# CodeAF

> Source: <https://openalternative.co/codeaf?utm_source=openalternative.co&utm_medium=rss>
> Published: 2026-11-22 19:27:51+00:00

**Key takeaway:** CodeAF v0.8.3 assigns a different model to each role via "Pareto Crewing" and gates merges on a held-out acceptance checklist the worker never sees, which the project claims cuts cost up to 25×.

Open Source Alternative to:

- Stars 825
- Last commit 3 hours ago
- Repository age 4 months
- Version v0.8.3
- License [Apache-2.0](https://openalternative.co/licenses/apache-2)
- Repository [agent-field/codeaf](https://github.com/Agent-Field/CodeAF)

This is a terminal-based software factory for people who want an [AI coding agent](https://openalternative.co/categories/developer-tools/ai-assisted-coding/ai-coding-agents) that works on open models. You describe a job, and it plans the work, runs tasks in parallel on separate branches, and merges only what passes an independent check.

It ships with three built-in specialists:

- **/senior-dev** implements a coding change and checks the result.
- **/sec** audits local code for security problems.
- **/review** reads a GitHub pull request and reports findings, much like an[AI code reviewer](https://openalternative.co/categories/developer-tools/ai-assisted-coding/ai-code-reviewers) . Security and review use read-only tools.

What sets it apart:

- **Pareto Crewing** assigns a different model to each role, so expensive models only handle the steps where quality is decided. The project claims up to 25× lower cost.
- **Held-out acceptance** turns your request into a checklist the worker never sees, so it can't write tests to fit the list.
- **Rewind** restores full working state, including untracked files like .env, through a bundled tool.
- **Plain-English rules** cover schedules, hooks and watchers, scoped to a chat, a project or everywhere.
- **SSH-native** sessions live on your dev box, and you attach from a laptop or phone.

It works with OpenRouter, DeepSeek, GLM, Kimi, MiniMax, Qwen, Ollama or any OpenAI-compatible endpoint. With Ollama, nothing leaves your machine. It reads your AGENTS.md, CLAUDE.md and existing skills folders, and connects to Slack, Linear, Jira, GitLab, Sentry and others.

Spending is capped by a daily backstop and per-conversation limits. Anything beyond reads and searches asks first. You can use it instead of [Claude Code](https://openalternative.co/alternatives/claude-code) or alongside it, and it's licensed Apache-2.0.

Every Sunday we deconstruct one proprietary app and pick the best open source alternatives worth switching to.

- Stars
- Last commit
- License

AI

AI coding agent for terminal, IDE, and desktop

- Stars Stars growing over the last 30 days228,575
- Last commit 2 hours ago
- License MIT

Open source AI coding agent that works in your terminal, IDE, or desktop app, supporting 75+ LLM providers with no code storage.

Compare with

AI coding agent that works inside your terminal

- Stars 136,140

Minimal terminal coding agent you can fully customize

- Stars 123,322

Autonomous coding agents that complete real engineering tasks

- Stars 94,071

Open-source AI coding agent for your editor and terminal

Coding agent that runs on local and open-weight models

- Stars 68,944

Open source AI coding agent for the terminal and IDE

- Stars 30,869

AI coding agent and CLI for complex terminal workflows

- Stars 27,826

AI coding agent for VS Code, JetBrains, CLI, and Cloud

Terminal coding agent with full model and data control

- Stars 1,782

Self-hosted AI coding agent that opens real PRs

Stars growing over the last 30 days

Last commit

2 hours ago
License

Apache-2.0
Terminal-based AI coding agent that inspects files, edits code, runs commands, and integrates into CI pipelines using OpenAI's Codex models.

Terminal-based coding agent with a minimal core, 15+ LLM providers, tree-structured session history, and a TypeScript extension system for building your own workflows.

AI agent platform that runs autonomous coding agents to plan, write, and ship changes across codebases end-to-end, with support for any model and self-hosted deployment.

Stars

71,823

AI coding agent that runs inside VS Code and the terminal, supporting multi-file edits, bash execution, and any LLM provider via bring-your-own-key.

Coding agent that lets LLMs write and execute code, manage files, and control your computer using local or low-cost models.

Terminal-based AI coding agent that reads your codebase, edits files and runs commands, with support for Qwen, OpenAI, Anthropic, Gemini and local models.

Terminal-based coding agent powered by Grok 4.5 that plans, builds, tests, and deploys across any codebase with parallel subagents and plugin support.

28,087

Open source AI coding agent with 500+ models, bring-your-own-key support, and specialized modes for writing, debugging, and planning code across IDEs and CLI.

Open-source AI coding agent for the terminal that works with 25+ model providers, keeps sessions on your disk, and ships as a single Go binary with no telemetry.

Stars growing quickly over the last 30 days350

Source-available, self-hosted AI coding agent that connects to your repo, tools, and chat to investigate issues and open reviewable PRs on your own infrastructure.
