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
zai-org/GLM-4.5
GLM-4.5 is an open-source large language model developed by Z.ai, designed specifically for intelligent agents. It features a series of foundation models with a focus on hybrid reasoning capabilities, combining reasoning, coding, and intelligent agent functionalities to address complex application demands. The flagship GLM-4.5 model contains 355 billion total parameters with 32 billion active parameters, while the more compact GLM-4.5-Air model has 106 billion total parameters and 12 billion active parameters. Both models support two operational modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses, making them versatile for various intelligent agent tasks. The project provides open-source access to the base models, hybrid reasoning models, and FP8 precision versions under the MIT license, allowing commercial use and secondary development. GLM-4.5 has demonstrated strong performance, ranking third among proprietary and open-source models across 12 industry-standard benchmarks with a score of 63.2, while GLM-4.5-Air offers competitive results with higher efficiency. Users can experience the models via platforms like Hugging Face and ModelScope or download them directly. The repository also details system requirements for inference and fine-tuning, specifying GPU configurations and precision formats such as BF16 and FP8. The models support extensive context lengths up to 128K tokens and can be fine-tuned using strategies like LoRA, SFT, and reinforcement learning with various GPU setups. The project includes integration with popular frameworks such as transformers, vLLM, and SGLang, providing code for model execution, tool parsing, and reasoning parsing. Comprehensive documentation, technical reports, and community support through WeChat and Discord are available to assist users. Overall, GLM-4.5 is a powerful, flexible, and accessible large language model tailored for advanced intelligent agent applications.
https://github.com/zai-org/GLM-4.5
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.