The Agent Harness Hackathon: give AI models a license to act. August 22 to 30, 2026, with an NVIDIA DGX Spark and a Mac Mini among the prizes

Sponsored by TrueFoundry · Hosted by WeMakeDevs

The Agent Harness Hackathon

Give AI models a License to act

You get an agent working in an afternoon. Then you point it at something that matters and it can't reach your tools, can't run its own code safely, and can't be stopped before it does damage. Build one that can do all three, on TrueForge, TrueFoundry's open-source agent harness.

Register nowSee the prizes

Mission dossier

File TF-007

When
August 22–30, 2026
Where
Take part ONLINE from anywhere, or join us in SF
Teams
Solo or up to 4 people
Prizes
$10,000 in prizes, include an NVIDIA DGX Spark, a Mac Mini, and more

01 / Prizes

Incredible Prizes

Two judged tracks, each backed by a sponsor, and two prizes open to everyone taking part. Nothing to pick when you enter.

Grand prize · Double-O trackPresented by TrueFoundry

NVIDIA DGX Spark

Personal AI supercomputer

Prize value

$5,000

To the winning team

Best Use of TrueForge

For the agent that gets the most out of the harness: real tools connected through MCP, generated code running in a sandbox, a pause for human approval before anything irreversible, work handed to subagents, a session that holds together across reconnects. Any domain, any use case. What matters is that the harness is doing the work rather than sitting underneath a thin wrapper.

The NVIDIA DGX Spark personal AI supercomputer awarded for the best use of TrueForge

Q Branch trackPresented by Qodo

The Mac Mini awarded for the best code quality

Mac Mini

To the winning team

Best Code Quality

For the team that treats a hackathon repo like real software. Run your pull requests through Qodo, deal with what it surfaces before you merge, and ship something a stranger could clone, understand, and extend. Using Qodo is required to win this track.

Field reportOpen to everyone

The Keychron keyboard awarded for the best blog post

Keychron Keyboard

To one writer

Best blog post

Write up what you built: the job you gave the agent, how you wired it up, what TrueForge handled for you, what broke along the way. Screenshots and a demo clip help. Publish it anywhere and add the link to your submission.

Calling cardOpen to everyone

The Logitech MX Master 3 drawn at random from everyone who stars the TrueForge repo

Logitech MX Master 3

To one villain

Star the TrueForge repo

Nothing to build for this one. Star TrueForge on GitHub and you are in the draw: one entry each, one name pulled out at random after submissions close. It is also the easiest way to keep an eye on what lands in the repo during the week.

The swag awarded for the ten best social posts

Radio trafficOpen to everyone

Swags

To ten of you

Top 10 social posts

Share what you are building while you build it: a clip of the agent working, a thing that surprised you, a bug that took an hour. Tag WeMakeDevs and TrueFoundry so we can find it.

02 / The challenge

A chatbot answers questions. An agent acts on them.

It opens the pull request, queries the database, runs the script. Acting is the hard part, because it takes three things a chat window never needed.

A TrueForge session

Illustration

Investigate the payment-failures alert. Roll back if a deploy caused it.

grafana · error rate by service (MCP)

sandbox · bisect the last four deploys

cause found · deploy 4c21 doubled checkout timeouts

Rollback is irreversible. Holding for your approval.Licence required

Approved by you · 4c21 rolled back

error rate recovering · session logged

The loop, the tool calls, the sandbox, and the pause are all the harness. You wrote one line of it.

  • A way to reach your systems

    Your GitHub, your database, your internal tools, your calendar. Connected, not mocked.

  • A safe place to run what it writes

    Generated code has to execute somewhere that cannot damage anything if it is wrong.

  • A way to stay in control

    It should stop and ask a person before doing anything you cannot undo.

The layer that sits between the model and everything it touches, and handles all three, is called an agent harness. TrueForge is an open-source one, so you spend the week on the actual problem instead of building the machinery around it. The domain is yours: pick a job worth handing to an agent, in any field you like, and build the agent that does it.

03 / Sponsors

The harness, the reviewer, and the credits

TrueFoundry builds the harness every submission runs on. Qodo reviews the code. OpenAI covers the experiments in the room.

TrueFoundry

Main sponsor

TrueFoundry builds the infrastructure companies use to run AI in production, across any model and any cloud, in their own environment. TrueForge is its open-source agent harness: the runtime layer around a model that turns it into a working agent, and the thing every submission this week runs on.

Drive it three ways: a chat UI, an HTTP API, or a TypeScript library. Open source, no account required.

Star TrueForge on GitHubMeet TrueFoundry

Once an agent is running for real users, TrueFoundry's AI Gateway and MCP Gateway answer what it costs, what it did, and what it is allowed to touch. Neither is needed for this hackathon.

  • Connects to your tools

    Any MCP server, including ones behind OAuth, plus 40+ built-in tools and web search.

  • Runs code safely

    Agent-written code executes in an isolated sandbox.

  • Waits for a human

    Pauses before sensitive actions until a person approves.

  • Delegates

    Subagents take on parts of a job.

  • Survives reconnects

    Sessions keep running through a refresh, a reconnect, or a server restart.

  • Runs on any model

    OpenAI, Anthropic, Gemini, DeepSeek, or any OpenAI-compatible endpoint, switchable from the UI.

  • Loads Skills

    Reusable instruction packs the agent picks up when a task calls for them.

  • Scales when you do

    A single process on SQLite on your machine; multiple replicas on Postgres and Redis.

Qodo

Code review partner

Qodo is an AI code review platform. It reviews every pull request with agents that read your full codebase rather than just the diff, flags real bugs, breaking changes, and rule violations, ranks findings by severity, and can apply the fix. It runs in your IDE, on your pull requests, and from the CLI.

Nine days is long enough to accumulate the kind of mess that makes a repo unreadable, and an open-source project only gets picked up if it is worth picking up. Qodo backs the Best Code Quality track, and using it is required to win that one.

Try Qodo
OpenAI

Model partner

OpenAI is providing $50 in credits to everyone who joins in person in San Francisco on August 29, so you can experiment on the day without paying for it.

Taking part online? Bring your own key. TrueForge runs on any provider, so you are free to use OpenAI, another provider, or a local model.

04 / Ideas

Start from one of these, or bring your own

The theme is open-ended. Build in any category, as long as TrueForge is running the agent.

  • Code review agent

    Reads a pull request, runs the test suite in a sandbox, and comments on what it found.

  • Incident responder

    Investigates an alert with read-only queries, then asks a person before restarting or rolling anything back.

  • Analytics agent

    Answers questions in plain English by writing the SQL itself, running it, and explaining the result.

  • Research desk

    Sends subagents across the web on a single question and merges what they find, with sources.

  • Approval-gated assistant

    Drafts the email, files the ticket, or books the trip, and does nothing irreversible until you approve it.

  • Untrusted code runner

    Executes code submitted by someone else inside an isolated sandbox and returns the result safely.

05 / Judging

What the judges are looking for

Six criteria, weighted equally. The demo is scored as hard as the code.

  1. Potential impact

    Does the agent do a clear, useful job someone would actually hand over?

  2. Creativity and originality

    Is this an inventive job to give an agent, or an inventive way of doing it?

  3. Technical excellence

    Is the implementation complete, reliable, and well structured?

  4. Use of TrueForge

    Is the harness central to the project, or a thin wrapper around a model?

  5. Control and safety

    Does the agent run its code somewhere safe and stop for a human before anything irreversible?

  6. Presentation

    Does the demo clearly explain the problem, the agent working, and where the harness fits?

06 / FAQ

Got questions?

Is it free?

Yes. Taking part costs nothing, online or in person.

Can I build with a team?

Solo or up to four. You can find teammates in the TrueFoundry Discord. Join the TrueFoundry Discord.

How do I submit?

Through this site by August 30 at 8:00 PM San Francisco time: a public repo, a demo video of about three minutes, and a short write-up of what your agent does and how it uses TrueForge. The schedule page shows that deadline in your own timezone.

What does "must run on TrueForge" mean?

Your agent runs through the TrueForge harness and a judge can see it doing real work. Beyond that, build anything.

Does my submission have to be open source?

Yes. Submit a public repo that judges can read and run.

Can I use code I already have?

Not as the project itself: the build has to happen during the nine days. Libraries, frameworks, public APIs, and AI coding tools are all fine.

Do I need my own model API key?

Yes, unless you join in San Francisco, where OpenAI is providing $50 in credits. TrueForge works with any provider.

Do I have to use Qodo?

Only if you want to win the Best Code Quality track.

Can one team win more than one track?

No. Every submission is considered for both, but a team can only take one.

Do I need experience with agents?

No. TrueForge handles the runtime, so you can have something working quickly.

What should I bring on the 29th?

A laptop, a charger, and ID for venue entry. Food and Wi-Fi provided.

Where do I get help?

The TrueFoundry Discord during the event, or GitHub issues on the repo. Open the TrueForge repo.

Also on · San Francisco

The week runs online from anywhere, and on August 29 it also runs in a room. Spend the day building alongside the TrueFoundry team in San Francisco, with $50 of OpenAI credits for everyone who turns up. Space is limited and the day takes a registration of its own.

Join us on Luma

Nine days · Submissions close August 30, 8:00 PM San Francisco time

Build the agent you would trust with root.

Registration is open now. The week runs online from August 22, and the room in San Francisco is there on the 29th if you want it.

Register nowJoin the TrueFoundry Discord

End of briefing

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.