Frontier-grade coding on open models, at a fraction of the cost.
CodeAF is a coding harness built for open models, to get the most out of every
dollar. It is also a different way to work once more than one thing is going on:
instead of three terminals of agents with you in the middle, one window where you
hand work off, see what is moving across every project, and step in only where
your judgment is needed. A factory, on your own machine, and the more you hand it
the more it does.
#1 on DeepSWE of ten coding harnesses on the same model, ahead of Claude Code,
Codex, OpenCode, Kilo and DeepSeek's own harness, at the lowest cost per solved
issue (benchmarks).
Written in Go as one small binary, with nothing else to install or run. Apache
2.0. By AgentField AI.
Early preview. CodeAF is young and moving fast. Expect rough edges, and tell
us where you hit them on Discord or in an issue.
https://github.com/user-attachments/assets/bc87e460-17b1-4d7a-8c69-284b524ea194
Real speed, with sound. The three tasks run live on DeepSeek V4.1 Flash; the other projects and the large task tree are a seeded demo machine.
Install
curl -fsSL https://agentfield.ai/get/codeaf | bash
codeaf
The script puts the release binary for your platform in ~/.codeaf/bin. To
pin a version, give it a tag from the
releases page, where the
assets and checksums also live:
curl -fsSL https://agentfield.ai/get/codeaf | VERSION=<tag> bash
To build it yourself: git clone, make build, bin/codeaf
(guide).
On first start it connects OpenRouter in your browser, or takes a key. Codex signs in
a ChatGPT plan from /connect or codeaf connect codex; DeepSeek, GLM, Kimi, MiniMax
and Qwen take keys; Ollama needs none.
One window for every project
An agent that lives in one folder means a terminal per repository, and a tmux
layout to remember which is which. CodeAF is one window.
home lists every project and conversation on the machine. enter opens any
of them in a tab, and the one you left keeps streaming with its tasks still
running. tab flips back. alt+k jumps to any conversation, open or closed.
Each keeps its own approval rules, models and spend limit.
home answers what needs you, what is unread, what is running and what it
cost, for all of them at once. A digit answers a question from its row.
Talk, and it becomes tasks
Say what is wrong the way you would to a colleague. Name three things in one
message and each can become its own task, in its own copy of the repository, on
its own branch. The conversation stays yours while they run, and the rail beside it
shows every task and its subtasks.
› three more while you are on it: the retry test fails one run in five on CI,
the pricing page wraps mid word on phones, and the deploy key expires friday
Work that passes its check lands on your branch by itself, never on main,
dev or a release branch. Work nothing could check waits under unread:
1 accept, 2 not right.
What a factory is
Agents run by hand got fast, but the scheduling, checking and merging stayed
with you.
A factory is the third picture: one line out, one line back.
- It does the middle. It sizes the work, splits it, runs the parts where
they cannot collide, tests what came back and merges what passed.
- It asks only when it must. A question waits under
needs you, from every
project. Everything else it decides, writes down, and carries on.
Subharnesses: specialists built for one job
Build a change, review a pull request, or audit local code. Each built-in specialist has a process for its own job and runs as a task beside your conversation. Open its task to follow the work or stop it; its result comes back to the chat. The built-in specialists run on macOS and Linux, with no extra specialist installation.
| Specialist | Try it in the chat | What comes back |
|---|
| senior-dev: coding changes | /senior-dev fix the retry bug and add tests | A submitted change and the project's build and test results, or an explanation of what could not be checked. In git, it works in a private copy on its own branch. |
| sec: local security audits | /sec changes since main | Security findings with evidence and suggested fixes; Markdown, JSON and SARIF reports. Use /sec alone for the whole repository. |
| review: GitHub pull requests | /review owner/repo#123 focus on retries | Findings with file locations, reasons, suggested fixes and review coverage; Markdown and JSON reports. |
review is imported from PR-AF, and sec from SEC-AF, under their codeaf command names. Both read source code without running your tests, build, app or exploits. They leave your code unchanged; posting a review or fixing findings is a separate action you request. Read the report's coverage and any incomplete analysis before acting on it. As always, it's important to note that a lack of findings does not and can not guarantee a lack of security problems.
The coding benchmark below measures senior-dev. PR-AF publishes its own Martian Code-Review-Bench results; those are results for the original project, not a measurement of codeaf's imported review specialist.
Your own saved programs: ask codeaf to design a harness for recurring work, such as triaging flaky tests. Review and approve its design, then open /subharness to run it again. See Saved shapes of work.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
