DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Code AF

CodeAF is an open-source Go coding harness for open models that runs as one local binary, with specialist subharnesses for coding, security audits and pull request reviews.

Trended earlier

Agent-Field/CodeAF on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

5 use cases

  • Audit local code changes for security problems

    Run the sec specialist on changes since main and get findings with evidence and fixes.

    View prompt
    Use the CodeAF repo at Agent-Field/CodeAF. Install it with its curl script, open the git repository at <project-path>, and run `/sec changes since main` in the chat. Expected output: a security report with findings, evidence and suggested fixes, in Markdown, JSON or SARIF. Verify that the report lists its coverage and any incomplete analysis, and that your source files were not modified.

  • Review a GitHub pull request with findings and reasons

    Run the review specialist on a PR and get findings with file locations and fixes.

    View prompt
    Use the CodeAF repo at Agent-Field/CodeAF. After installing it, run `/review <owner>/<repo>#<number> focus on retries` in the chat. Expected output: a review report with findings, file locations, reasons, suggested fixes and coverage, in Markdown or JSON. Verify that the code was not changed and that the coverage section lists what was not analyzed.

  • Hand a coding fix to senior-dev on its own branch

    Describe a bug and let senior-dev change code in a private copy, then check the results.

    View prompt
    Use the CodeAF repo at Agent-Field/CodeAF. Install it, open the git repository at <project-path>, and run `/senior-dev <describe the bug and tests>`. Expected output: a submitted change on its own branch with build and test results. Verify that your working branch and main were not changed and that the reported test results match a local run.

  • Run a batch of coding tasks headless in CI or cron

    Use codeaf do with a timeout and JSON output to run unattended work from scripts.

    View prompt
    Use the CodeAF repo at Agent-Field/CodeAF. In a CI job for <repo-path>, run `codeaf do "<brief>" --timeout 30m --json`. Expected output: one JSON object and an exit code. Verify the JSON result and exit code match the work that landed on the branch, and that the job fails when the exit code is nonzero.

  • Drive a coding agent on a remote dev box from your laptop

    Run the conversation on a remote machine with codeaf chat --host and keep the work going.

    View prompt
    Use the CodeAF repo at Agent-Field/CodeAF. Install it on a dev box named <host> and on a laptop, then run `codeaf chat --host <host>` from the laptop. Expected output: the live conversation of the dev box in the local terminal. Verify that a task started on the dev box keeps running after the laptop disconnects and that its result is visible on reconnect.

How to use Code AF

  1. Check you have what it needs: macOS or Linux machine with a terminal; A provider key (OpenRouter, DeepSeek, GLM, Kimi, MiniMax, Qwen), a ChatGPT plan through Codex, or a running Ollama install; A git repository for the project you want to work on.
  2. Open Agent-Field/CodeAF on GitHub and read the README and license.
  3. Run curl -fsSL https://agentfield.ai/get/codeaf | bash and then codeaf.
  4. Connect a provider on first start, in the browser through OpenRouter or with a key.
  5. Open the project's folder in Code AF and type /sec changes since main.
  6. Open the sec task to follow the work, then read the findings and the coverage notes in the report.

These steps come from our top use case, Audit local code changes for security problems, which also has a copy-paste agent prompt.

Code AF alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forSoftware developers and teams who want to run coding, review and audit work with open models from one local window or a headless command.
  • Why it is hot
  • LanguageGo
  • Sourcegithub.com/Agent-Field/CodeAF · Back to Hot repos

Requirements

  • macOS or Linux machine with a terminal
  • A provider key (OpenRouter, DeepSeek, GLM, Kimi, MiniMax, Qwen), a ChatGPT plan through Codex, or a running Ollama install
  • A git repository for the project you want to work on
  • Install CodeAF with the curl script, or build it from source with make build
Maintain Code AF? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/agent-field-codeaf.svg)](https://dedupedai.com/use-cases/agent-field-codeaf/?ref=badge)

More badge styles and HTML

Questions about Code AF

What is Code AF?

CodeAF is an open-source Go coding harness for open models that runs as one local binary, with specialist subharnesses for coding, security audits and pull request reviews. It is an open-source project on GitHub: https://github.com/Agent-Field/CodeAF.

Who is Code AF for?

Software developers and teams who want to run coding, review and audit work with open models from one local window or a headless command.

What can I do with Code AF?

5 use cases so far, for example: Audit local code changes for security problems; Review a GitHub pull request with findings and reasons; Hand a coding fix to senior-dev on its own branch. Each has steps and a copy-paste agent prompt.

What do I need to run Code AF?

macOS or Linux machine with a terminal; A provider key (OpenRouter, DeepSeek, GLM, Kimi, MiniMax, Qwen), a ChatGPT plan through Codex, or a running Ollama install; A git repository for the project you want to work on; Install CodeAF with the curl script, or build it from source with make build.

What are alternatives to Code AF?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Code AF safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.