kepano/obsidian-skills
Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we...
Awesome AI Agents › AI Agent Development
LLaVA-VL/LLaVA-Plus-Codebase
LLaVA-Plus is a project focused on developing large language and vision assistants that can plug in and learn to use various skills and tools for multimodal tasks. The project aims to enable large multimodal models (LMM) to utilize external tools for general vision tasks, enhancing their capabilities beyond basic language and vision understanding. The repository provides a comprehensive codebase for training, evaluating, and deploying these assistants. It includes instructions for installation, launching demos, and training the models. The project is designed primarily for Linux users, with additional instructions for macOS and Windows. The demo setup involves launching a controller, model workers, tool workers, and a Gradio web server to provide a user interface. Training the model involves two stages: feature alignment and visual instruction tuning, with support for multi-GPU setups and memory optimization techniques like LoRA and DeepSpeed ZeRO. The project also offers a model zoo with pre-trained checkpoints and a dataset for training. The data and models are licensed for research use only, with restrictions on commercial use. The project is actively maintained, with ongoing updates and preparations for additional features and weights. It integrates with other projects for tool workers and provides detailed guidelines for usage and training. Overall, LLaVA-Plus represents an advanced effort to create versatile AI assistants capable of understanding and interacting with visual and textual information through learned tool usage.
https://github.com/LLaVA-VL/LLaVA-Plus-Codebase
Also in AI Agent Development
Panniantong/Agent-Reach
Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.
JCodesMore/ai-website-cloner-template
This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.
huggingface/smolagents
Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.
alibaba/page-agent
Page Agent is a JavaScript in-page GUI agent enabling natural language control of web interfaces without browser extensions or headless browsers, supporting various LLMs.
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.
titanwings/distilly
A meta-skill that distills messages, documents, interviews and public sources about a person into a source-grounded Person Profile, packaged as an Agent Skill for coding agents and chat bots.
coze-dev/coze-studio
Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.