--- title: "conduit vs openpi" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/cogwheel0-conduit-vs-physical-intelligence-openpi" tools: ["cogwheel0-conduit", "physical-intelligence-openpi"] --- # conduit vs openpi *GraphCanon updated Aug 14, 2026* ## Verdict Pick conduit if conduit is an open-source mobile application enabling users on iOS and Android to interface with self-hosted AI services via the OpenWebUI API; pick openpi if openpi is a specialized tool for model training, inference & serving that leverages advanced GPU capabilities and has specific requirements for memory and hardware configurations. [conduit](https://conduit.mobile) reports 1.9k GitHub stars, 193 forks, and 63 open issues, last pushed Aug 10, 2026. [openpi](https://github.com/Physical-Intelligence/openpi) has 13k stars, 2.3k forks, and 316 open issues, last pushed Jun 16, 2026. Figures are from public GitHub metadata via [conduit's repository](https://github.com/cogwheel0/conduit) and [openpi's repository](https://github.com/Physical-Intelligence/openpi). | | [conduit](/tools/cogwheel0-conduit.md) | [openpi](/tools/physical-intelligence-openpi.md) | | --- | --- | --- | | Tagline | Mobile client for OpenWebUI | Repository for running AI models with GPU requirements specified. | | Stars | 1,945 | 13,098 | | Forks | 193 | 2,276 | | Open issues | 63 | 316 | | Language | Dart | Python | | Adopt for | Conduit is an open-source mobile application enabling users on iOS and Android to interface with self-hosted AI services via the OpenWebUI API. | openpi is a specialized tool for model training, inference & serving that leverages advanced GPU capabilities and has specific requirements for memory and hardware configurations. | | Persona | - | - | | Runtime | - | - | | License | GPL-3.0 License | Apache-2.0 | | Categories | Inference & Serving, LLM Frameworks | Inference & Serving, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [conduit](/tools/cogwheel0-conduit.md) | [openpi](/tools/physical-intelligence-openpi.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 3d | 46d | | Open issues (now) | 63 | 316 | | Stars delta | +157 (30d) | Unknown | | Open issues delta | +10 (30d) | Unknown | | Owner type | User | Organization | | Full report | [trust report](/tools/cogwheel0-conduit/trust.md) | [trust report](/tools/physical-intelligence-openpi/trust.md) | ## Decision facts: conduit - **Requirements:** - The application requires a recent Flutter SDK with Dart version 3.9 or newer.; - For building on Android, Java 17 and Android 7.0+ (API level 24) are necessary requirements.; - On iOS, the application supports only devices running iOS 16.0+. Xcode is required for builds. - **Adopt for:** Conduit is an open-source mobile application enabling users on iOS and Android to interface with self-hosted AI services via the OpenWebUI API. - **License detail:** GPL-3.0 License ## Decision facts: openpi - **Adopt for:** openpi is a specialized tool for model training, inference & serving that leverages advanced GPU capabilities and has specific requirements for memory and hardware configurations. ## Choose when ### Choose conduit if… - conduit is primarily Dart; openpi is Python. - License: conduit is GPL-3.0, openpi is Apache-2.0. - Requirements: - The application requires a recent Flutter SDK with Dart version 3.9 or newer.; - For building on Android, Java 17 and Android 7.0+ (API level 24) are necessary requirements.; - On iOS, the application supports only devices running iOS 16.0+. Xcode is required for builds.. - Tags unique to conduit: mobile, ollama, openwebui, selfhosted. - Also covers LLM Frameworks. - - You are using a self-hosted AI service compatible with OpenWebUI, OpenAI APIs, or Ollama endpoint, and require a mobile interface for it. ### Choose openpi if… - openpi is primarily Python; conduit is Dart. - License: openpi is Apache-2.0, conduit is GPL-3.0. - Tags unique to openpi: fine-tuning, lora, model parallelism, nvidia gpu. - Also covers Model Training. - When you have an NVIDIA GPU with at least 8 GB of VRAM for inference or at least 22.5 GB to fine-tune models using LoRA (Low-Rank Adaptation) on a single GPU. ## When NOT to use conduit - - If you aim to use proprietary AI services that do not offer OpenAI-compatible APIs or are not compatible with the endpoints supported by Conduit. - - Your development setup does not include Flutter SDK with Dart 3.9 or newer, Java 17 for Android builds, and Xcode or Android Studio. ## When NOT to use openpi - When your project is not compatible with Ubuntu 22.04 or if you do not have access to a supported GPU configuration. - If you need to support multi-node training, as this capability has yet to be implemented in the current version of openpi. ## Common questions ### What is the difference between conduit and openpi? conduit: Mobile client for OpenWebUI. openpi: Repository for running AI models with GPU requirements specified.. See the comparison table for live GitHub stats and shared categories. ### When should I choose conduit over openpi? Choose conduit over openpi when conduit is primarily Dart; openpi is Python; License: conduit is GPL-3.0, openpi is Apache-2.0; Requirements: - The application requires a recent Flutter SDK with Dart version 3.9 or newer.; - For building on Android, Java 17 and Android 7.0+ (API level 24) are necessary requirements.; - On iOS, the application supports only devices running iOS 16.0+. Xcode is required for builds.; Tags unique to conduit: mobile, ollama, openwebui, selfhosted; Also covers LLM Frameworks; - You are using a self-hosted AI service compatible with OpenWebUI, OpenAI APIs, or Ollama endpoint, and require a mobile interface for it. ### When should I choose openpi over conduit? Choose openpi over conduit when openpi is primarily Python; conduit is Dart; License: openpi is Apache-2.0, conduit is GPL-3.0; Tags unique to openpi: fine-tuning, lora, model parallelism, nvidia gpu; Also covers Model Training; When you have an NVIDIA GPU with at least 8 GB of VRAM for inference or at least 22.5 GB to fine-tune models using LoRA (Low-Rank Adaptation) on a single GPU. ### When should I avoid conduit? - If you aim to use proprietary AI services that do not offer OpenAI-compatible APIs or are not compatible with the endpoints supported by Conduit. - Your development setup does not include Flutter SDK with Dart 3.9 or newer, Java 17 for Android builds, and Xcode or Android Studio. ### When should I avoid openpi? When your project is not compatible with Ubuntu 22.04 or if you do not have access to a supported GPU configuration. If you need to support multi-node training, as this capability has yet to be implemented in the current version of openpi. ### Is conduit or openpi more popular on GitHub? openpi has more GitHub stars (13,098 vs 1,945). Stars measure visibility, not whether either tool fits your constraints. ### Are conduit and openpi open source? Yes - both are open-source projects on GitHub (conduit: GPL-3.0, openpi: Apache-2.0). ### Where can I find alternatives to conduit or openpi? GraphCanon lists graph-backed alternatives at [conduit alternatives](/tools/cogwheel0-conduit/alternatives) and [openpi alternatives](/tools/physical-intelligence-openpi/alternatives) ([conduit markdown twin](/tools/cogwheel0-conduit/alternatives.md), [openpi markdown twin](/tools/physical-intelligence-openpi/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/cogwheel0-conduit-vs-physical-intelligence-openpi.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, conduit or openpi? conduit: Very active. openpi: Steady. 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 conduit and openpi? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [conduit trust report](/tools/cogwheel0-conduit/trust); [openpi trust report](/tools/physical-intelligence-openpi/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=cogwheel0-conduit`](/api/graphcanon/graph?tool=cogwheel0-conduit) - 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/_