The Agent Harness Hackathon

Rules

Everything you're held to

Read these before you start building. Registering for The Agent Harness Hackathon means agreeing to all of them, along with the WeMakeDevs Code of Conduct.

1. 1.

   You can take part online from anywhere in the world, and it costs nothing to enter. If you're in San Francisco on August 29, you can also spend the day building in the room.^*

2. 2.

   You can participate solo or in a team of up to 4 members. Each participant may only be part of one team.

3. 3.

   Required technology: your agent must run on TrueForge, the open-source agent harness. A judge has to be able to see the harness doing real work rather than sitting under a thin wrapper around a model call.

4. 4.

   Code review is part of the build. To be considered for the Double-O and Q Branch tracks, every substantive change has to go through a GitHub pull request reviewed by Qodo before it is merged, whether you are solo or in a team. Direct pushes to main do not count as reviewed work.^**

5. 5.

   Beyond that the challenge is open-ended. Build a developer tool, an internal assistant, a research desk, an incident responder, a data pipeline, or anything else worth handing to an agent, in any domain you like.

6. 6.

   Your submission must be open source. Judges have to be able to read the code and run it.

7. 7.

   Anything your agent touches has to be yours to touch. Connect tools, data, and accounts you own or have permission to use, and keep private, personal, and login-protected information out of your repo and your demo.

8. 8.

   The project has to be built during the hackathon. You may discuss ideas, take notes, plan the architecture, or prepare diagrams beforehand, but the coding and design work itself has to happen between the 8:00 AM London start on August 24 and the deadline.

9. 9.

   You may use frameworks, open-source libraries, public APIs, templates, third-party tools, and publicly available assets. The original work completed during the hackathon is what gets judged.

10. 10.

    Every submission must include:^***

    • A public source-code repository
    • A clear README with setup steps
    • A demo video of about three minutes showing the agent working
    • A short write-up of what the agent does and how it uses TrueForge
    • For the Double-O and Q Branch tracks, a "## Qodo Code Review Evidence" section in the README: a link to at least one representative merged pull request containing meaningful hackathon code, one or two sentences on what Qodo surfaced and what you changed or intentionally dismissed, and a pull request history showing the completed review, your decisions, and a follow-up review against the final code
    • A link to your blog post, if you're entering that prize
11. 11.

    Submissions close on August 30 at 8:00 PM London time, and the schedule page shows that deadline in your own timezone.

12. 12.

    AI coding assistants are allowed, but their use must be disclosed.

13. 13.

    Participants must understand the submitted code and be able to explain the agent, the project architecture, and the technical decisions behind it.

14. 14.

    Projects that are entirely generated using AI without meaningful participant contribution, verification, or technical understanding may be rejected.

15. 15.

    There are three judged tracks: Best Use of TrueForge, Best Code Quality, and Best UI. One team can only take one of them. Best Use of TrueForge and Best Code Quality award one prize to the winning team, and only projects built through Qodo-reviewed pull requests are considered for them; Best UI awards an iPad to every member of the winning team. Best Code Quality is judged on that Qodo review trail.

16. 16.

    The blog post prize goes to one writer: publish your write-up anywhere you like and add the link to your submission. Swag goes to ten participants who share their build publicly and tag WeMakeDevs and TrueFoundry.

17. 17.

    Everyone who submits a project that meets these rules gets a certificate of participation by email after judging, whether or not they win a track.

18. 18.

    Separately from the tracks, TrueFoundry offers a job interview to the teams behind the top projects. There is nothing to apply for: the judges pass those names on once the results are in. Winning a track is neither a condition of being on that list nor a guarantee of a place on it.

19. 19.

    Any intellectual property developed during the hackathon belongs to the participant or team that created it. Teams are encouraged to agree internally on ownership before submitting.

20. 20.

    Treat participants, organisers, sponsors, speakers, judges, and community members with respect.

21. 21.

    Harassment, discrimination, plagiarism, or attempts to manipulate the judging process will result in disqualification.

22. 22.

    Failure to follow these rules or the WeMakeDevs Code of Conduct may result in disqualification.

• *The live day has limited space and takes a registration of its own on Luma. Everyone who turns up gets $50 in OpenAI credits; online participants bring their own model API key.
• **One installation per team is enough, and teammates do not need Qodo accounts of their own. Fix every valid High-severity finding, or dismiss it in the Qodo thread with a reason; Medium and Low findings are your engineering call. Qodo supports the review, and your team still owns the merge.
• ***The public pull request link is the required evidence. Screenshots may add context, but they cannot replace it. Judges may inspect other substantive merges to confirm that Qodo review was part of the build rather than a one-time submission step.

Disclaimer: The Agent Harness Hackathon is an independent developer hackathon organised by WeMakeDevs in collaboration with TrueFoundry. It is not affiliated with, endorsed by, or associated with the James Bond films or novels, Eon Productions, Danjaq, Metro-Goldwyn-Mayer, or any of their rights holders. The theme is used purely for creative purposes.