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
lancedb/vectordb-recipes
VectorDB-recipes is a comprehensive repository designed to help developers and data scientists build Generative AI (GenAI) applications using LanceDB, an open-source, serverless vector database. The repository offers a rich collection of high-quality resources, including examples, applications, starter code, and tutorials that facilitate rapid prototyping and development of AI projects. LanceDB stands out by requiring no setup and seamlessly integrating with the Python data ecosystem, supporting tools like pandas, Arrow, and Pydantic. It also provides a native TypeScript SDK, enabling vector search capabilities within serverless functions. The repository is organized into two main sections: Examples and Applications. The Examples section provides minimal introductory content to quickly move users from concept to proof of concept (PoC). It includes various categorized examples such as building AI applications from scratch, multimodal applications that handle text and images, retrieval-augmented generation (RAG) combining document retrieval with LLM-powered responses, vector search techniques, chatbot creation, evaluation of AI-generated answers, AI agents collaboration, recommender systems, and foundational AI concepts. The Applications section features ready-to-use Python and web applications that leverage LLMs, VectorDB, and GenAI tools for practical use cases. The repository also highlights new projects and integrations, such as monitoring and tracing RAG workflows using HoneyHive. VectorDB-recipes is ideal for developers looking to explore and implement advanced AI functionalities like multimodal search, chatbots, and recommendation systems with minimal setup. It supports both local and cloud-based LLMs and offers interactive notebooks and scripts to facilitate learning and experimentation. The community support via Discord and updates through Twitter further enhance the user experience. Keywords: Generative AI, LanceDB, vector database, serverless, Python integration, TypeScript SDK, vector search, multimodal AI, retrieval-augmented generation, chatbots, AI agents, recommender systems, tutorials, examples, applications, GenAI projects, AI development, open-source
https://github.com/lancedb/vectordb-recipes
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.
developersdigest/llm-answer-engine
A Perplexity-inspired answer engine built with Next.js and multiple AI and search technologies to provide rich, context-aware responses including sources, images, videos, and follow-up questions.
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.