Archive position — measured, not model output
0 likes on Devpost
2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #7,661 place in the like-ranked listing is a tie-break inside that group, not a ranking.
Projects (log scale)
Likes on Devpost. ▲ marks this project's group.
Show the figures
| Likes | Projects | Share of archive |
|---|---|---|
| 0 | 5,592 | 71.2% |
| 1 | 1,758 | 22.4% |
| 2 | 285 | 3.6% |
| 3–4 | 132 | 1.7% |
| 5–9 | 75 | 1.0% |
| 10+ | 14 | 0.2% |
Executive Summary
What the company appears to be
WeAxes CanonGate is a self-reported tool that audits software repositories against explicit requirements using AI-assisted semantic reasoning. It returns PASS, FAIL, or NOT VERIFIED with file-and-line evidence, and is built as a Streamlit application.
What changed
The author reports building a working prototype of a tool that evaluates code repositories for compliance with defined requirements, using GPT-5.6 and structured outputs to validate AI-generated evidence.
Single most important open question
Is there any evidence of real-world usage or adoption beyond the author’s own demo?
What The Product Actually Is
The description states that WeAxes CanonGate is a tool that reviews software repositories against a list of acceptance requirements. It returns one of three results: PASS, FAIL, or NOT VERIFIED. The system uses GPT-5.6 to assess requirements and requires the model to cite file paths, line ranges, and source snippets to support its conclusion.
The author reports that CanonGate validates these citations against the uploaded repository and changes a verdict to NOT VERIFIED if the cited evidence is invalid or missing.
It can be used by uploading a ZIP file or using sample repositories. The output can be downloaded as JSON or Markdown.
Evidence
- The description states: “CanonGate reviews a small source-code repository against a list of acceptance requirements.”
- It returns PASS, FAIL, or NOT VERIFIED.
- GPT-5.6 is used for semantic assessment.
- Citations must include file path, line range, and exact snippet.
- Results are validated by comparing citations to the repository.
Inference The tool appears to be a proof-of-concept application built with Python, Streamlit, and OpenAI APIs, designed to assess code compliance in AI-assisted development workflows.
Positioning & Claim Evolution
The author positions CanonGate as an evidence-first system for auditing software repositories. It is described as a way to avoid relying on statements like “the feature is done” or “the tests are covered,” instead demanding explicit proof within the repository.
Key claims from the description
- “No evidence, no certification.”
- “CanonGate was built to help developers and reviewers check whether a software repository actually contains evidence that specific requirements were implemented.”
- The tool does not execute uploaded code.
- It distinguishes between test source and test execution.
- It is designed to be honest about its limitations.
Evidence
- The author states: “I did not want to rely only on statements like ‘the feature is done’ or ‘the tests are covered.’”
- The system is described as a governance tool for AI-assisted development.
Inference The positioning is that of a lightweight, transparent, and accountable audit tool for developers working in AI-assisted environments. It is not positioned as a full CI/CD replacement but rather as an evidence-checking gate.
Target Customer & ICP
The description does not explicitly name target customers or define an ideal customer profile (ICP). However, it implies that the primary users are developers and reviewers working in AI-assisted development environments.
Evidence
- The author states: “I work with AI-assisted development a lot.”
- It is designed to help “developers and reviewers check whether a software repository actually contains evidence.”
Inference The tool targets developers or teams who want to ensure code compliance and accountability in AI-augmented workflows, especially those working with requirements-based development.
Business Model & Pricing Evidence
There is no evidence of a business model or pricing structure. The project is described as a hackathon submission and a public demo.
Evidence
- The tool is deployed on Streamlit Community Cloud.
- It is presented as a prototype, not a commercial product.
- No mention of monetization, subscriptions, or licensing.
Inference The tool appears to be in early-stage development with no commercial model evident. It may be intended for future monetization or integration into larger platforms.
Technical & Delivery Signals
The project is built using Python 3.12, Streamlit, OpenAI APIs, Pydantic, pytest, and GitHub Actions. It includes automated tests, type checking, code quality checks, and a CI/CD pipeline.
Evidence
- Built with: Python, Streamlit, OpenAI API, GPT-5.6, Pydantic, pytest, Ruff, Mypy, GitHub Actions.
- Uses Codex for implementation.
- Includes automated offline tests, type checking, and deployment via Streamlit Community Cloud.
- Supports ZIP uploads, safe repository ingestion, secret redaction.
Inference The tool is technically sound for a prototype but lacks enterprise-grade features like integration with CI/CD systems or large-scale repository handling.
Traction & Maturity Signals
There is no evidence of traction, revenue, customers, or adoption beyond the author’s own demo. The project is described as a hackathon submission and a public demo.
Evidence
- The tool is deployed on Streamlit Community Cloud.
- It includes sample BEFORE/AFTER repositories.
- The author reports specific results from its own testing (2 PASS, 1 FAIL, 1 NOT VERIFIED in BEFORE; 4 PASS, 0 FAIL, 0 NOT VERIFIED in AFTER).
Inference The tool is at a very early stage of maturity. It has not been tested in real-world environments or integrated into larger workflows.
Competitive Context
There is no evidence of direct competitors or market positioning against other tools. The author does not reference existing solutions for code auditing or AI-assisted development governance.
Evidence
- No mention of competing tools.
- No comparison to existing platforms like SonarQube, CodeClimate, or similar.
Inference The tool may be a niche solution in the AI-assisted development space. It is not positioned against known tools but rather as a new way to enforce evidence-based decision-making.
Key Risks & Red Flags
- No real-world usage or adoption: The tool is only demonstrated by the author.
- Limited scope: It works on small repositories and does not support large-scale CI/CD integration.
- Unverified claims: The system relies heavily on AI-generated evidence, which may be misinterpreted.
- No commercial viability: No pricing, monetization or business model is evident.
Evidence
- The tool is a demo, not a product.
- It does not integrate with GitHub or CI/CD systems.
- No customer data or revenue mentioned.
Inference The project may be a useful concept but lacks traction and commercial viability at this stage.
Diligence Questions To Ask The Founders
- What is the actual use case for this tool in real development workflows?
- Has it been tested with any external teams or organizations?
- How does it handle edge cases like large repositories, binary files, or complex code structures?
- Is there a plan to integrate with CI/CD pipelines or GitHub pull requests?
- What are the long-term goals for scaling and monetization?
Investment/Partnership Verdict
Not evidenced.
The project is described as a hackathon submission and a demo, with no evidence of traction, revenue, or commercial adoption. It is not clear whether it has any strategic value beyond its current prototype form.
Inference At this stage, the tool is more of an idea than a product. It may be worth exploring for future development or integration into larger platforms, but there is no basis for investment or partnership at present.
Source
Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.
The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.