anycode
万能编程智能体 — 用 任意 OpenAI 兼容大模型 驱动你的终端 AI 编程助手。
基于 Claude Code v2.1.88 重构,完整保留所有代理能力,支持第三方模型。
安装
pip install anycode-ai
要求: Node.js >= 18(安装)
快速开始
# 首次运行 — 交互式配置向导
anycode
# 非交互模式
anycode -p "解释这个代码库"
# 测试连接
anycode --test
# 查看当前配置
anycode provider-info
支持的服务商
| 服务商 | 模型 | API 地址 |
|---|---|---|
| OpenAI | gpt-4o, gpt-4o-mini, o1, o3 | api.openai.com |
| DeepSeek | deepseek-chat, deepseek-reasoner (R1) | api.deepseek.com |
| Qwen(通义千问) | qwen-max, qwen-plus, qwen-turbo | dashscope.aliyuncs.com |
| MiniMax | MiniMax-M2.7, M2.5, M2.1, M2 | api.minimax.io |
| GLM(智谱清言) | glm-4-plus, glm-4 | open.bigmodel.cn |
| SiliconFlow(硅基流动) | DeepSeek-V3, Qwen2.5 | api.siliconflow.cn |
| Kimi(月之暗面) | moonshot-v1-auto | api.moonshot.cn |
| Ollama(本地模型) | llama3, codellama, mistral | localhost:11434 |
| 任意 OpenAI 兼容 API | 任意模型 | 任意端点 |
配置
# 环境变量(CI/CD 友好)
export ANYCODE_API_KEY="sk-..."
export ANYCODE_BASE_URL="https://api.deepseek.com/v1"
export ANYCODE_MODEL="deepseek-chat"
anycode -p "修复这个 bug"
# 或使用配置文件:~/.anycode/provider.json
核心能力
- Bash — 执行终端命令
- Read / Write / Edit — 文件读写编辑
- Grep / Glob — 代码搜索
- Agent — 子代理并行执行
- WebFetch — 获取网页内容
- MCP — Model Context Protocol 协议支持
- Worktree — Git 工作区隔离
版本记录
v1.3.0
- 禁用 Anthropic 遥测数据发送和 GrowthBook 远程功能标记
- 第三方供应商费用显示改为只显示 token 用量(不再显示虚假美元价格)
- 自动隐藏不可用的 WebSearch 工具
anycode auth login重定向到供应商配置提示
v1.2.2
- 不支持图片的供应商(MiniMax、DeepSeek 等)上传图片时显示警告提醒
- 图片安全降级为文本占位符,避免 API 报错
v1.2.1
- 修复 MiniMax M2.7 文本输出为空的问题:支持
<think>标签格式的推理内容解析 - 推理内容正确显示为 thinking block,正式回答正常输出
v1.2.0
- 修复 MiniMax 服务商配置:API 端点迁移至
api.minimax.io,默认模型更新为 MiniMax-M2.7 - 新增 Kimi(月之暗面)预设服务商
- 更新上下文窗口配置(MiniMax: 204,800 tokens)
- 新增详尽的中文功能支持列表与功能兼容性对照表
- 明确标注支持/部分支持/不支持的功能
v1.1.2
- 首个 PyPI 发行版
- pip install 一键安装
- 交互式供应商配置向导
- 支持 8 个预设服务商 + 自定义端点
GitHub
Metadata
Release files for anycode-ai 1.3.0
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 |
|---|---|---|---|---|
| anycode_ai-1.3.0.tar.gz | 9.3 MB | Without provenance | Details for anycode_ai-1.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| anycode_ai-1.3.0-py3-none-any.whl | Python 3 | none | any | Details for anycode_ai-1.3.0-py3-none-any.whl |
Total release size: 21.4 MB
Release files / anycode_ai-1.3.0.tar.gz
| Download URL | anycode_ai-1.3.0.tar.gz |
|---|---|
| Size | 9.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
94bea83483c32b6d76a10c2ba85b2fa1deb7c4fcb0ba286a48fd7a679e51a2f6
|
|
BLAKE2b-256 checksum How to use checksums |
9c40ecbd5391563b1f1c1faf6c60e38287a3a532664871a4670cc344fe20e39d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / anycode_ai-1.3.0-py3-none-any.whl
| Download URL | anycode_ai-1.3.0-py3-none-any.whl |
|---|---|
| Size | 12.1 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c867b7c327e43c3b07667b4093cd46e15b60ccfd7d000bf3329e6c621d8a20c1
|
|
BLAKE2b-256 checksum How to use checksums |
1ef3944045f3589d2c303f173e35b1c986f06d6193d95016e4df3779adbbb32b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Security for anycode-ai 1.3.0
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.