StrideOS

StrideOS is a self-reported training plugin for ChatGPT and Codex that claims to help runners plan, manage, and execute their training using LLMs. The author states it was built during OpenAI Build Week and is structured as a .codex-plugin package with six skills, designed to be installed in ChatGPT Work mode or Codex. It integrates with wearable devices (via imports) and supports human review through a "Training Circle" feature. The plugin is described as open-source under an MIT license and includes a local-first Node.js reference runtime and PWA for inspection.

The project appears to be a prototype or proof-of-concept, not yet commercially deployed or validated in the market. It does not show evidence of revenue, customers, or traction beyond its own description. The author's claims about functionality, integration capabilities, and user experience are self-reported and unverified.

The description states that StrideOS is a training plugin for ChatGPT and Codex, built during OpenAI Build Week. It is described as a .codex-plugin package with six skills, structured to support:

• Onboarding athletes conversationally
• Combining wearable or provider evidence with athlete check-ins
• Proposing running and strength plans based on goals, experience, schedule, and recovery
• Explaining uncertainty and asking before activating changes
• Supporting optional fueling guidance
• Preparing coaching rhythms (morning, pre-workout, post-workout, weekly)
• Building a "Training Circle" where coaches or friends can review and suggest edits

The plugin is said to work alongside existing athlete accounts and not handle login credentials directly. Actions are previewed and require approval before execution.

Evidence The description states this is a six-skill ChatGPT Work and Codex plugin, built with Codex, using GPT-5.6, and includes six SKILL.md modules.

Inference It appears to be a prototype or MVP, not yet commercially launched or used by end-users.

The author claims that StrideOS is designed to make training feel more natural and customizable, using LLMs. It positions itself as an AI-powered tool that helps runners plan and manage their training in a way that adapts to individual needs, schedules, and recovery patterns.

It also claims to be deeply personal—no two runners need the same plan or feedback loop—and supports customization by the athlete or their agent. The plugin is described as installable, open-source, and validated through a .codex-plugin package.

The project evolved from the author's personal experimentation with AI coaching tools, leading to a structured solution that can be shared and used by others.

Evidence The description states it was built during OpenAI Build Week, is installable as a plugin, and is open-source under MIT license.

Inference The positioning suggests a niche product for runners who are tech-savvy or early adopters of AI tools. It does not appear to target mainstream or commercial adoption yet.

The description states that StrideOS is intended for runners, particularly those looking for customizable, personal training plans. It claims to support athletes who want:

• A structured training profile
• Integration with wearables (via imports)
• Coaching rhythms and feedback loops
• Human review through a “Training Circle”

It does not explicitly define a细分 customer segment beyond runners or specify whether it targets amateur, semi-professional, or elite athletes.

Evidence The description says it helps runners plan, manage, and execute training using LLMs and integrates with wearables.

Inference The ICP appears to be tech-savvy runners, possibly early adopters of AI tools, who value customization and personalization in their training.

There is no evidence in the description of a business model or pricing structure. The project is described as open-source under an MIT license, and the author mentions that it was built for a hackathon.

Evidence The project is described as open-source with an MIT license, and no mention of monetization or pricing.

Inference No commercial model is evident. It may be intended for personal use or future monetization, but there is no indication of how this would work.

The project was built using Codex, GPT-5.6, and JavaScript/Node.js, with support for PWA and a local-first Node.js reference runtime. It includes:

• Six SKILL.md modules
• UI metadata
• An icon
• MIT license
• Synthetic data for testing
• Browser verification
• A zero-setup judge mode

The plugin is said to separate reasoning, evidence, permission, and execution using deterministic policies outside the model.

Evidence The description states it was built with Codex, uses GPT-5.6, and includes a reference runtime, PWA, and synthetic data for testing.

Inference It shows technical sophistication in structuring AI workflows and managing permissions, but lacks evidence of production deployment or scalability.

There is no evidence of traction, revenue, or customer adoption. The project is described as a hackathon submission, built during OpenAI Build Week, and is open-source.

Evidence The project was submitted to the OpenAI 2026 hackathon and is described as a prototype.

Inference No signs of market traction or commercial maturity are evident. It appears to be in early development or proof-of-concept stage.

The description does not mention any competitors or direct market positioning against other training tools or AI coaching platforms. The author does not reference existing apps, platforms, or services for running training or coaching.

Evidence No mention of competitors or similar products is present in the description.

Inference It is unclear whether StrideOS competes with existing platforms like Strava, TrainingPeaks, or other AI-powered coaching tools. The project may be a new entry into a crowded space, but no evidence supports this.

• No commercial traction or revenue — the project is described as a hackathon submission and open-source prototype.
• Unverified claims — all functionality and features are self-reported without independent validation.
• Limited scope — the plugin is built for ChatGPT and Codex, limiting its reach to users of those platforms.
• No evidence of user feedback or testing beyond author’s own use — no third-party adoption or usage data.
• Unclear path to monetization — no business model or pricing structure is evident.

Evidence The project is open-source, built for a hackathon, and lacks any commercial or customer data.

Inference The risk of misalignment between the author’s vision and real-world use cases is high. The product may not be ready for market adoption.

1. What specific user feedback has been gathered from runners who have tested StrideOS beyond your own use?
2. How does StrideOS handle data privacy, especially with regard to wearable data and personal health information?
3. Are there any plans for integrating with mainstream running platforms or wearables (e.g., Garmin, Strava)?
4. What is the long-term vision for monetization or commercial deployment of this tool?
5. Can you provide evidence of how the plugin performs in real-world scenarios beyond synthetic testing?