跳到主要内容Skip to main content
投机取巧 Speculative Speculation

AI 工具AI Tools · Coding

AI 编程AI coding

自己能跑的成品 AI 编程工具，共用八维（模型接入 / 运行位置 / 本地文件 / 关机后任务 / 工具扩展 / 上下文 / 权限 / 适合场景）。按形态分三列——IDE 形态、CLI 形态、厂商云形态。前两者是同一产品的不同装法、不是竞争关系；厂商云形态则是另一个方向：不需要自己装，工作在别人的机器上做。Finished AI coding tools you can run yourself, compared on eight shared dimensions (model access / where it runs / local files / tasks after shutdown / tools and extensions / context / permissions / best fit). Grouped into three forms — IDE, CLI and vendor cloud. The first two are different install forms of the same product, not competitors; vendor cloud is a different direction entirely: nothing to install, the work happens on someone else's machine.

41 个对象objects 8 个固定维度fixed dimensions 0 个已完整核验fully verified 最后核验Last checked 2026-10-30
  1. 本站按 10 大类收录 AI 产品。编程、对话、图像、视频、音频、研究、自动化、框架、MCP 工具、本地运行器——每类都有明确的收录标准，写在各大类的目录页里。This site files AI products into 10 categories. Coding, chat, image, video, audio, research, automation, frameworks, MCP tools and local runners — each with explicit admission criteria, written on the category page itself.
  2. 大类看目录，形态看字段。一个产品属于哪一类由收录边界决定；它怎么装进你的工作流（IDE / CLI / 厂商云 / 框架 / MCP…）是另一根独立的轴。Category comes from the shelf, form from a field. Which category a product belongs to is decided by admission boundaries; how it installs into your workflow (IDE / CLI / vendor cloud / framework / MCP…) is a separate axis.
  3. 每条档案都是核验快照。字段逐条挂官方出处与核验日期，本站不实测、不排名，未知就写未知。Every entry is a verification snapshot. Each field carries an official source and a checked date; we run no benchmarks, publish no rankings, and write "unknown" when it is unknown.

先回答一件事：你要它替你干多少事Answer one question first: how much do you want it to do for you

这一大类 41 份档案，分三个方向：19 份是装在自己机器上的 IDE 形态、12 份是 CLI 形态、10 份是厂商云形态（本机什么都不装，工作在别人的机器上做）。其中五组是同一个产品的两种装法——Aider、Claude Code、Codex、Copilot、Cursor 各有一份 IDE 形态和一份 CLI 形态，它们不是竞品，差别在装在哪、怎么被唤起、能不能塞进脚本；去重后是 36 个产品。This section holds 41 entries, split three ways: 19 are IDE-form tools installed on your own machine, 12 are CLI-form, and 10 are vendor cloud — nothing installs locally, the work happens on someone else's machine. Five pairs are the same product in two forms — Aider, Claude Code, Codex, Copilot and Cursor each have an IDE entry and a CLI entry; they are not competitors, and they differ in where they install, how they are invoked, and whether they drop into scripts. Deduplicated, that is 36 products.

  1. 1我要一个自己能开的编辑器I want an editor I can launch myself
    看 IDE · 独立编辑器See IDE · standalone editorCursor、已改称 Devin Desktop 的 Windsurf、Zed、AWS 的 Kiro 都在这一类。Cursor, Windsurf (now renamed Devin Desktop), Zed and AWS's Kiro are all in this group.
  2. 2我已经在用 VS Code / Cursor 了I already use VS Code / Cursor
    看 IDE · 扩展形态See IDE · extension formClaude Code、Codex、Copilot、Cline、JetBrains 的 Junie、Continue 都是在既有编辑器里装。注意其中 Claude Code / Codex / Copilot 另有 CLI 形态，别当成两个产品比。Claude Code, Codex, Copilot, Cline, JetBrains' Junie and Continue all install into an existing editor. Note that Claude Code, Codex and Copilot also have CLI forms — do not compare them as if they were two products.
  3. 3我不想换编辑器，也不想装插件I do not want to switch editors or install plugins
    看 Aider（Watch 模式）See Aider (Watch mode)它不是编辑器插件而是后台常驻进程，你在任意编辑器里加 AI 注释它就响应。It is not an editor plugin but a background resident process: add an AI comment in any editor and it responds.
  4. 4我要它每一步都问我I want it to ask me at every step
    看默认逐次确认的那几个 CLISee the CLIs that confirm every action by defaultCrush 默认每次工具调用都问；Aider 有自动提交但沙箱机制未核验。Crush asks before every tool call by default; Aider has auto-commit but its sandbox mechanism is unverified.
  5. 5我要它在指定范围内自己跑I want it to run on its own within a set scope
    看有明确沙箱 / 可信目录的那几个See those with an explicit sandbox / trusted directoriesGemini CLI 的沙箱与 Trusted Folders 都有独立官方文档；Claude Code CLI 的权限粒度最细，还有「允许这一次」。Gemini CLI documents its sandbox and Trusted Folders separately; Claude Code CLI has the finest permission granularity, including "allow just this once".
  6. 6我要它能塞进 CI / 脚本里跑I need it to run in CI / scripts
    有一整批有官方证据的落点A whole batch now has official evidenceGemini CLI、Codex CLI 之外，2026-10 收录的一批也都给了非交互文档：Cursor CLI（headless）、Copilot CLI（-p）、Continue（cn -p）、goose（goose run）、Droid（droid exec）、Kiro CLI（--no-interactive）。Beyond Gemini CLI and Codex CLI, the 2026-10 additions all document non-interactive execution: Cursor CLI (headless), Copilot CLI (-p), Continue (cn -p), goose (goose run), Droid (droid exec) and the Kiro CLI (--no-interactive).
  7. 7我要关掉客户端后它还在干活I want it to keep working after I close the client
    主看厂商云形态那 10 份Start with the 10 vendor-cloud entries那一层是「整台机器都在云上」：Dot / Muse / Grok Bot / Jules / Augment / Bolt / Devin / Lovable / Replit Agent / v0，差别在审批与异步流程怎么设计——Muse 有独立的 Sentinel agent，Dot 是自动审核，Grok Bot 官方页没写，Jules 以「批准计划」为节点（API 可跳过）。本地形态里也有一批给特定任务提供云端执行（Cursor 的云端 Agent、Kiro 的 Cloud Session、Amp 的 orb、Copilot 的 coding agent），所以「关机后能不能跑」要按对象的 background 维度逐个看，别按形态一刀切。That layer is 'the whole machine is in the cloud': Dot, Muse, Grok Bot, Jules, Augment, Bolt, Devin, Lovable, Replit Agent and v0 — they differ in how approval and async flow are designed — Muse has a separate Sentinel agent, Dot reviews automatically, Grok Bot's official page does not say, and Jules gates on an approved plan (skippable via API). Some local forms also offer cloud execution for specific tasks (Cursor's cloud agents, Kiro's Cloud Sessions, Amp's orb, Copilot's coding agent) — so check the `background` dimension per entry instead of assuming by form.
  8. 8我要数据完全不离开本机I need data never to leave my machine
    这一层也没有合适的Nothing here fits either厂商云形态的机器在别人那里（Dot 默认与本机隔离、授权后才碰）；本地形态里只有 sandbox / 可信目录那一档能限制写入范围。The vendor-cloud machines are on someone else's (Dot is isolated from your machine by default and only touches it once authorised); among local forms, only the sandbox / trusted-directory tier can restrict write scope.

⚠ 两个最容易踩的误解：「AI 原生编辑器」不等于「模型可自选」——形态看 runtime，模型接入看 model_access，两个维度是分开的；Codex CLI 的审批模式与沙箱档位在 CLI 文档里查不到，在它 SDK 的源码里有——四种审批 × 三档沙箱（read-only / workspace-write / danger-full-access），还能按路径 deny 掉读 .env，跨平台差异仍未核验。⚠ Two misconceptions people fall into most easily: "AI-native editor" does not mean "model is selectable" — form is `runtime`, model access is `model_access`, and the two dimensions are separate. Codex CLI's approval modes and sandbox tiers are not in its CLI documentation, only in its SDK source: four approval modes × three sandbox tiers (read-only / workspace-write / danger-full-access), plus per-path denies on reading `.env`. Cross-platform differences remain unverified.

按装法分By install form

同一产品常有 IDE 与 CLI 两种装法，它们不是竞品——装在哪、怎么被唤起、能不能进脚本都不同。选你实际要用的那个。A product often has both an IDE and a CLI form. They are not competitors — they differ in where they install, how they are invoked, and whether they drop into scripts. Pick the one you will actually use.

IDE 形态IDE form 19

IDE 形态IDE form

装进编辑器，或本身就是独立编辑器。看得见界面，权限多在对话里给。Installed into an editor, or an editor in its own right. You see a UI, and permissions are mostly granted in conversation.

Aider Watch 模式Aider (Watch mode)

Aider-AI

不是编辑器插件，是一种使用模式。 Aider 常驻 watch 你的文件，你在任意编辑器里加 AI 注释，它就响应。Not an editor plugin but a usage mode — Aider stays resident a

部分核验Partly verified 详情 →Details →

ClineCline

Cline Bot

提供 CLI、桌面和编辑器入口的编码工具。CLI、Desktop App、VS Code 扩展共享同一开源核心。模型也是自选A coding tool with CLI, desktop and editor entry points — CLI,

部分核验Partly verified 详情 →Details →

CodeBuddyCodeBuddy

腾讯云Tencent Cloud

CodeBuddy 是腾讯云的三端编码助手（插件/AI IDE/CLI）：混元为主、可接其它大模型， Figma 到代码、CCodeBuddy is Tencent Cloud's three-surface coding assistant (p

部分核验Partly verified 详情 →Details →

ContinueContinue

Continue

开源、模型完全自配的 IDE 扩展。 但它已停更：Continue 被 Cursor 收购，上游仓库转入 read-onlyAn open-source IDE extension with fully self-configured models

部分核验Partly verified 详情 →Details →

GitHub CopilotGitHub Copilot

GitHub / Microsoft

与 GitHub 生态集成的编码工具——从网站到 CLI 到主流编辑器全覆盖，且能把任务委派给 Claude / CodexA coding tool integrated with the GitHub ecosystem — website,

部分核验Partly verified 详情 →Details →

CursorCursor

Anysphere

支持编辑器、云端 Agent 与自有机器执行。模型可得性、额度和数据边界随档位与部署方式变化，需分别核对。An editor with cloud-agent and self-hosted execution options.

部分核验Partly verified 详情 →Details →

JunieJunie

JetBrains

Junie 是 JetBrains 官方的 AI coding agent。 它的形态是插件加 CLI：插件装进 JetBrJetBrains' official "AI coding agent" — a plugin inside JetBra

部分核验Partly verified 详情 →Details →

Kilo CodeKilo Code

Kilo-Org

Kilo Code 是开源编码 agent（GitHub MIT）：VS Code/JetBrains/CLI/DesktoKilo Code is a leading open-source coding agent (MIT): VS Code

部分核验Partly verified 详情 →Details →

KiroKiro

AWS

AWS 出的 agentic 工程环境：一套 harness 同时撑起 IDE / CLI / Web / Mobile 四AWS's agentic engineering environment: one unified harness acr

部分核验Partly verified 详情 →Details →

QoderQoder

阿里云Alibaba Cloud

Qoder 是阿里体系的 AI 编码产品国际线（qoder.com，与国内线 Qoder CN/原通义灵码分线）： QodeQoder is the Alibaba-affiliated international Qoder line (qode

部分核验Partly verified 详情 →Details →

TraeTrae

字节跳动ByteDance

Trae 是字节跳动的三端 AI IDE（桌面/Web/移动）：Desktop 双窗口（Agent/IDE）+ SOLO 模Trae is ByteDance's three-client AI IDE (desktop / web / mobil

部分核验Partly verified 详情 →Details →

ZedZed

Zed Industries

Zed 在一个编辑器里编排三种 agent 路径：Zed 原生 Agent，Claude / Codex，OpenCode Not "yet another AI coding tool" but an orchestration layer fo

部分核验Partly verified 详情 →Details →

CLI 形态CLI form 12

CLI 形态CLI form

在终端里跑。能进脚本与 CI，权限确认粒度是最细的一层。Runs in the terminal. Drops into scripts and CI, with the finest granularity of permission confirmation.

AiderAider

Aider-AI

Aider 是一个终端 pair programming 工具。 它把 Git 集成当核心设计，不是附加功能。 AI 改动始A terminal pair-programming tool where Git integration is core

部分核验Partly verified 详情 →Details →

AmpAmp

Amp Frontier Corporation（原 Sourcegraph，2025-12 分拆独立）Amp Frontier Corporation (spun out of Sourcegraph, Dec 2025)

Amp 原是 Sourcegraph 出的前沿编码 agent，2025-12 官方公告分拆为独立公司 Amp FrontiSourcegraph's Amp: a frontier coding agent spanning CLI + clou

部分核验Partly verified 详情 →Details →

Claude Code CLIClaude Code CLI

Anthropic

提供终端编程与工具执行的产品，带 CHANGELOG 与 Atom feed；权限设置、执行边界与版本变化见下文。A terminal coding and tool-execution product, with a CHANGELOG

部分核验Partly verified 详情 →Details →

Codex CLICodex CLI

OpenAI

OpenAI 官方的终端编码 agent，Rust 实现，架构上强调 app server 与线程续接。OpenAI's official terminal coding agent, written in Rust, arch

部分核验Partly verified 详情 →Details →

GitHub Copilot CLIGitHub Copilot CLI

GitHub

Copilot 在终端里的编码 agent 形态，与 GitHub 订阅同源。 它能在终端里走完一条链。 "读仓库 / 改代The Copilot agent in your terminal, carried by your GitHub sub

部分核验Partly verified 详情 →Details →

CrushCrush

Charm

crush 是 Charm 生态出品的 TUI 编码 agent，在终端里跑。 它的 列明 MCP 三种传输方式，并带一个官A TUI coding agent in the Charm ecosystem that runs in your te

部分核验Partly verified 详情 →Details →

Cursor CLICursor CLI

Anysphere

Cursor 的终端形态：和编辑器共用同一账户、同一批模型、同一份 mcp.json。 命令名是 agent。 官方称它支持The terminal form of Cursor: it shares one account, one model

部分核验Partly verified 详情 →Details →

DroidDroid

Factory AI

Droid 是 Factory AI 的终端编码 agent。 它模型无关——官方托管、BYOK、本地模型三路并存。 它以滚Factory AI's terminal coding agent, model-agnostic (factory-ho

部分核验Partly verified 详情 →Details →

Gemini CLIGemini CLI

Google

Google 官方的开源终端 agent，npx 免安装启动。 明确支持 MCP，另有非交互脚本模式。Google's official open-source terminal agent — npx, no install

部分核验Partly verified 详情 →Details →

GooseGoose

Agentic AI Foundation

本地优先的开源通用 agent：桌面应用 + CLI + 可嵌入 API 三种形态都能跑。 由 Block 创建，现属 AgCreated by Block and now hosted by the Agentic AI Foundation (

部分核验Partly verified 详情 →Details →

OpenCodeOpenCode

OpenCode

MIT 许可的多 provider 编程 harness。它运行 bash 命令前会询问权限，并支持 ACP 载入。An MIT-licensed multi-provider programming harness that asks p

部分核验Partly verified 详情 →Details →

WarpWarp

Warp

开源的终端 agent 环境。 官方自称： 「Agentic Development Environment」 它把现代终端An open-source Agentic Development Environment — the vendor's

部分核验Partly verified 详情 →Details →

厂商云形态Vendor cloud 10

厂商云形态Vendor cloud

本机不装任何东西，在厂商的云端机器上持续工作（OpenAI Dot / Meta Muse / xAI Grok Bot）。差别不在功能多寡，而在机器归谁 —— 代价是本地文件与离线能力基本让出，收益是关机后仍在跑。Nothing installs locally; the work happens on the vendor's cloud machine (OpenAI Dot / Meta Muse / xAI Grok Bot). The difference is not how many features you get but whose machine it runs on — the cost is giving up local files and offline capability, the benefit is that it keeps running after shutdown.

Augment CodeAugment Code

Augment Code

Augment Code 是企业级「软件工厂」平台：Cosmos 把规划-实现-评审-反馈连成可重复的 agent 流水线，Augment Code is the enterprise 'software factory' platform: Co

部分核验Partly verified 详情 →Details →

Bolt.newBolt.new

StackBlitz

Bolt.new 是 StackBlitz 的浏览器内全栈 AI 构建器：跑在 WebContainers 上（浏览器里直接Bolt.new is StackBlitz's in-browser full-stack AI builder: it

部分核验Partly verified 详情 →Details →

DevinDevin

Cognition

Devin 是「工单进、草稿 PR 出」的云异步软件工程师（Cognition）：会话在厂商云工作区跑， 自带 shell/Devin is the 'ticket in, draft PR out' cloud async software en

部分核验Partly verified 详情 →Details →

xAI Grok BotxAI Grok Bot

xAI

官方以具体岗位清单说明用途。 它不谈机制，直接列了九个岗位：销售线索、网站搭建、收件箱、会议代听……The official page explains uses through a list of jobs. It doe

部分核验Partly verified 详情 →Details →

JulesJules

Google

本机什么都不装，任务跑在 Google 的云机器上，做完给你一个 PR。 它和你熟悉的 IDE / CLI 助手最大的差别在Nothing installs locally: the work runs on a Google Cloud VM a

部分核验Partly verified 详情 →Details →

LovableLovable

Lovable

Lovable 是瑞典 Lovable 的全栈 AI 建站平台：自然语言生成带前端/数据库/认证/托管的完整应用， 内置后端Lovable is Sweden's full-stack AI app builder: natural languag

部分核验Partly verified 详情 →Details →

Meta MuseMeta Muse

Meta

用独立 agent 承担审批的设计。Muse Secure VM 上跑着两个系统级隔离的东西：干活的 Muse，和否决它的 A design with a separate agent handling approval — two system-

部分核验Partly verified 详情 →Details →

OpenAI DotOpenAI Dot

OpenAI

OpenAI 官方的云端编码 agent：本机什么都不装，所有工作发生在 OpenAI 的云端机器上。官方给的能力边界写得很Nothing installs locally; all work happens on OpenAI's cloud m

部分核验Partly verified 详情 →Details →

Replit AgentReplit Agent

Replit

Replit Agent 是「从自然语言到能上线的应用」的云 IDE agent：建项目、装基础设施、测试、部署一条龙， FReplit Agent is the cloud-IDE agent from plain language to a d

部分核验Partly verified 详情 →Details →

v0v0

VercelVercel

v0 是 Vercel 的提示词到全栈应用平台：聊天生成 Next.js 应用，VM 沙箱内跑真终端与预装 agent （cv0 is Vercel's prompt-to-full-stack platform: chats generate N

部分核验Partly verified 详情 →Details →

本站目前是「核验快照」，还没有实测数据This site is currently a verification snapshot — no measured runs yet

下面每一个字段都能回到官方原文核对，但我们还没有在同一批任务上跑过这些工具。Every field below can be traced back to the official source, but we have not yet run these tools on the same batch of tasks. 实测协议已经写好（统一任务、统一验收、记录人工介入与返工次数），任务清单也已就绪，The measurement protocol is written (shared tasks, shared acceptance criteria, recording human interventions and rework counts) and the task list is ready, but it is 尚未执行。not yet run.

所以本站给的是能力边界与证据，不是「哪个更好用」的结论。So what this site gives you is capability boundaries and evidence, not a verdict on which is better to use. 真正的选型请用你自己的输入、预算与验收标准跑一遍。For an actual choice, run them yourself against your own inputs, budget and acceptance criteria.

8 个维度，每格都能回溯8 dimensions, every cell traceable

所有对象在同一坐标系下被描述。All objects are described on the same coordinate system. 点开任一对象，每一格下面都有官方源链接与核验日期——不认同可以自己回去查。Open any object and every cell carries an official source link and a checked date — disagree and verify it yourself.

01

模型与开放条件Model & openness

用谁的模型？能不能换第三方？多模型路由怎么配？Whose model does it use? Can you switch to a third party? How is multi-model routing configured?

02

运行位置Where it runs

本地 / 云端 / 混合？索引在本地还是云端？远程控制不等于云端执行。Local, cloud or hybrid? Is the index local or remote? Remote control is not the same as cloud execution.

03

本地文件Local files

能访问多大范围？未打开的大文件怎么读？符号级能力如何？How wide an area can it reach? How does it read large files you have not opened? How capable is it at the symbol level?

04

关机后的任务Tasks after shutdown

电脑关了还能继续跑吗？这是本地形态最常见的误解来源。Does it keep running once the computer is off? This is the most common misconception about local forms.

05

工具与扩展Tools & extensions

工具链有多宽：MCP · LSP · 插件 · Hooks · 自定义指令。How wide is the toolchain: MCP · LSP · plugins · hooks · custom instructions?

06

上下文与记忆Context & memory

索引算法、上下文窗口、会话恢复与分叉、跨会话记忆边界。Indexing algorithm, context window, session resume and fork, and the boundary of cross-session memory.

07

权限与限制Permissions & limits

沙箱与审批边界、凭据管理、数据是否出境、额度如何计算。Sandbox and approval boundaries, credential handling, whether data leaves your machine, and how quota is charged.

08

适合什么任务Best for

最擅长什么任务？什么情况下别用它？What tasks is it best at? When should you not use it?

全部数据一览All data at a glance

同一张表横向对比。点对象名进详情页看逐格证据。The same table side by side. Click an object name to see per-cell evidence.

对象Object形态Form厂商Vendor适合Best for核验日Checked状态Status
AAIAiderAider CLI 形态CLI form Aider-AI 适合三类场景。 留在 git 里的改动：希望 AI 改动始终留在 git 版本控制里。 这样的改动可 diff、可撤销。 多模型接入：需要连Scenarios where AI changes must stay in git version control, diffable 2026-10-23 partial
AAIAider Watch 模式Aider (Watch mode) IDE 形态IDE form Aider-AI 适合两类人： 习惯在任意编辑器里工作，不愿切换到专门的 Agent 界面的人 需要「加注释 → 自动响应」这种轻量交互的人People who work in whatever editor they like and refuse to move to a d 2026-10-23 partial
AmAMAmazon Q DeveloperAmazon Q Developer IDE 形态IDE form AWS 适合：重度 AWS 用户——问架构/资源/最佳实践带引用、IDE 内做 Java 升级与安全扫描这类官方招牌改造任务。 不适合：要 agenFits: heavy AWS users — architecture Q&A with citations, resource trou 2026-10-22 partial
AAMAmpAmp CLI 形态CLI form Amp Frontier Corporation（原 Sourcegraph，2025-12 分拆独立）Amp Frontier Corporation (spun out of Sourcegraph, Dec 2025) 适合四类用法： 想让 agent 在自己的云端机器（orb）里长跑、合上笔记本仍继续的人 需要多模型前沿路由 + Oracle 第二意见的团Four kinds of use fit: People who want an agent that keeps working in 2026-10-23 partial
AuAUAugment CodeAugment Code 厂商云形态Vendor cloud Augment Code 适合：企业级「软件工厂」叙事——要跨 SDLC 的 agent 流水线（ticket→PR→merge→monitor）、 self-hosFits: enterprise cross-SDLC agent pipelines, self-hosted environments 2026-10-22 partial
文心BA文心快码（Baidu Comate）Baidu Comate (Wenxin Kuaima) IDE 形态IDE form 百度Baidu 适合：国内合规与私有化叙事（金融/医疗等客群官方点名）、IDE 全家桶（含 Xcode/Visual Studio 这类 同行少覆盖的 IDFits: domestic-compliance and private-deployment narratives (finance/h 2026-10-22 partial
BoBOBolt.newBolt.new 厂商云形态Vendor cloud StackBlitz 适合：免装环境浏览器内直接建全栈应用（WebContainers 底座）、要 GitHub 同步线、 要内置托管+数据库一条龙（Bolt CFits: building full-stack apps in the browser with zero local setup (W 2026-10-22 partial
CCCLClaude Code CLIClaude Code CLI CLI 形态CLI form Anthropic 重视权限可控性、需要 MCP 生态、希望用 Anthropic 官方模型的用户。 不适合需要开源许可或自托管的场景（许可明确 proprieUsers who value permission control, want the MCP ecosystem, and want A 2026-10-23 partial
CCCLClaude Code IDE 扩展Claude Code (IDE extension) IDE 形态IDE form Anthropic 已在用 IDE 且希望不切换工具就能用 Claude 的人。 需要在终端、IDE、GitHub 三处用同一工具的人。 重视权限可控性与 MCPeople already in an IDE who want Claude without switching tools. Peop 2026-10-23 partial
CCLClineCline IDE 形态IDE form Cline Bot 适合四类人： 需要同一工具覆盖编辑器、终端、桌面三种工作形态 需要模型自选（不想绑定单一厂商） 需要 CI/CD 集成（CLI headleUsers who need one tool across editor, terminal and desktop. People wh 2026-10-23 partial
CoCOCodeBuddyCodeBuddy IDE 形态IDE form 腾讯云Tencent Cloud 适合：国内团队要合规叙事（混元已备案）、腾讯云生态（CloudBase/CloudStudio）内建站到部署一条龙、 插件+IDE+CLI Fits: mainland teams wanting the compliance narrative (Hunyuan is file 2026-10-30 partial
CCOCodex CLICodex CLI CLI 形态CLI form OpenAI 适合在终端里做工程任务，要接 CI 或要自建客户端的场景。 它有个别人少有的证据：非交互模式有官方文档支持。 docs/exec.md 的标Engineering work in the terminal, including CI integration or building 2026-10-23 partial
CCOCodex IDE 扩展Codex (IDE extension) IDE 形态IDE form OpenAI 适合两类人： 已在用 VS Code / Cursor / Windsurf 等编辑器，希望在同一环境里用 Codex 而不切换工具的人 需A fit for two groups: People already in VS Code / Cursor / Windsurf wh 2026-10-23 partial
CoCOContinueContinue IDE 形态IDE form Continue 适合三类人： 需要模型自由（多 provider，含 Ollama 本地模型）而不想被单一厂商锁定的人。 已在 VS Code / JetBA fit for three groups: People who need model freedom (many providers, 2026-10-23 partial
CPGIGitHub Copilot CLIGitHub Copilot CLI CLI 形态CLI form GitHub 适合三类人： 已在 GitHub 生态、想在终端把「读仓库 / 改代码 / 跑测试 / 开 PR / 管 Issue」走完的人。官方用例直接People already in the GitHub ecosystem who want to walk the whole chai 2026-10-23 partial
GHGIGitHub CopilotGitHub Copilot IDE 形态IDE form GitHub / Microsoft 已在 GitHub 生态内（用 PR / Issue / Actions 工作）的人； 需要最广编辑器覆盖的人（VS Code / JetBPeople already inside the GitHub ecosystem (working via PR / Issue / A 2026-10-23 partial
CRCRCrushCrush CLI 形态CLI form Charm 适合这几类人： 喜欢 Charm 生态的终端体验（TUI 审美与交互） 需要在多个 provider 间切换，或想用官方订阅方案 HyperSeveral kinds of people fit: Users who like the Charm ecosystem's term 2026-10-23 partial
CCUCursor CLICursor CLI CLI 形态CLI form Anysphere 适合三类人： 在终端里做工程任务、写脚本、或进 CI/CD 的人（官方 GitHub Actions 文档与 cookbook） 已用 CuPeople doing engineering work in the terminal, writing scripts, or run 2026-10-23 partial
CCUCursorCursor IDE 形态IDE form Anysphere 适合三类人： 需要云端 Agent、希望合上笔记本任务继续跑的人 需要长周期（数月级）上下文维持与大规模子智能体编排的人 代码不能离开自有基For people evaluating cloud tasks, long-running projects or tool execu 2026-10-23 partial
DeDEDevinDevin 厂商云形态Vendor cloud Cognition 适合：把积压工单批量委派出去、并行跑多个任务、在 Slack 里随手 @ 派单、要「先给个草稿 PR 再接管」。 不适合：要选模型、要全程本Fits: delegating backlog tickets in bulk, parallel multi-task work, @- 2026-10-30 partial
DDRDroidDroid CLI 形态CLI form Factory AI 适合在终端里跑端到端软件工程、且需要企业级治理的团队。 三类团队最对得上： 已有仓库，想跑完规划 → 实现 → 测试的完整流程（/missiEnd-to-end software engineering in the terminal for teams that need en 2026-10-23 partial
GGEGemini CLIGemini CLI CLI 形态CLI form Google 适合三类场景： 想免安装快速试用（npx，不留安装痕迹） 需要 MCP 扩展，尤其是把 Gemini 的多模态生成能力（Imagen / VThree scenarios fit: You want a quick trial without installing anythin 2026-10-23 partial
GoGOGoogle AntigravityGoogle Antigravity IDE 形态IDE form Google 适合：要 Google 系模型+多面协同（桌面指挥中心/终端/IDE 扩展/SDK 同一 harness）、 要定时任务与后台子 agentFits: Google-family models plus multi-surface coordination (desktop co 2026-10-30 partial
GGOGooseGoose CLI 形态CLI form Agentic AI Foundation 四类人适合用： 想要一个本地优先、可换任意 provider（含本地模型）的通用 agent，而不止写代码的人 需要桌面应用 + CLI 双A fit for four kinds of people. People who want a local-first, general 2026-10-23 partial
xAIXAxAI Grok BotxAI Grok Bot 厂商云形态Vendor cloud xAI 适合按岗位选人的人。 官方给的是一份岗位化的 jobs 清单（见 tools 维），可以当清单用：销售线索、 网站搭建、邮箱清理、客服、游戏A fit if you pick tools by job to be done. The official list of nine j 2026-10-23 partial
JLJUJulesJules 厂商云形态Vendor cloud Google 官方给自己划的活是具体的：把任务描述交进 GitHub 仓库后，它做这些事： 官方原文："fix bugs, update dependenSelf-contained, verifiable work: fixing a named bug, bumping dependenc 2026-10-23 partial
JJUJunieJunie IDE 形态IDE form JetBrains 适合三类人，不适合另外三类。 适合： 已经在用 JetBrains IDE（IntelliJ IDEA / PyCharm / WebStoPeople already using JetBrains IDEs (IntelliJ IDEA / PyCharm / WebStor 2026-10-23 partial
KiKIKilo CodeKilo Code IDE 形态IDE form Kilo-Org 适合：要开源可自审 + 500+ 模型零加价 + BYOK/本地模型全支持、VS Code/JetBrains/CLI/云端多形态、 免费起Fits: open-source and auditable, an extremely wide model menu (zero-ma 2026-10-22 partial
KKIKiroKiro IDE 形态IDE form AWS 适合三类人： 在 AWS 生态里做正式工程交付、要「先出 spec 再实现」的团队 需要云端会话在关机后继续跑的人（Cloud sessioTeams doing formal engineering delivery in the AWS ecosystem who want 2026-10-23 partial
LoLOLovableLovable 厂商云形态Vendor cloud Lovable 适合：从想法到带数据库/认证/托管的全栈应用一条龙、要 Git 双向同步把代码放进自己仓库、 企业治理叙事（SSO/SCIM/审计/EU iFits: idea-to-launch in one place, Git sync into your own repo, enterp 2026-10-22 partial
MUMEMeta MuseMeta Muse 厂商云形态Vendor cloud Meta 官方定位是 官方原文："for billions of people worldwide, so there's no learning cFits (official positioning): everyday tasks plus longer goals — bookin 2026-10-23 partial
OAOPOpenAI DotOpenAI Dot 厂商云形态Vendor cloud OpenAI 官方给的是岗位化场景，值得直接抄成选型依据： 把反馈转成经过测试的修复（交完整 PR 附演示视频） 产品范围变化时调整发布方案 拿到新证据后Fits (scenarios the vendor itself gives, usable directly as selection 2026-10-23 partial
OCOPOpenCodeOpenCode CLI 形态CLI form OpenCode 需要多 provider 可切换、且重视命令执行前确认的用户。 ACP 生态参与者。Users who need switchable multiple providers and who care about confir 2026-10-23 partial
QoQOQoder CN（原通义灵码）Qoder CN (formerly Lingma) IDE 形态IDE form 阿里云Alibaba Cloud 适合：要国内合规叙事（阿里云一方产品、国内主流大模型+国内云上部署，官方点名金融/政务客群）、 IDE/JetBrains 插件/CLI 三Fits: domestic compliance narrative (an official 'first-party Alibaba 2026-10-22 partial
QoQOQoderQoder IDE 形态IDE form 阿里云Alibaba Cloud 适合：要「IDE+插件+CLI+云端」一个账号全家的 agentic 编码闭环、Repo Wiki/记忆/Skills 上下文体系、 可 BFits: one account spanning IDE/plugin/CLI/cloud with a full agentic lo 2026-10-22 partial
ReREReplit AgentReplit Agent 厂商云形态Vendor cloud Replit 适合：从自然语言直接到「能上线的应用」（含数据库/部署）、非工程师做原型、要 checkpoint 回滚兜底。 不适合：要接你自己已有的代码Fits: idea straight to a deployable app (database/deploy included), no 2026-10-30 partial
TrTRTraeTrae IDE 形态IDE form 字节跳动ByteDance 适合：要桌面+Web+移动三端同一任务流、SOLO 模式整段委托、内置多模型免自己配 key 起步。 不适合：要国内版国际版功能一致的预期（Fits: one task flow across desktop+web+mobile, whole-task delegation v 2026-10-30 partial
v0V0v0v0 厂商云形态Vendor cloud VercelVercel 适合：Next.js/Vercel 栈团队（部署链原生打通）、要沙箱内跑真终端与预装 agent、 企业席位与 Vercel 账号体系统一。Fits: Next.js/Vercel-stack teams (the deployment chain is natively wir 2026-10-22 partial
WWAWarpWarp CLI 形态CLI form Warp 适合：在终端里同时做命令执行与编码 agent 工作、并希望团队协作与云自动化的用户。 特别适合： 想把终端工作流标准化为 WorkflowDevelopers who run both shell commands and coding agent work in the te 2026-10-23 partial
WWIWindsurf / Devin DesktopWindsurf / Devin Desktop IDE 形态IDE form Cognition 需要多模型供应商可选（不想被单一模型绑定）的人； 需要 ACP 以接入自定义 agent 的人（注意是 preview）； 需要远程主机（SPeople who want a choice of model providers rather than being locked t 2026-10-23 partial
ZZEZedZed IDE 形态IDE form Zed Industries 适合重视编辑器性能（Rust）、解析准确度（Tree-sitter）与多人协作的场景。 也适合想在一个编辑器里混用多种 CLI Agent Scenarios where editor performance (Rust), syntactic parsing accuracy 2026-10-23 partial

为什么这里不给总分排名Why there is no overall ranking

这不是省略，是方法上的明确取舍。This is not an omission but a deliberate methodological choice.

  • 缺统一实测，就不给分。跨工具的跑分口径不同——题目、预算、执行环境都不一样，A 的 90 分和 B 的 88 分不可比。No shared measurement, no score. Benchmarks across tools use different rules — different questions, budgets and environments. A 90 and a B 88 are not comparable.
  • 「未知」是合法答案。查不到就写「未知」并说明为什么，不用推测填充。缺信息本身也是信息。"Unknown" is a legitimate answer. If it cannot be found, we write "unknown" and explain why, instead of filling the gap with guesses. Missing information is itself information.
  • 来源链接、类型与核验日都在详情页里，可以逐条回去复核。The source link, its kind and the checked date are all on the detail page, so you can walk any of them back and re-check.
  • lifecycle 单独标注。核验日新不等于数据有效——上游归档后数据会失效，所以单独标 active / maintenance / archived。lifecycle is marked separately. A recent check date does not mean the data is still valid — it goes stale when upstream archives the repo, so active / maintenance / archived are tracked separately.
  • 不同族不混排。找现成的、自己搭的、接上与跑起来的是三种角色，坐标系不同；硬合成一张总表只会制造假的可比性。Families are not mixed. Ready-made tools, things you build yourself, and plug-in-and-run components are three different roles with different coordinate systems; forcing them into one master table would manufacture false comparability.

可信度标记怎么读How to read the confidence marks

详情页与上表都带Both the detail pages and the table above carry confidence，它反映, which reflects 本站数据的完整度how complete this site's data is，不是对产品的评价。, not a judgement of the product.

verified8 个维度均有官方源支撑，且核验日在 90 天内all 8 dimensions have official sources and were checked within 90 days
partial部分维度标为未知，或官方文档不可访问，或核验日超过 90 天some dimensions are marked unknown, or the official docs were unreachable, or checked over 90 days ago
stale官方已发布重大变化，本站尚未核验the vendor has shipped a significant change that this site has not re-checked

本站当前的完整度Current completeness on this site

数据层用Recheck this figure with node scripts/audit-gaps.mjs 可随时复核这个数字。. 下表实时计算（本页档案最后核验日 2026-10-30）：Computed from current data; profiles last checked 2026-10-30:

大类Category已补齐Filled说明Meaning
AI 编程AI coding 283/328 多为闭源产品，索引策略等细节官方不公开；CLI 类官方文档相对完整Mostly closed-source, so details like indexing strategy are not disclosed; CLI entries have better official docs

全站合计 1372/1896 维度已补齐Site-wide 1372/1896 dimensions filled（72%）

剩余未补齐项分三类：官方未公开（索引算法、沙箱实现细节本就不对外说明）、需实测才能确定（大仓库表现、CI 无 TTY 行为）、客观渠道不可达。The remaining gaps fall into three kinds: not disclosed by the vendor (indexing algorithms, sandbox internals are simply not documented), requires measurement (behaviour on very large repositories, CI without a TTY), and unreachable through objective channels.

我们选择留白而不是填「已支持」——错误的成本最终由使用者承担。We chose to leave a blank rather than fill in "supported" — the cost of an error is ultimately borne by whoever uses it.

数据来源与复核方式Sources and how to re-check them

全部数据来自开源仓库All data comes from the open-source repository speculcom/ai-handbook（CC BY 4.0）。 (CC BY 4.0).

每个条目都是纯 Markdown + frontmatter，含维度记录、证据链接、核验日与可信度标记。仓库内含：Every entry is plain Markdown plus frontmatter, carrying dimension records and an evidence chain with links, checked dates and confidence marks. The repository contains:

  • tools/METHODOLOGY.md —— 方法论总纲与核心规则the methodology charter and core rules
  • tools/axes/ —— 每个维度的定义与判定标准（含正反例）the definition and decision criteria for each dimension (with positive and negative examples)
  • tools/SCHEMA.md —— 数据格式规范与构建校验规则the data-format spec and build validation rules
  • tools/protocols/<大类><category>/_protocol.md —— 实测协议(the measurement protocol (尚未执行not yet run，故本站暂无实测结论), so this site has no measured conclusions)

发现错误或有新证据，欢迎提 Issue 或 PR——每条修正都会注明依据与影响范围。Found an error or have new evidence? Open an issue or a PR — each correction notes its basis and blast radius.