IntelligenceIntegrationSystem
Intelligence Integration System with AI and Workflow
Stars: 317
IntelligenceIntegrationSystem is an intelligence system that fetches public news from mainstream news websites, analyzes and scores them using AI. It falls under the category of OSINT. The system includes features for crawling, AI analysis, content filtering, and archiving. It aims to improve the quality of news by filtering out non-informative content and providing a platform for analyzing and sharing intelligence. The system utilizes MongoDB for storing intelligence documents and offers a web interface for users to access and interact with the collected data. It also provides tools for managing users, authentication, and web API services.
README:
情报整合系统:通过抓取主流新闻网站的公开新闻,并使用AI进行分析和评分的情报系统。属于OSINT的一种。
项目地址:https://github.com/SleepySoft/IntelligenceIntegrationSystem
从2026年2月15日开始,main分支将正式切换到v2版本。
同时v1版本归档到 这个分支。
v2版本兼容v1版本的数据,数据库不需要额外的升级操作。 最新导出的数据在 这里下载
关于v2版本的设计理念,以及与v1版本的区别,请阅读 这篇文章 。
除了情报数据结构及评分机制改变外,v2版本还对爬虫框架进行了进一步的改进。 一方面通过界面“所见即所得”的方式生成爬虫配置,另一方面增加了监控及调度功能,今后接入网站会非常方便。
另外向量数据库也进行了调整,但由于时间问题并没有正式应用到本次的更新中。 导出数据也包括了所有情报对应的向量数据,使用该向量数据启动向量数据库后,是可以使用相关功能的,只不过新情报不会更新到向量数据库而已。
经过调整后的向量数据库对关联情报的查询表现优异,接下来我会重点研究情报的聚合。
现在的新闻素质堪忧,特别是国内媒体。
-
一方面现代社会每日产生的新闻数量巨大,并且参杂着毫无情报价值的水文。
-
另一方面媒体看重点击量,所以标题成为了吸引点击的工具而非事件的概括。
我一直认为,公开信息中有四成只需要看标题,有两成看总结即可,而只有不到一成的信息有阅读全文的必要。而剩下的三成都是垃圾。
既然媒体们自己不体面,那么我来让新闻体面。
本程序核流程为:抓取 -> 提交到情报中心 -> 清洗、AI分析 -> 筛选并重发布 -> 归档
程序的结构如下:
本程序只通过RSS抓取公开新闻,原因在于这类新闻抓取难度小(本身就是给RSS阅读器的公开信息),且法律风险低。
程序中由CrawlerServiceEngine.py启动并驱动CrawlTasks目录下的抓取模块,
该服务框架会监控该目录下的文件更新并重新加载更新后的模块。
当前各个抓取模块主要通过CommonFeedsCrawFlow.py这个通用流程进行抓取并将抓取内容提交到IntelligenceHub。
抓取模块通过partial构建偏函数供抓取流程调用。
实际上采集数据只需要按照
class CollectedData定义格式将数据通过 POST 提交到/collect这个端点的网络服务即可。 唯一需要注意的是如果设置了安全Token,则提交数据时要将该凭据附上。至于数据的来源,IHub并不关心。使用通用流程的好处在于增加一个RSS源抓取非常方便,并且通用流程中实现了抓取记录和防重复抓取的功能。
如果想抓取非RSS源,或者需要抓取的网页需要特殊技术,则需要自己实现抓取器。同时注意法律风险。
当前实现的抓取方式有:
- RequestsScraper.py:用以抓取简单的内容。最快,但对于动态网页来说抓取不到。
- PlaywrightRawScraper.py:使用Playwright的无头浏览器抓取 ,速度一般,能抓取到一些requests抓取不到的网页。
- PlaywrightRenderedScraper.py:同是无头浏览器方案,但等待网页渲染完成,最慢,但成功率最高。
- Crawl4AI.py:未实现。
- IntelligenceHub.py(IHub):程序的核心。所有的信息都会提交汇总至此,由该模块进行处理、分析、归档,并提供查询功能。
- IntelligenceHubWebService.py:为IHub提供网络服务的模块,包括API、网页发布和鉴权。
- IntelligenceHubStartup.py:初始化所有子组件、IntelligenceHub和IntelligenceHubWebService。
-
IntelligenceHubLauncher.py:IHub的启动器,选用合适的backend载入IntelligenceHubWebService的wsgi_app,
[20250910] 提供Flask原生、waitress、gunicorn三种WSGI服务器,默认服务器为waitress。
注意gunicorn仅支持Linux。
该文件不包含业务代码,几乎全部由AI生成,没有阅读的必要。如果对启动原理不理解,可以去搜索WSGI的机制。
IHub的处理流程请参见:IIS_Diagram.drawio
情报分析的所有prompt。程序中的dict校验和该prompt指示的输出格式紧密相关,如果prompt改变,那么校验规则同样需要改变。
已知的问题为:
- 该prompt在小模型(甚至于65b)上表现不佳。
在小模型上AI通常不按规定格式输出,有可能是prompt + 文章内容太长,使AI无法集中注意力的缘故。
正式部署的环境使用的是满血云服务,这是一笔不小的开支。
- AI评分还是过于宽松,没有达到我的期望。
对于一些非情报新闻,AI还是给出了6分的评价,尽管我在prompt中强调不含情报的数据应该抛弃,但效果不佳。
对于情报的评分偏高,我理想中80%的新闻应当处于6分及以下的区间。
AI分析实现的主要文件。调用AI Client,组织数据、使用prompt进行分析,并解析和返回结果。
值得一提的是,自从使用了json_repair后,python的解析率几乎100%。接下来我会尝试在小模型上使用constrained decoding,看是否能提升表现。
如前所述,网络服务由IntelligenceHubWebService.py提供。包含以下内容:
-
登录与鉴权
由 WebServiceAccessManager 和 UserManager.py 进行管理。其中:
- API Token位于配置文件中:config_example.json
- 登录与注销的页面分别为:'/login','/logout'
- 用户信息保存在Authentication.db,通过UserManagerConsole.py管理用户。
-
WebAPI
'/api'接口:采用 ArbitraryRPC.py ,不用额外编码或配置即可调用Stub的所有函数,同时支持任意层次的转发调用。
'/collect'接口:收集采集情报。
其它API接口:子功能,如Log、统计、监控等等,由对应模块注册路由。
-
网页
不使用前后端的架构,所有内容由服务器生成。包括以下文件:
PostManager.py:根据 posts 目录下的markdown文件生成HTML。
ArticleRender.py:文章页面。
ArticleListRender.py:文章列表页面。
intelligence_search.html:文章查询页面(20251029:重构为前后端分离)。
(旧)ArticleTableRender.py:文章列表项。 (新)intelligence_table.js:文章列表项。
子功能页面,由对应模块提供,前后端分离。这里就不列出了,详见登录后的管理页面。
程序会生成以下内容:
-
情报存储(主要)
MongoDB,数据库名:IntelligenceIntegrationSystem。包含三个记录:
- intelligence_cached:Collector提交的采集到的原始新闻数据。
- intelligence_archived:经过处理并归档的数据。
-
向量数据库
供向量查询,保留。
如果开启,会存储于:IntelligenceIndex目录
-
鉴权信息
供 UserManager.py 使用,可通过 UserManagerConsole.py 工具进行管理。
-
抓取内容
分网站和RSS子项二级目录,可以通过查看抓取内容对抓取脚本进行问题分析。
-
对话内容
目录:conversion
和AI的沟通记录,可以通过查看记录对AI分析的效果进行评估。
-
生成网页
目录:generated
PostManager.py 生成的网页
- MongoDB
程序使用MongoDB数据库存储情报文档,这是一个NoSql数据库,请在官网下载:
https://www.mongodb.com/products/self-managed/community-edition
同时建议安装mongodb tools,用以导出及导出数据库(从某个版本开始命令行工具不再和MongoDB主程序打包):
本项目建议使用python版本为3.10以上。当然,不创建虚拟环境,直接使用系统默认的python环境也不是不行。
所谓python虚拟环境,其实非常简单,它就是一个目录,当你切换到这个虚拟环境时,使用的解析器、安装的库、使用的库,都仅限于该目录下,从而和其它环境隔离。
知道这个原理后,大家应该能想到:使用pycharm时,选择已创建的虚拟环境其实就是选择这个目录下的python.exe。
创建虚拟环境主要有三种方法:
- 原生的venv
- Anaconda(及其兼容方法)
- uv
# 创建虚拟环境
# - 通常在项目目录下执行以下命令,虚拟环境的python版本跟你当前运行的python环境有关
# - 对我来说,通常是在anaconda下创建一个指定版本python的虚拟环境,再使用这个虚拟环境创建venv
# - (那为什么不直接用anaconda?好问题。)
python -m venv .venv
# 切换到该虚拟环境(接下来安装依赖前都需要先切换到该虚拟环境,下同)
# ---- Windows ----
.venv\Scripts\activate.bat
# ----- Linux -----
source .venv/Scripts/activate
Anaconda好处是方便,缺点是重
下载:https://www.anaconda.com/download
# 创建虚拟环境
conda create -n iis python=3.10
# 切换到该虚拟环境
conda activate iis
这是现在流行的工具,非常轻量,而且快,不过我还不是很熟悉。以下内容来自AI。
# 安装uv
pip install uv
# 创建虚拟环境
uv venv
# 切换到该虚拟环境
.venv\Scripts\activate.bat
# 接下来可以使用pip install -r,也可以使用uv的方式安装依赖(自行查阅)。
# Clone this project to your local
git clone https://github.com/SleepySoft/IntelligenceIntegrationSystem.git
# Enter this project dir
cd IntelligenceIntegrationSystem
# Important: Fetch sub modules
git submodule update --init --recursive
# -------------------------------------------------------------------------------
# ! Reference to above: Create virtual environment and switch to this environment
# -------------------------------------------------------------------------------
# Old pip version will not support utf-8, so upgrade to newest pip first.
python.exe -m pip install --upgrade pip
# Install dependency
pip install -r requirements.txt
# If has dependency issue when using upper command
pip install -r requirements_freeze.txt
# ------------------------------------------------------------------------------------
# ! Before launching program, you should do some config first (read following section)
# ------------------------------------------------------------------------------------
# After pip install. Install playwright's headless browser
playwright install chromium
# Run main service
python IntelligenceHubLauncher.py
# Run collectors
python CrawlerServiceEngine.py
- 重要:运将 config_example.json 复制为 config.json,按照实际情况更改配置(默认能启动,但不能进行分析)。
配置主要在 IntelligenceHubStartup.py 中载入,阅读该文件可以知道各配置项的用法。
如果想使用AI进行情报分析,需要配置 ai_service 项,包括token。
如果想使用咸鱼上购买的批量14元key,需要配置 ai_service_rotator 项,指定key文件。
对于抓取外网新闻,需要配置 global_site_proxy。
- 重要:运行 UserManagerConsole.py ,按提示增加一个用户,设置密码。
-
程序运行后,打开 localhost:5000/login 输入刚才配置的账号密码进入后台页面。
-
打开localhost:5000则是无密码的公开页面。
- MongoDB工具
https://www.mongodb.com/try/download/database-tools
用以导出/导出MongoDB记录,可以配合mongodb_exporter.py一系列脚本使用。
{ domain: "voanews.com", nameCN: "美国之音", country: "USA", flag: "🇺🇸", accessibleInChina: false },
{ domain: "bbc.com", nameCN: "英国广播公司", country: "UK", flag: "🇬🇧", accessibleInChina: false },
{ domain: "cbc.ca", nameCN: "加拿大广播公司", country: "Canada", flag: "🇨🇦", accessibleInChina: false },
{ domain: "rfi.fr", nameCN: "法国国际广播电台", country: "France", flag: "🇫🇷", accessibleInChina: false },
{ domain: "dw.com", nameCN: "德国之声", country: "Germany", flag: "🇩🇪", accessibleInChina: false },
{ domain: "abc.net.au", nameCN: "澳大利亚广播公司", country: "Australia", flag: "🇦🇺", accessibleInChina: false },
{ domain: "elpais.com", nameCN: "国家报", country: "Spain", flag: "🇪🇸", accessibleInChina: false },
{ domain: "investing.com", nameCN: "英为财情", country: "International", flag: "🌍", accessibleInChina: true },
{ domain: "aljazeera.com", nameCN: "半岛电视台", country: "Qatar", flag: "🇶🇦", accessibleInChina: true },
{ domain: "aa.com.tr", nameCN: "阿纳多卢通讯社", country: "Turkey", flag: "🇹🇷", accessibleInChina: true },
{ domain: "nhk.or.jp", nameCN: "日本广播协会", country: "Japan", flag: "🇯🇵", accessibleInChina: true },
{ domain: "xinhuanet.com", nameCN: "新华社", country: "China", flag: "🇨🇳", accessibleInChina: true },如果有意见和建议,可以到这个讨论下留言:https://zhuanlan.zhihu.com/p/1957783829684154704
或者可以加入wx讨论组:
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for IntelligenceIntegrationSystem
Similar Open Source Tools
IntelligenceIntegrationSystem
IntelligenceIntegrationSystem is an intelligence system that fetches public news from mainstream news websites, analyzes and scores them using AI. It falls under the category of OSINT. The system includes features for crawling, AI analysis, content filtering, and archiving. It aims to improve the quality of news by filtering out non-informative content and providing a platform for analyzing and sharing intelligence. The system utilizes MongoDB for storing intelligence documents and offers a web interface for users to access and interact with the collected data. It also provides tools for managing users, authentication, and web API services.
meet-libai
The 'meet-libai' project aims to promote and popularize the cultural heritage of the Chinese poet Li Bai by constructing a knowledge graph of Li Bai and training a professional AI intelligent body using large models. The project includes features such as data preprocessing, knowledge graph construction, question-answering system development, and visualization exploration of the graph structure. It also provides code implementations for large models and RAG retrieval enhancement.
YesImBot
YesImBot, also known as Athena, is a Koishi plugin designed to allow large AI models to participate in group chat discussions. It offers easy customization of the bot's name, personality, emotions, and other messages. The plugin supports load balancing multiple API interfaces for large models, provides immersive context awareness, blocks potentially harmful messages, and automatically fetches high-quality prompts. Users can adjust various settings for the bot and customize system prompt words. The ultimate goal is to seamlessly integrate the bot into group chats without detection, with ongoing improvements and features like message recognition, emoji sending, multimodal image support, and more.
step-free-api
The StepChat Free service provides high-speed streaming output, multi-turn dialogue support, online search support, long document interpretation, and image parsing. It offers zero-configuration deployment, multi-token support, and automatic session trace cleaning. It is fully compatible with the ChatGPT interface. Additionally, it provides seven other free APIs for various services. The repository includes a disclaimer about using reverse APIs and encourages users to avoid commercial use to prevent service pressure on the official platform. It offers online testing links, showcases different demos, and provides deployment guides for Docker, Docker-compose, Render, Vercel, and native deployments. The repository also includes information on using multiple accounts, optimizing Nginx reverse proxy, and checking the liveliness of refresh tokens.
qwen-free-api
Qwen AI Free service supports high-speed streaming output, multi-turn dialogue, watermark-free AI drawing, long document interpretation, image parsing, zero-configuration deployment, multi-token support, automatic session trace cleaning. It is fully compatible with the ChatGPT interface. The repository provides various free APIs for different AI services. Users can access the service through different deployment methods like Docker, Docker-compose, Render, Vercel, and native deployment. It offers interfaces for chat completions, AI drawing, document interpretation, image parsing, and token checking. Users need to provide 'login_tongyi_ticket' for authorization. The project emphasizes research, learning, and personal use only, discouraging commercial use to avoid service pressure on the official platform.
spark-free-api
Spark AI Free 服务 provides high-speed streaming output, multi-turn dialogue support, AI drawing support, long document interpretation, and image parsing. It offers zero-configuration deployment, multi-token support, and automatic session trace cleaning. It is fully compatible with the ChatGPT interface. The repository includes multiple free-api projects for various AI services. Users can access the API for tasks such as chat completions, AI drawing, document interpretation, image analysis, and ssoSessionId live checking. The project also provides guidelines for deployment using Docker, Docker-compose, Render, Vercel, and native deployment methods. It recommends using custom clients for faster and simpler access to the free-api series projects.
glm-free-api
GLM AI Free 服务 provides high-speed streaming output, multi-turn dialogue support, intelligent agent dialogue support, AI drawing support, online search support, long document interpretation support, image parsing support. It offers zero-configuration deployment, multi-token support, and automatic session trace cleaning. It is fully compatible with the ChatGPT interface. The repository also includes six other free APIs for various services like Moonshot AI, StepChat, Qwen, Metaso, Spark, and Emohaa. The tool supports tasks such as chat completions, AI drawing, document interpretation, image parsing, and refresh token survival check.
newapi-ai-check-in
The newapi.ai-check-in repository is designed for automatically signing in with multiple accounts on public welfare websites. It supports various features such as single/multiple account automatic check-ins, multiple robot notifications, Linux.do and GitHub login authentication, and Cloudflare bypass. Users can fork the repository, set up GitHub environment secrets, configure multiple account formats, enable GitHub Actions, and test the check-in process manually. The script runs every 8 hours and users can trigger manual check-ins at any time. Notifications can be enabled through email, DingTalk, Feishu, WeChat Work, PushPlus, ServerChan, and Telegram bots. To prevent automatic disabling of Actions due to inactivity, users can set up a trigger PAT in the GitHub settings. The repository also provides troubleshooting tips for failed check-ins and instructions for setting up a local development environment.
metaso-free-api
Metaso AI Free service supports high-speed streaming output, secret tower AI super network search (full network or academic as well as concise, in-depth, research three modes), zero-configuration deployment, multi-token support. Fully compatible with ChatGPT interface. It also has seven other free APIs available for use. The tool provides various deployment options such as Docker, Docker-compose, Render, Vercel, and native deployment. Users can access the tool for chat completions and token live checks. Note: Reverse API is unstable, it is recommended to use the official Metaso AI website to avoid the risk of banning. This project is for research and learning purposes only, not for commercial use.
Senparc.AI
Senparc.AI is an AI extension package for the Senparc ecosystem, focusing on LLM (Large Language Models) interaction. It provides modules for standard interfaces and basic functionalities, as well as interfaces using SemanticKernel for plug-and-play capabilities. The package also includes a library for supporting the 'PromptRange' ecosystem, compatible with various systems and frameworks. Users can configure different AI platforms and models, define AI interface parameters, and run AI functions easily. The package offers examples and commands for dialogue, embedding, and DallE drawing operations.
EduChat
EduChat is a large-scale language model-based chatbot system designed for intelligent education by the EduNLP team at East China Normal University. The project focuses on developing a dialogue-based language model for the education vertical domain, integrating diverse education vertical domain data, and providing functions such as automatic question generation, homework correction, emotional support, course guidance, and college entrance examination consultation. The tool aims to serve teachers, students, and parents to achieve personalized, fair, and warm intelligent education.
oba-live-tool
The oba live tool is a small tool for Douyin small shops and Kuaishou Baiying live broadcasts. It features multiple account management, intelligent message assistant, automatic product explanation, AI automatic reply, and AI intelligent assistant. The tool requires Windows 10 or above, Chrome or Edge browser, and a valid account for Douyin small shops or Kuaishou Baiying. Users can download the tool from the Releases page, connect to the control panel, set API keys for AI functions, and configure auto-reply prompts. The tool is licensed under the MIT license.
illufly
illufly is an Agent framework with self-evolution capabilities, aiming to quickly create value based on self-evolution. It is designed to have self-evolution capabilities in various scenarios such as intent guessing, Q&A experience, data recall rate, and tool planning ability. The framework supports continuous dialogue, built-in RAG support, and self-evolution during conversations. It also provides tools for managing experience data and supports multiple agents collaboration.
Chat-Style-Bot
Chat-Style-Bot is an intelligent chatbot designed to mimic the chatting style of a specified individual. By analyzing and learning from WeChat chat records, Chat-Style-Bot can imitate your unique chatting style and become your personal chat assistant. Whether it's communicating with friends or handling daily conversations, Chat-Style-Bot can provide a natural, personalized interactive experience.
Gensokyo-llm
Gensokyo-llm is a tool designed for Gensokyo and Onebotv11, providing a one-click solution for large models. It supports various Onebotv11 standard frameworks, HTTP-API, and reverse WS. The tool is lightweight, with built-in SQLite for context maintenance and proxy support. It allows easy integration with the Gensokyo framework by configuring reverse HTTP and forward HTTP addresses. Users can set system settings, role cards, and context length. Additionally, it offers an openai original flavor API with automatic context. The tool can be used as an API or integrated with QQ channel robots. It supports converting GPT's SSE type and ensures memory safety in concurrent SSE environments. The tool also supports multiple users simultaneously transmitting SSE bidirectionally.
emohaa-free-api
Emohaa AI Free API is a free API that allows you to access the Emohaa AI chatbot. Emohaa AI is a powerful chatbot that can understand and respond to a wide range of natural language queries. It can be used for a variety of purposes, such as customer service, information retrieval, and language translation. The Emohaa AI Free API is easy to use and can be integrated into any application. It is a great way to add AI capabilities to your projects without having to build your own chatbot from scratch.
For similar tasks
meridian
Meridian is a tool that provides personalized daily intelligence briefings by scraping news from hundreds of sources, analyzing stories with AI, and delivering concise briefs. It offers key global events, context, implications analysis, and open-source transparency. Built for the curious who seek in-depth news beyond headlines without spending too much time. The tool uses multi-stage LLM processing for article and cluster analysis, smart clustering techniques to group related articles, and a web interface powered by Nuxt 3. The workflow involves scraping RSS feeds, processing articles with Gemini for relevance, clustering articles, and generating a final brief. The project leverages AI models like Gemini, multilingual embeddings, UMAP, and HDBSCAN for analysis. The tech stack includes Turborepo, Cloudflare services, TypeScript, PostgreSQL, and Nuxt 3 with Vue 3 and Tailwind for the frontend.
AIDailyNews
AIDailyNews is a tool that allows users to deploy their personalized daily news overview using GPT3 and Gemini Pro models. It collects content from RSS feeds every morning at 9 am, analyzes and summarizes it using GPT, and generates a daily report. Users can customize the RSS feeds they want to subscribe to and configure data collection environment variables for Github Action scheduled tasks. The tool supports AI services like GLM, OpenAI, and Google Gemini, allowing users to choose the AI provider, GPT model name, API key, and base URL. It also provides instructions for deploying the tool on Vercel for daily content summaries.
IntelligenceIntegrationSystem
IntelligenceIntegrationSystem is an intelligence system that fetches public news from mainstream news websites, analyzes and scores them using AI. It falls under the category of OSINT. The system includes features for crawling, AI analysis, content filtering, and archiving. It aims to improve the quality of news by filtering out non-informative content and providing a platform for analyzing and sharing intelligence. The system utilizes MongoDB for storing intelligence documents and offers a web interface for users to access and interact with the collected data. It also provides tools for managing users, authentication, and web API services.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.
