. - **Adopt for:** claude-code-local offers an MLX-native Anthropic-API server and support for running large models locally on Apple Silicon with high token throughput and privacy guarantees. ## Choose when ### Choose Foundry-Local if… - Foundry-Local is primarily C++; claude-code-local is Python. - License: Foundry-Local is Other, claude-code-local is MIT. - Pricing: Free to use SDK and CLI under MIT and Microsoft licenses, individual AI models subject to their own license terms.. - Tags unique to Foundry-Local: ai-sdk, chat-completions, foundry-local, gpu acceleration. - Also covers Speech & Audio. - Need to run AI models locally with GPU acceleration ### Choose claude-code-local if… - claude-code-local is primarily Python; Foundry-Local is C++. - License: claude-code-local is MIT, Foundry-Local is Other. - Pricing: Free to use under the MIT license; premium support or features may incur costs not detailed in the repository.. - Requirements: - Needs Apple Silicon hardware.; - Compatible with Python.. - Tags unique to claude-code-local: ai-privacy, airgap, anthropic-api, apple-silicon. - Also covers LLM Frameworks. - - You need to conduct NDA, legal or healthcare projects that require strict data privacy and airgapping. ## When NOT to use Foundry-Local - Require cloud-based inference services for resource-intensive tasks - Prefer using models not supported by ONNX Runtime or Whisper ## When NOT to use claude-code-local - - If you are not working within the Apple ecosystem as it primarily supports devices running Apple Silicon. - - For workflows where real-time collaboration and cloud-sharing features are integral to your operations, as claude-code-local focuses on local execution. ## Common questions ### What is the difference between Foundry-Local and claude-code-local? Foundry-Local: SDK and CLI for local AI inference with GPU acceleration, supporting speech-to-text models like Whisper.. claude-code-local: Run Claude Code on-device using local AI models for privacy-sensitive workflows.. See the comparison table for live GitHub stats and shared categories. ### When should I choose Foundry-Local over claude-code-local? Choose Foundry-Local over claude-code-local when Foundry-Local is primarily C++; claude-code-local is Python; License: Foundry-Local is Other, claude-code-local is MIT; Pricing: Free to use SDK and CLI under MIT and Microsoft licenses, individual AI models subject to their own license terms.; Tags unique to Foundry-Local: ai-sdk, chat-completions, foundry-local, gpu acceleration; Also covers Speech & Audio; Need to run AI models locally with GPU acceleration. ### When should I choose claude-code-local over Foundry-Local? Choose claude-code-local over Foundry-Local when claude-code-local is primarily Python; Foundry-Local is C++; License: claude-code-local is MIT, Foundry-Local is Other; Pricing: Free to use under the MIT license; premium support or features may incur costs not detailed in the repository.; Requirements: - Needs Apple Silicon hardware.; - Compatible with Python.; Tags unique to claude-code-local: ai-privacy, airgap, anthropic-api, apple-silicon; Also covers LLM Frameworks; - You need to conduct NDA, legal or healthcare projects that require strict data privacy and airgapping. ### When should I avoid Foundry-Local? Require cloud-based inference services for resource-intensive tasks Prefer using models not supported by ONNX Runtime or Whisper ### When should I avoid claude-code-local? - If you are not working within the Apple ecosystem as it primarily supports devices running Apple Silicon. - For workflows where real-time collaboration and cloud-sharing features are integral to your operations, as claude-code-local focuses on local execution. ### Is Foundry-Local or claude-code-local more popular on GitHub? claude-code-local has more GitHub stars (3,193 vs 2,479). Stars measure visibility, not whether either tool fits your constraints. ### Are Foundry-Local and claude-code-local open source? Yes - both are open-source projects on GitHub (Foundry-Local: Other, claude-code-local: MIT). ### Where can I find alternatives to Foundry-Local or claude-code-local? GraphCanon lists graph-backed alternatives at [Foundry-Local alternatives](/tools/microsoft-foundry-local/alternatives) and [claude-code-local alternatives](/tools/nicedreamzapp-claude-code-local/alternatives) ([Foundry-Local markdown twin](/tools/microsoft-foundry-local/alternatives.md), [claude-code-local markdown twin](/tools/nicedreamzapp-claude-code-local/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/microsoft-foundry-local-vs-nicedreamzapp-claude-code-local.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Foundry-Local or claude-code-local? Foundry-Local: Very active. claude-code-local: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for Foundry-Local and claude-code-local? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Foundry-Local trust report](/tools/microsoft-foundry-local/trust); [claude-code-local trust report](/tools/nicedreamzapp-claude-code-local/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-foundry-local`](/api/graphcanon/graph?tool=microsoft-foundry-local) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_