Fosowl/agenticSeek
AgenticSeek is a fully local, autonomous AI assistant powered by Deepseek R1 agents that can code, browse the web, and manage files without relying on cloud services, ensuring user data privacy and eliminating ongoing costs.
Awesome AI Agents › Programming Languages
developersdigest/llm-answer-engine
The project "llm-answer-engine" is a sophisticated answer engine inspired by Perplexity, designed to provide comprehensive and efficient responses to user queries by leveraging multiple advanced technologies. It integrates Groq, Mistral AI's Mixtral, Langchain.JS, Brave Search, Serper API, and OpenAI to deliver answers, sources, images, videos, and follow-up questions. The engine is built using Next.js, a React framework, and styled with Tailwind CSS, ensuring a modern and responsive user interface. It also utilizes the Vercel AI SDK for building AI-powered streaming text and chat interfaces. The engine processes and understands user queries through Groq and Mixtral, while Langchain.JS handles text operations like splitting and embeddings. Brave Search and Serper API are employed to fetch relevant content, images, and videos, enhancing the richness of the answers. OpenAI embeddings create vector representations of text chunks, and Cheerio is used for HTML parsing to extract content from web pages. Optional features include Ollama for streaming inference and embeddings, Upstash Redis for rate limiting, and Upstash Semantic Cache for faster response times. The project provides detailed setup instructions, including obtaining necessary API keys from OpenAI, Groq, Brave Search, and Serper. It supports both Docker and non-Docker installations, making it accessible for various development environments. Configuration options allow customization of inference models, embeddings, text chunk sizes, and other parameters to optimize performance. Function calling support is in beta, enabling integration with APIs for maps, shopping, stock data, and Spotify, with the possibility to extend functionality through community contributions. Ollama support is partially implemented, offering streaming text responses and embeddings with some limitations. Overall, this project serves as an excellent foundation for developers interested in building advanced natural language processing and search-based answer engines, combining multiple cutting-edge tools and APIs to deliver rich, context-aware responses.
https://github.com/developersdigest/llm-answer-engine
Also in Programming Languages
MODSetter/SurfSense
SurfSense is a highly customizable AI research agent that integrates with personal knowledge bases and external sources to provide advanced, privacy-conscious research and knowledge management capabilities.
HKUDS/AI-Researcher
AI-Researcher is a fully automated scientific discovery platform powered by large language models that autonomously conducts research from idea generation to manuscript creation.
InternLM/xtuner
XTuner is a comprehensive and efficient toolkit for fine-tuning large language and vision-language models, supporting a wide range of models and training algorithms with scalability and flexibility.
run-llama/LlamaIndexTS
LlamaIndexTS is a lightweight, extensible data framework designed to integrate large language models into server-side JavaScript applications, supporting multiple runtimes and a wide range of LLM providers.
EgoAlpha/prompt-in-context-learning
An open-source comprehensive resource and engineering guide for mastering in-context learning and prompt engineering with large language models like ChatGPT, GPT-3, and FlanT5.
AnotiaWang/deep-research-web-ui
Deep Research Web UI is a secure, AI-powered web interface that enables iterative, deep research by combining search engines, web scraping, and large language models with real-time feedback and exportable research reports.
rotemweiss57/gpt-newspaper
GPT Newspaper is an AI-driven autonomous agent system that creates personalized newspapers tailored to individual user preferences by automating news curation, writing, design, and publishing.