Deepseek PHP Client is a robust and community-driven PHP client library for seamless integration with the Deepseek API.
-
A conversational Q&A agent configuration system, self-hosted deployment solutions, and a convenient all-in-one application SDK, allowing you to create intelligent Q&A bots for your GitHub repositories.
+ FastGPT is an open-source AI knowledge base platform built on large language models (LLMs), supporting various models including DeepSeek and OpenAI. We provide out-of-the-box capabilities for data processing, model invocation, RAG retrieval, and visual AI workflow orchestration, enabling you to effortlessly build sophisticated AI applications.
+
RuZhi AI Notes is an intelligent knowledge management tool powered by AI, providing one-stop knowledge management and application services including AI search & exploration, AI results to notes conversion, note management & organization, knowledge presentation & sharing. Integrated with DeepSeek model to provide more stable and higher quality outputs.
TigerGPT is the first financial AI investment assistant of its kind based on OpenAI, developed by Tiger Group. TigerGPT aims to provide intelligent investment decision-making support for investors. On February 18, 2025, TigerGPT officially integrated the DeepSeek-R1 model to provide users with online Q&A services that support deep reasoning.
The simplest way to build great agents. Agents write python code to call tools and orchestrate other agents. Priority support for open models like DeepSeek-R1!
A foundational protocol framework for trusted communication between agents. Any agents based on DeepSeek, By integrating with the ATTPs SDK, can access features such as agent registration, sending verifiable data, and retrieving verifiable data. So that it can make trusted communication with agents from other platforms.
AI i18n for front-end developers. It can achieve fully automatic HTML translation with just two lines of JavaScript. You can switch among dozens of languages with a single click. There is no need to modify the page, no language configuration files are required, and it supports dozens of fine-tuning extension instructions. It is SEO-friendly. Moreover, it opens up a standard text translation API interface.
An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data.
AutoFlow is an open-source knowledge base tool based on GraphRAG (Graph-based Retrieval-Augmented Generation), built on TiDB Vector, LlamaIndex, and DSPy. It provides a Perplexity-like search interface and allows easy integration of AutoFlow's conversational search window into your website by embedding a simple JavaScript snippet.
DeepSearcher combines powerful LLMs (DeepSeek, OpenAI, etc.) and Vector Databases (Milvus, etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answer and comprehensive report.
An open-source SDK for encrypting AI with Fully Homomorphic Encryption (FHE) and integrating with Mind Network for agent consensus. FHE is considered the holy grail of cryptography, enabling computations directly on encrypted data without the need for decryption. With FHE, agents can safeguard their privacy while using Deepseek, ensuring both model integrity and result consensus - all without exposing their data - by connecting to Mind Network. The SDK source code is implemented in pure Rust> and the package also available on crates.io .
An intelligent RSS reader browser extension with AI-powered RSS summarization and multi-dimensional feed views. Supports DeepSeek model configuration for enhanced content understanding.
A Chrome extension that enables users to chat with DeepSeek by opening a sidebar on any website. In addition, it provides a floating menu underneath any selected text on any website that allows users to generate text summaries, check grammar issues, and translate content.
An intelligent assistant built on the Comfy-UI framework that simplifies and enhances the AI algorithm debugging and deployment process through natural language interactions.
一个开源 SDK，可使用**全同态加密（FHE）**对 AI 进行加密，实现代理共识。FHE被誉为密码学的圣杯，能够在无需解密的情况下直接对加密数据进行计算。借助FHE，代理在使用Deepseek时可以保护隐私，同时确保模型的完整性和计算结果的一致性，无需暴露任何数据。该SDK的源代码采用纯Rust实现，并可在crates.io获取
diff --git a/docs/HIX.AI/assets/logo.svg b/docs/HIX.AI/assets/logo.svg
new file mode 100644
index 0000000..ee496fc
--- /dev/null
+++ b/docs/HIX.AI/assets/logo.svg
@@ -0,0 +1 @@
+
diff --git a/docs/TigerGPT/assets/logo.png b/docs/TigerGPT/assets/logo.png
new file mode 100644
index 0000000..5f5e137
Binary files /dev/null and b/docs/TigerGPT/assets/logo.png differ
diff --git a/docs/fhe.mind-network/mind-network-log.png b/docs/fhe.mind-network/mind-network-log.png
new file mode 100644
index 0000000..1947fe6
Binary files /dev/null and b/docs/fhe.mind-network/mind-network-log.png differ
diff --git a/docs/translate.js/README.md b/docs/translate.js/README.md
new file mode 100644
index 0000000..b35d4b7
--- /dev/null
+++ b/docs/translate.js/README.md
@@ -0,0 +1,89 @@
+
+ translate.js
+
+
+ It is an AI i18n tool designed for front-end developers. With just two lines of JavaScript code, it can achieve fully automatic translation of HTML.
+ Leave it to the AI. There is no need to modify the page, no language configuration file is required, no API Key is needed, and it is SEO-friendly!
+
+
+
+
+
+# Usage method
+### 1. Deploy the text translation API
+First, deploy the text translation open interface. It supports batch translation of multiple texts at once and has a built-in multi-layer caching system, which minimizes the time-consuming process of AI translation. This enables users to achieve instant and delay-free translation when using it.
+
+##### 1.1 Server specifications
+It can run perfectly with the following server configuration: 1 core, 1GB of memory, a 20GB system disk, a bandwidth of 1MB, and the operating system being CentOS 7.4 (any version from 7.0 to 7.9 is acceptable).
+
+##### 1.2 Install
+````
+wget https://gitee.com/mail_osc/translate/raw/master/deploy/install_translate.service.sh -O install.sh && chmod -R 777 install.sh && sh ./install.sh
+````
+
+##### 1.3 Configure DeepSeek parameters
+
+Edit application.properties ，Edit command：
+````
+vi /mnt/tomcat8/webapps/ROOT/WEB-INF/classes/application.properties
+````
+Then append a few lines of configuration at the very end:
+````
+# The request URL of the large model interface. For example, the following is the request URL of Huawei DeepSeek. Additionally, the request URL of GiteeAI is https://ai.gitee.com/v1/chat/completions , You can obtain and fill in the information for other platforms by yourself.
+translate.service.deepSeek.url=https://infer-modelarts-cn-southwest-2.modelarts-infer.com/v1/infers/fd53915b-8935-48fe-be70-449d76c0fc87/v1/chat/completions
+# Access token
+translate.service.deepSeek.key=QM8jrVl98lTluLhzCaO4i9PFv-caRk6U7kDL-H6CIyApytMG69jO33aasO1GnduQak8fGI7dtpmbsM98Qh3ywA
+# Which model to use? Here, it is advisable to use DeepSeek-V3 by default, and there is no need to make any changes.
+translate.service.deepSeek.model=DeepSeek-V3
+# The maximum number of tokens for a single AI operation. If not set, the default value is 3000. You can just use this default value here.
+translate.service.deepSeek.max_tokens=3000
+````
+The final effect is shown in the following figure:
+
+
+##### 1.4 Restart the service
+````
+pkill java
+sudo /mnt/tomcat8/bin/startup.sh
+````
+
+##### 1.5 Test the text translation API.
+
+The "from" passed in here represents the language before translation. If you know what language it is, fill it in. If you don't know and it's difficult to judge, just fill it in as shown in the picture above. DeepSeek will automatically recognize and perform the translation.
+For detailed instructions on this translation API interface, please refer to: [http://api.zvo.cn/translate/service/20230807/translate.json.html](http://api.zvo.cn/translate/service/20230807/translate.json.html)
+
+
+
+### 2. Use translate.js in HTML.
+
+**Click on a certain language in an ordinary website to switch. **
+
+As shown in the following figure, there should be an option to switch among several languages at a certain position on the website.
+
+Directly add the following code at the end of its HTML code:
+
+````
+
+
+
+
+
+
+````
+
+This is just the use in the most common scenario. In addition, for various frameworks such as VUE, React, and so on, as well as all kinds of management backends, as long as JavaScript can be run, it can be used!
+
+# Open-source repository
+https://github.com/xnx3/translate
+
diff --git a/docs/translate.js/README_cn.md b/docs/translate.js/README_cn.md
new file mode 100644
index 0000000..fd364ad
--- /dev/null
+++ b/docs/translate.js/README_cn.md
@@ -0,0 +1,141 @@
+
+ translate.js
+
+
+ 它是面向前端开发者使用的 AI i18n，两行js实现html全自动翻译。
+ 交给AI，无需改动页面、无语言配置文件、无API Key、对SEO友好！
+
