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

AI 工具AI Tools · Automation

AI 自动化与工作流AI automation & workflows

可视化/低代码搭 AI 工作流与 agent 的产品——交付物是「搭出来的应用/流程」，运行在平台的运行时上。给程序用的编排 SDK 归 framework；传统 RPA（无 LLM 主轴）归 nav。Visual / low-code platforms for building AI workflows and agents — the deliverable is the app or flow you assemble, running on the platform's runtime. SDKs for programmers go to frameworks; classic RPA without an LLM core goes to the nav site.

23 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 2026-11-03
  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.

全部对象All objects

按统一坐标系排列。点开任一对象可看到 模型与开放条件 / 运行位置 / 本地文件 / 关机后的任务 / 工具与扩展 / 上下文与记忆 / 权限与限制 / 适合什么任务 的完整记录、证据链接与未知项清单。Everything on one coordinate system. Open any object to see its full record across Model & openness / Where it runs / Local files / Tasks after shutdown / Tools & extensions / Context & memory / Permissions & limits / Best for, with source links and a list of unknowns.

ActivepiecesActivepieces

Activepieces Inc.

Activepieces 是开源低代码自动化平台：主体 MIT Expat，只有 ee/ 目录是商业许可区—— 比 n8n Activepieces is an open-source low-code automation platform: M

部分核验Partly verified 详情 →Details →

BotpressBotpress

Botpress

Botpress 是企业向客服场景的 AI agent 平台（首页当日招牌：enterprise-grade AI agenBotpress is an enterprise-oriented AI agent platform for custo

部分核验Partly verified 详情 →Details →

扣子 / CozeCoze

字节跳动ByteDance

扣子（Coze）是字节的云托管 agent 搭建平台：国内版主打「模型自由切换 + 云手机/云电脑常驻 + 微信/抖音/飞书Coze is ByteDance's cloud-hosted agent-building platform: the

部分核验Partly verified 详情 →Details →

DifyDify

LangGenius（国产出海）LangGenius (China-founded, global product)

Dify 是国产出海的 agentic 工作流平台：把提示词逻辑做成可见、可测、可交接的 Workflow/ChatflowDify is the China-origin, globally-facing agentic workflow pla

部分核验Partly verified 详情 →Details →

FastGPTFastGPT

labring（环际云，国产）labring (Huanji Cloud, China-origin)

FastGPT 是国产开源的 RAG 知识库问答与应用构建平台（文档主轴：知识库问答+agent/工作流编排）： 开源仓自托FastGPT is a China-origin open-source RAG knowledge-base Q&A a

部分核验Partly verified 详情 →Details →

FlowiseFlowise

FlowiseAI, Inc.

Flowise 是「画布搭 LLM 应用」的开山一代（LangChain 组件族的可视化封装）：RAG/agent 流原型极Flowise is the founding generation of “build LLM apps on a can

部分核验Partly verified 详情 →Details →

GumloopGumloop

Gumloop

Gumloop 是画布+连接器形态的企业向 AI agent 平台，多模型选择器是显性卖点（首页当日招牌：Build AI Gumloop is a canvas+connectors enterprise AI agent platform wi

部分核验Partly verified 详情 →Details →

LangflowLangflow

DataStax（原 Langflow AI）DataStax (Langflow AI origin)

Langflow 是 使用 MIT 许可的 LLM 画布平台，现归 DataStax—— 产品叙事向企业数据栈（AstraDLangflow is an LLM canvas platform with a whole-repository MIT

部分核验Partly verified 详情 →Details →

LindyLindy

Lindy

Lindy 是「雇一个 AI 员工」形态的云端自动化平台（首页当日招牌：Hire an AI Employee That GLindy is a cloud automation platform packaged as "hiring an AI

部分核验Partly verified 详情 →Details →

MakeMake

Make（原 Integromat）Make (formerly Integromat)

Make（原 Integromat）是「流程图派」的可视化自动化平台——分支、迭代、路由器在画布上比表单派更直白； AI 是Make (formerly Integromat) is the flowchart school of visual a

部分核验Partly verified 详情 →Details →

MaxKBMaxKB

飞致云（国产）Fit2Cloud (China-origin)

MaxKB 是飞致云出品的国产开源企业级智能体平台（官方博客当日口径：RAG 检索增强生成+工作流编排+技能 Skills+MaxKB is Fit2Cloud's China-origin open-source enterprise agent

部分核验Partly verified 详情 →Details →

n8nn8n

n8n GmbH

n8n 是「自动化优先」的低代码工作流平台——AI 是它众多节点里的一类，不是它的身份。 它最容易被误读的地方是许可：源码公n8n is an automation-first low-code workflow platform — AI is

部分核验Partly verified 详情 →Details →

Google OpalGoogle Opal

Google LabsGoogle Labs

Opal 是 Google Labs 的无代码 AI mini-app 搭建器：用自然语言描述，就能把生成、搜索、视频等步骤A no-code AI mini-app builder from Google Labs: describe it in

部分核验Partly verified 详情 →Details →

Relevance AIRelevance AI

Relevance AI（悉尼）Relevance AI (Sydney)

Relevance AI 主打「无代码搭 AI 员工团队」——多 agent 协作是它的叙事主轴，销售/运营自动化是主战场。Relevance AI leads with “build an AI workforce with no code” —

部分核验Partly verified 详情 →Details →

SmythOSSmythOS

SmythOS

SmythOS 现役真相面是 GitHub 上的开源 agent 运行时 SRE（仓描述当日在册：cloud-native SmythOS's current truth surface is the open-source agent runti

部分核验Partly verified 详情 →Details →

VoiceflowVoiceflow

Voiceflow

Voiceflow 是企业向客服/CX 场景的对话与语音 agent 画布平台（首页当日招牌：Enterprise ConvVoiceflow is an enterprise-oriented conversational & voice age

部分核验Partly verified 详情 →Details →

ZapierZapier

Zapier

Zapier 是「连接器生态」的代名词——6000+ SaaS 集成的云托管自动化平台， 官方叙事已把 AI/agent（CZapier is the synonym for the connector ecosystem — a cloud-ho

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
AcACActivepiecesActivepieces 网页服务Web service Activepieces Inc. 适合：要 MIT 主体许可的自托管自动化、要可魔改的低代码。 不适合：要企业功能开箱（在 ee 商业线）；要连接器生态与 Zapier 同量A fit for: MIT-level license freedom, self-hosting, reading and modify 2026-10-30 partial
SaSASalesforce AgentforceSalesforce Agentforce 网页服务Web service Salesforce 适合：Salesforce 存量企业（客服/销售场景）、要 CRM 上下文开箱即用。 不适合：不在 Salesforce 生态（价值锚点消失A fit for: Salesforce incumbents' service/sales automation, CRM contex 2026-10-30 partial
AuAUAutoGPT（现 Experts AI 团队平台）AutoGPT (now the Experts AI-team platform) 网页服务Web service AutoGPT（Determinist Ltd 运营）AutoGPT (operated by Determinist Ltd) 适合：多步异步的「AI 团队」委托式工作（内容/销售/研究）、要开源自托管（平台 Polyform Shield+ classic MIT Fits: multi-step asynchronous delegated "AI team" work (content/sales/ 2026-10-30 partial
BeBEBedrock Agents / AgentCoreBedrock Agents / AgentCore 网页服务Web service AWS 适合：AWS 存量企业、要 IAM 级治理、要「框架无关的托管运行时」（AgentCore）。 不适合：不在 AWS 生态；要自托管。A fit for: AWS incumbents, IAM-level enterprise governance, “any frame 2026-10-30 partial
BoBOBotpressBotpress 网页服务Web service Botpress 适合：客服/支持场景的 agent 平台（工单分流、升级交接、AI 动作）、要现成集成生态（CRM/帮助台）。 不适合：要产品本体开源（主仓Fits: support-ticket agents (deflection, escalation & handoff, AI acti 2026-10-30 partial
MiMIMicrosoft Copilot StudioMicrosoft Copilot Studio 网页服务Web service Microsoft 适合：Microsoft 365/Power Platform 存量企业、要企业治理现成、要 M365 生态内分发。 不适合：不在 MicrA fit for: M365/Power Platform incumbents, ready-made enterprise gover 2026-10-30 partial
扣子CO扣子 / CozeCoze 网页服务Web service 字节跳动ByteDance 适合：国内分发链路（微信/抖音/飞书）直达的 agent 搭建、国产模型自由切换、零部署。 不适合：要自托管掌控数据；要源码级控制（归 frA fit for: domestic distribution channels, free switching among Chines 2026-10-30 partial
DiDIDifyDify 网页服务Web service LangGenius（国产出海）LangGenius (China-founded, global product) 适合：要「提示词逻辑变成可见执行路径」的团队、要自托管的国产出海栈、知识库+agent 一体。 不适合：要源码做多租户 SaaS（需商业授权A fit for: teams wanting “product/legal/engineering aligned on one can 2026-10-30 partial
FaFAFastGPTFastGPT 网页服务Web service labring（环际云，国产）labring (Huanji Cloud, China-origin) 适合：中文知识库问答/RAG 应用（自托管可控）、要大陆直连的托管入口（fastgpt.cn）。 不适合：要纯 Apache 2.0 无附加Fits: Chinese knowledge-base Q&A / RAG apps (self-hosted and controlla 2026-10-30 partial
FlFLFlowiseFlowise 网页服务Web service FlowiseAI, Inc. 适合：画布搭 LLM 应用（RAG/agent 流）起步快、要自托管。 不适合：要企业功能开箱；要活跃发版节奏（2026-08 后推送放缓—A fit for: fast LLM-app prototyping (RAG, agent flows), self-hosting, 2026-10-30 partial
GuGUGumloopGumloop 网页服务Web service Gumloop 适合：GTM/客服场景的多模型 agent（画布+连接器）、要按 credits 统一用量治理（Model Providers 面板）。 不Fits: multi-model agents for GTM/support (canvas + connectors + Skills 2026-10-30 partial
LaLALangflowLangflow 网页服务Web service DataStax（原 Langflow AI）DataStax (Langflow AI origin) 适合：要 MIT 许可的 LLM 画布、要 Python 自定义组件、DataStax 栈。 不适合：要开箱企业治理（在托管线）。A fit for: MIT-level freedom, writing custom components in Python, Dat 2026-10-30 partial
LiLILindyLindy 网页服务Web service Lindy 适合：邮件/日历/通话/CRM 的「AI 员工」自动化（定时例程、演示即学）、要 1,500+ 集成与 MCP。 不适合：要自托管、要大陆直Fits: email/calendar/call/CRM routine automation (scheduled routines, 2026-10-30 partial
MaMAMakeMake 网页服务Web service Make（原 Integromat）Make (formerly Integromat) 适合：可视化流程图式自动化、复杂分支/迭代逻辑比 Zapier 表单更直白。 不适合：要自托管；要 AI 是产品主轴（它是自动化主轴）。A fit for: visual scenarios with complex branches/data transforms, cro 2026-10-30 partial
MaMAMaxKBMaxKB 网页服务Web service 飞致云（国产）Fit2Cloud (China-origin) 适合：企业内网自托管知识库问答（数据不出域）、要 MCP 工具调用与工作流编排的国产开源方案、 要已备案的合规叙事（算法备案双条目在册）。 Fits: intranet self-hosted KB Q&A (data never leaves the domain), a Ch 2026-10-30 partial
n8N8n8nn8n 网页服务Web service n8n GmbH 适合：跨系统自动化为主轴、要把 AI 节点嵌进既有流程、要自托管掌控数据。 不适合：要把 n8n 包进自己产品卖给客户（需商业协议）；要纯代A fit for: cross-system automation as the main axis, embedding AI node 2026-10-30 partial
GoGOGoogle OpalGoogle Opal 网页服务Web service Google LabsGoogle Labs 适合：不写代码、想把「生成 + 搜索 + 视频」串成小应用的人；需要快速做原型并分享。 不适合：要自托管、要模型自选、要长期稳定生产（官方已Fits people who do not code and want to chain generation, search and v 2026-11-03 partial
PiPIPipedream（Connect / Workflows）Pipedream（Connect / Workflows） 网页服务Web service Pipedream 适合：开发者向自动化（代码+界面混合）、要做「被集成」的 SaaS（Connect 线）。 不适合：完全不想碰代码的团队（那是 ZapierA fit for: engineers automating, wanting code-level control plus a hos 2026-10-30 partial
ReRERelevance AIRelevance AI 网页服务Web service Relevance AI（悉尼）Relevance AI (Sydney) 适合：无代码搭「多 agent 协作」工作流、销售/运营自动化场景。 不适合：要自托管；要代码级控制（归 framework）。A fit for: no-code multi-agent workflows, sales/operations scenario au 2026-10-30 partial
SmSMSmythOSSmythOS 网页服务Web service SmythOS 适合：要 MIT 许可的 agent 运行时自托管（local/cloud/edge）、读源码评估 agent 编排设计。 不适合：要活跃产Fits: self-hosting an MIT-licensed agent runtime (local/cloud/edge), r 2026-10-30 partial
VeVEVertex AI Agent Builder（Gemini Enterprise 平台线）Vertex AI Agent Builder 网页服务Web service Google 适合：GCP 存量企业、要 Gemini 原生栈、要企业治理现成。 不适合：不在 GCP 生态；要自托管。A fit for: GCP incumbents, Gemini-native stacks, ready-made enterprise 2026-10-30 partial
VoVOVoiceflowVoiceflow 网页服务Web service Voiceflow 适合：客服/CX 场景的对话与语音 agent（画布编排、企业交付）、要现成客户案例与合规叙事。 不适合：要自托管（未见官方发行）、要大陆直Fits: CX/support conversational & voice agents (canvas orchestration, 2026-10-30 partial
ZaZAZapierZapier 网页服务Web service Zapier 适合：SaaS 生态自动化为主轴、要把 AI agent 挂到现成连接器上、完全不碰部署。 不适合：要数据不出自有环境；要免费自托管。A fit for: SaaS-to-SaaS automation as the main axis, hooking AI agents 2026-10-30 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 2026-11-03）：Computed from current data; profiles last checked 2026-11-03:

大类Category已补齐Filled说明Meaning
自动化编排Automation 86/184 平台产品的功能文档充分，运行时内部与额度计费细节变动频繁Platform feature docs are solid; runtime internals and quota mechanics change often

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.