Awesome AI AgentsProgramming Languages

MODSetter/SurfSense

⭐ 16139 TypeScript added to this list on 2025-03-20 repository created 2024-07-30

SurfSense is a highly customizable AI research agent designed to enhance personal knowledge management and research capabilities by integrating with various external sources. It functions similarly to tools like NotebookLM and Perplexity but offers deeper integration with personal knowledge bases and multiple external platforms such as search engines (Tavily), Slack, Linear, Notion, YouTube, GitHub, and more. The project supports uploading multiple file formats (27 supported extensions) to build a personal knowledge base, enabling users to quickly search and interact with their saved content through natural language queries. It provides cited answers, ensuring the reliability of information, and supports privacy-focused local large language models (LLMs) like Ollama. SurfSense is open source and self-hostable, allowing users to deploy it locally for full control. The system employs advanced retrieval-augmented generation (RAG) techniques, supporting over 150 LLMs and 6000 embedding models, along with major rerankers such as Pinecode, Cohere, and Flashrank. It uses hierarchical indices and hybrid search methods combining semantic and full-text search with reciprocal rank fusion for efficient and accurate information retrieval. The platform also offers a cross-browser extension to save webpages, including those behind authentication, directly into the knowledge base. SurfSense is actively developed and not yet production-ready, with features like podcast integration currently being reworked. It requires setup of dependencies such as pgvector for vector search, Unstructured.io API for document parsing, and Google OAuth for authentication. The backend is built to be run via Docker or manual setup, with environment variables for database connection, authentication, embedding models, and API keys. The frontend is a Next.js application, and the browser extension is built using the Plasmo framework. Overall, SurfSense aims to provide a powerful, customizable, and privacy-conscious AI research assistant that integrates seamlessly with personal and external data sources to facilitate efficient knowledge discovery and management.

https://github.com/MODSetter/SurfSense

aceternity-uiadvanced-rag-techniquesagentagentsaiai-research-agentchrome-extensioncited-answerscross-browser-extensiondockerembedding-modelsextensionexternal-sources-integrationfastapifile-uploadinggithubgleangoogle-oauthhierarchical-indiceshybrid-searchlangchainlinearllm-supportlocal-llm-supportmultiple-file-formatsnatural-language-interactionnext.jsnextjsnextjs15notebooklmnotionollamaopen-sourceperplexityperplexity-aipersonal-knowledge-baseplasmo-frameworkprivacypythonragrerankerssearch-enginesself-hostableslacktypescriptwebpage-savingyoutube

Also in Programming Languages

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.

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.

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.