fang503/antflow

59 stars · Last commit 2026-04-01

AI agent platform enhanced with Agent OS architecture inspired by Claude Code, built on DeerFlow

README preview

# AntFlow

[English](./README.md) | [中文](./README_zh.md)

[![Python](https://img.shields.io/badge/Python-3.12%2B-3776AB?logo=python&logoColor=white)](./backend/pyproject.toml)
[![Node.js](https://img.shields.io/badge/Node.js-22%2B-339933?logo=node.js&logoColor=white)](./Makefile)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)

AntFlow is a **production-grade AI agent platform** forked from [DeerFlow](https://github.com/bytedance/deer-flow) and deeply enhanced with core architectural patterns from **Claude Code** — Anthropic's Agent Operating System.

> **Why the name?** "Ant" nods to **Ant**hropic, whose Claude Code source code inspired the architectural overhaul. "Flow" inherits from DeerFlow's workflow orchestration DNA.

### What's New at a Glance

| Enhancement | From Claude Code | What It Does |
|---|---|---|
| **Permission System** | 5-level layered model | Every tool call checked against `READ_ONLY` → `ALLOW` policy |
| **Hook Governance** | PreToolUse / PostToolUse | Audit, block, or modify any tool call via shell scripts or Python |
| **Execution Pipeline** | toolExecution.ts | Structured 5-stage pipeline: Permission → PreHook → Execute → PostHook → Merge |
| **Prompt Assembly** | getSystemPrompt() | Modular builder with static/dynamic cache boundary, ~88% cache hit |

View full repository on GitHub →