百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
C

ChatScript

> 编程语言
开源

状态 ChatScript 的以前的存储库位于 https://GitHub.com/bwilcox-1234/ChatScript,但我失去了对这个存储库的访问权限(2 …

393 stars0 点赞0 次浏览
访问官网GitHub

工具介绍

状态 ChatScript 的以前的存储库位于 https://GitHub.com/bwilcox-1234/ChatScript,但我失去了对这个存储库的访问权限(2 …

Status

The former repository of ChatScript was at https://github.com/bwilcox-1234/ChatScript, however, I lost access to this repository (2 factor authentication lost that I didn't want in the first place and I could not convince github to restore my access). So it is no longer maintained. But the global user ChatScript became available, and is a better name anyway.

ChatScript

Natural Language tool/dialog manager

ChatScript is the next generation chatbot engine that has won the Loebner's 4 times and is the basis for natural language company for a variety of tech startups.

ChatScript is a rule-based engine, where rules are created by humans writers in program scripts through a process called dialog flow scripting. These use a scripting metalanguage (simply called a "script") as their source code. Here what a ChatScript script file looks like:

…

Above example mentioned in article How to build your first chatbot using ChatScript.

Basic Features

  • Powerful pattern matching aimed at detecting meaning.
  • Simple rule layout combined with C-style general scripting.
  • Built-in WordNet dictionary for ontology and spell-checking.
  • Extensive extensible ontology of nouns, verbs, adjectives, adverbs.
  • Data as fact triples enables inferencing and supports JSON representation.
  • Rules can examine and alter engine and script behavior.
  • Remembers user interactions across conversations.
  • Document mode allows you to scan documents for content.
  • Ability to control local machines via popen/tcpopen/jsonopen.
  • Ability to read structured JSON data from websites.
  • Built in english pos-tagging and parsing
  • Postgres and Mongo databases support for big data or large-user-volume chatbots.

OS Features

  • Runs on Windows or Linux or Mac or iOS or Android
  • Fast server performance supports a thousand simultaneous users.
  • Multiple bots can cohabit on the same server.

Support Features

  • Mature technology in use by various parties around the world.
  • Integrated tools to support maintaining and testing large systems.
  • UTF8 support allows scripts written in any language
  • User support forum on chatbots.org
  • Issues or bugs on this repo

Getting started

Installation

Take this project and put it into some directory on your machine (typically we call the directory ChatScript, but you can name it whatever). That takes care of installation.

bash
git clone https://github.com/ChatScript/ChatScript

Standalone mode - run locally on a console (for developement/test)

From your ChatScript home directory, go to the BINARIES directory:

bash
cd BINARIES

And run the ChatScript engine

Windows

bash
ChatScript

Linux

bash
./LinuxChatScript64 local

Note: to set the file executable: chmod a+x ./LinuxChatScript64

MacOS

bash
./MacChatScript local

This will cause ChatScript to load and ask you for a username. Enter whatever you want. You are then talking to the default demo bot Harry.

Server Mode (for production)

From your ChatScript home directory, go to the BINARIES directory and run the ChatScript engine as server

Run the server on Windows

bash
ChatScript port=1024

Run the server on Linux

bash
./LinuxChatScript64

Run the server on MacOS

bash
./MacChatScript

This will cause ChatScript to load as a server.
But you also need a client (to test client-server communication). You can run a separate command window and go to the BINARIES directory and type

Run a client (test) on Windows

bash
ChatScript client=localhost:1024 

Run a client (test) on Linux

bash
./LinuxChatScript64 client=localhost:1024

Run a client (test) on MacOS

bash
./MacChatScript client=localhost:1024

This will cause ChatScript to load as a client and you can talk to the server.

How to build a bot

Run ChatScript locally. From the ChatScript command prompt, type

:build Harry

or whatever other preinstalled bot exists. If you have revised basic data, you can first:

:build 0

How to compile the engine.

On windows if you have Visual Studio installed, launch VS2010/chatscript.sln or VS2015/chatscript.sln and do a build. The result will go in the BINARIES directory.

On Linux, go stand in the SRC directory and type make server (assuming you have make and g++ installed). This creates BINARIES/ChatScript, which can run as a server or locally. There are other make choices for installing PostGres or Mongo.

Docker image

Building the base Docker image

The Dockerfile in this repository provides a ChatScript server with no bots. To build and run it, run the following commands:

bash
docker build -t chatscript .
docker run -it -p 1024:1024 chatscript

Note: You will probably want to replace the image tag chatscript with a more meaningful one for your purposes.

Building a Docker image containing bot data

Adding bot data to the base image above is as simple as writing a Dockerfile like the following one, which builds the Harry bot:

FROM chatscript

# Copy raw data needed for Harry
COPY ./RAWDATA/filesHarry.txt
COPY ./RAWDATA/HARRY /opt/ChatScript/RAWDATA/HARRY
COPY ./RAWDATA/QUIBBLE /opt/ChatScript/RAWDATA/QUIBBLE

# Build Harry
RUN /opt/ChatScript/BINARIES/LinuxChatScript64 local build1=filesHarry.txt

This Dockerfile can then be built and run in the same manner as the base chatscript image:

bash
docker build -t chatscript-harry .
docker run -it chatscript-harry local

Full Documentation

ChatScript Wiki (user guides, tutorials, papers)

Contributing

  1. Fork it
  2. Create your feature branch (git checkout -b my-new-feature)
  3. Commit your changes (git commit -am 'Add some feature')
  4. Push to the branch (git push origin my-new-feature)
  5. Create new Pull Request

Last releases

changes.md

Author

  • Bruce Wilcox
    • home website: BrilligUnderstanding.com
    • mail: [email protected]

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

C++

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言