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
Alibaba-NLP/CHRONOS
CHRONOS is a research project focused on news timeline summarization, introduced in a NAACL 2025 paper titled "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization." The project proposes a novel retrieval-based approach to timeline summarization by iteratively posing questions about the topic and the retrieved documents to generate chronological summaries. This method aims to improve the efficiency and scalability of timeline summarization, especially in open-domain settings. The project includes the release of an up-to-date dataset called Open-TLS, designed for open-domain timeline summarization. This dataset surpasses existing public datasets in both size and the duration of timelines, providing a more comprehensive resource for research in this area. The dataset includes news queries and corresponding ground truth timelines formatted in JSONL. CHRONOS is implemented with dependencies managed via Python, and it provides scripts for generating example questions and running the timeline summarization process. Users need to replace placeholder API keys with their own for services such as Qwen or GPT models, Bing Web Search API, and Jina for full-page content retrieval. The project also offers a web demo and integration with the ModelScope platform for interactive use. The approach demonstrated by CHRONOS achieves comparable results to state-of-the-art methods in closed-domain timeline summarization while offering significant improvements in efficiency and scalability for open-domain tasks. The repository includes detailed instructions for setup, running experiments, and accessing the dataset, making it a valuable resource for researchers and developers working on news summarization and information retrieval. Keywords extracted from the project include news timeline summarization, timeline summarization, retrieval-based approach, iterative self-questioning, open-domain timeline summarization, Open-TLS dataset, news retrieval, chronological summaries, efficiency, scalability, NAACL 2025, dataset release, question generation, API integration, and ModelScope demo.
https://github.com/Alibaba-NLP/CHRONOS
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.