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
YuxiangChai/AMEX-codebase
The AMEX-codebase repository is a project built upon the LLaMA2-Accessory framework, which is designed to facilitate working with large language models. This repository customizes and extends the original LLaMA2-Accessory by replacing the accessory folder with a modified version provided here. The project includes a model checkpoint hosted on Huggingface, specifically the GUIAgent-InternLM7B model, which can be used for various language model tasks. The repository provides detailed instructions for installation, data preparation, fine-tuning, and inference. For data preparation, users can run a Python script that processes data at different levels (l1, l2, l3, or all) to convert it into a question-answer format suitable for training or evaluation. Fine-tuning instructions are linked to the original LLaMA2-Accessory documentation, guiding users on how to adapt the model to their specific datasets or tasks. Inference can be performed either by following the original framework's instructions or by running a provided shell script, making it straightforward to generate predictions or responses from the fine-tuned model. The repository also showcases new experiments, including screenshots of experimental setups such as screenspot and android control experiments, indicating practical applications or demonstrations of the model's capabilities. Overall, the AMEX-codebase serves as an enhanced toolkit for leveraging the LLaMA2-Accessory framework with additional data processing utilities, fine-tuning capabilities, and inference scripts. It is particularly useful for researchers and developers interested in customizing large language models for specific tasks, supported by clear documentation and example experiments.
https://github.com/YuxiangChai/AMEX-codebase
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.