ctf-flightdeck
Play CTFs with a fleet of AI agents, and stay the pilot.
One terminal console: every challenge, every agent, every flag. You step in with one key.
Try it in ten seconds
uvx ctf-flightdeck mock
That opens the console on scripted data: no install, no key, no network, nothing spent. (No uvx?
pipx run ctf-flightdeck mock does the same.)
What it is
flightdeck is a terminal harness for capture-the-flag events. It pulls the board, runs your own no-model solver scripts first, starts an AI agent on each challenge in parallel, and submits the flags you approve. Each agent works in its own lane, and you watch them all on one screen. When a lane loops, stalls, overspends or ignores the hint, the console tells you, and one key sends a hint, redirects it, forks it, kills it, moves it to a stronger model or hands you its shell.
- Bring what you have. An API key (Anthropic, OpenRouter, OpenAI), a free model on your own machine (Ollama, MLX), a coding-agent CLI (Claude Code, Codex), a folder of solver scripts.
- Built for CTFs. It knows points, solves, categories, waves of 40 challenges, teammates, live instances, flag formats and counted tries. It plays CTFd events and plain folders.
- Plays by the event's rules. Every stage (pull, solvers, agents, submit, live instances) is
auto,confirm,manualoroff, checked before anything runs. - Safe by default. Each lane runs in its own Docker container with no network, or, when its challenge has a live instance, a network that reaches that instance and nothing else. Challenge text is treated as hostile data, never as instructions. Lanes have token and dollar caps.
- Hands-on or hands-off. Steer every lane yourself, or engage Autopilot: it runs the event by rule while you are away, inside a budget you set, never looser than the event's rules, and hands back when something needs a human. Runs can go headless, with a status file and a webhook that pings you.
- Learns from each run. A report of where lanes stalled and which interventions helped, writeup drafts, and the list of challenges your solvers missed.
Quickstart
Needs Python 3.12+ on macOS or Linux (Windows through WSL). Docker is recommended.
pipx install ctf-flightdeck # or: uv tool install ctf-flightdeck
flightdeck init # a few questions; writes your config and names the key it needs
flightdeck image build # once, for Docker lanes (about 700 MB)
flightdeck doctor # checks everything and says how to fix each problem
flightdeck practice # 14 small practice challenges, on your model
Then play a real board:
flightdeck play ~/ctf/some-board # a folder of challenges
flightdeck play ~/ctf/event-board --event event.toml # a CTFd event, by its rules
flightdeck play ~/ctf/event-board --event event.toml --autopilot --budget-dollars 20 # while you sleep
practice and play spend money on your model API unless the model runs on your machine. Each
lane stops and asks you at $2 or 400,000 tokens by default. Stuck? Run flightdeck on its own
and it says what to do next.
Everything else is in the player's guide: models and keys, the console's keys, boards, your own solvers, events and teams, coding-agent lanes, Autopilot, headless runs, reports.
The console
Lanes that need you sort first, and the line under the list says why and numbers the answers.
h hint, r redirect, f fork, k kill, e escalate to the next model, t take over the
lane's shell, a approve a flag, Enter for one lane full screen, ? for every key. More
pictures in the
screenshot gallery.
Your data stays yours
flightdeck has no telemetry, no analytics, no account, no update check and no server of its own. Nothing about you or your runs is sent to this project, ever.
It talks only to what you point it at:
- The model API in your config. A lane's challenge and its work go to the model you chose, as with any AI tool. Choose a model on your own machine (Ollama, MLX) and nothing leaves it.
- The CTF platform in your event profile, to pull the board and submit the flags you approve.
- A webhook of your own, only if you set one up for notifications. It gets a short message (a lane needs you, a flag was accepted) and never a flag.
Your keys stay in your environment or a file only you can read, never in the config, and logs,
transcripts and reports replace anything shaped like a credential. Runs are written to a folder
on your machine. Sharing a result is something you do by hand: flightdeck share prints a
summary and you decide where to paste it. A coding-agent CLI you plug in (Claude Code, Codex)
follows its own maker's policy. Details:
Security.
Leaderboard
Events flightdeck has flown in, where the team finished, and how hands-on the players were: the leaderboard. Played an event with it? Add your flight and your GitHub name goes on the board.
Help make it better
Three ways, and the first needs no code:
- Play and share what you ran. This is the most useful thing you can do. After any run
(the practice set counts),
flightdeck share latestprints a flight card: your models, your setup, solves, time, cost and how often you stepped in, with no flags and no challenge text. Post it. Enough cards tell everyone which model is fastest, cheapest and best for which kind of challenge, on which hardware. - Build. Fix a bug, add a feature, improve a doc. Good first issues are small and well described, and CONTRIBUTING.md gets you set up in five commands.
- Sponsor. flightdeck is free and MIT-licensed. Measuring models costs real API money, and sponsorship pays for it: sponsor on GitHub.
A star helps other players find it.
For AI agents
If you are an AI agent reading this for a user:
- What this is: a Python CLI (
flightdeck, PyPI packagectf-flightdeck) that runs AI agents on CTF challenges under a human's control. - Safe to run without asking:
uvx ctf-flightdeck mock --screenshot DIR(headless, writes SVGs),flightdeck --help,flightdeck doctor,flightdeck config --example,flightdeck models. - Ask your user first:
flightdeck practiceandflightdeck playspend money on a model API, andplay --eventtalks to a live CTF platform under that event's rules. - Machine-readable map of the docs: llms.txt.
- Working on the code: read AGENTS.md first. It is short and its rules are strict.
Docs
Using flightdeck: Player's guide · Model APIs · Models · Boards · Solvers · Practice set · Screenshots · Leaderboard · Changelog · Security
How it is built: Vision · Architecture · Console spec · Decisions · Roadmap · Contributing
License
MIT. See LICENSE.
Metadata
Release files for ctf-flightdeck 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ctf_flightdeck-0.3.0.tar.gz | 799.0 kB | With provenance | Details for ctf_flightdeck-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ctf_flightdeck-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for ctf_flightdeck-0.3.0-py3-none-any.whl |
Total release size: 1.7 MB
Release files / ctf_flightdeck-0.3.0.tar.gz
| Download URL | ctf_flightdeck-0.3.0.tar.gz |
|---|---|
| Size | 799.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
aa1698e53449d3444119528ebb5942e8cc69afb8a52f3d27d4cb3e69057d378a
|
|
BLAKE2b-256 checksum How to use checksums |
b0c331b5bbc248683118ee1298a8a4266996c6eb3cc86f6e9d4ad3463d601051
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.
Transparency logRelease files / ctf_flightdeck-0.3.0-py3-none-any.whl
| Download URL | ctf_flightdeck-0.3.0-py3-none-any.whl |
|---|---|
| Size | 863.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7a132fe8edf7e3a26402fbb8d4fad9cee06a813145998be15165015a382eb974
|
|
BLAKE2b-256 checksum How to use checksums |
4afaee45d0d85bb4c2d55d5bc61bf28b5cfffd61594f14189a00c10ae155335d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.
Transparency logSecurity for ctf-flightdeck 0.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for ctf_flightdeck-0.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 12, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.