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
pguso/ai-agents-from-scratch
The project 'AI Agents From Scratch' by pguso is an educational repository designed to teach users how to build AI agents locally from first principles without relying on external frameworks. It focuses on using local large language models (LLMs) and the node-llama-cpp library to provide a deep understanding of how AI agents function under the hood. The repository emphasizes learning by building, allowing users to grasp the fundamental workings of LLMs, the concept of agents as a combination of LLMs, tools, and reasoning patterns, and the architectural choices made by popular frameworks. The project is structured into progressive learning phases, starting with basic LLM interaction, moving through specialized behaviors, reasoning, parallel processing, streaming responses, function calling, memory management, and culminating in the implementation of the ReAct pattern for iterative reasoning and acting. Each phase includes code examples, detailed code explanations, and conceptual overviews to facilitate comprehensive learning. The repository also plans to extend into re-implementing core parts of popular frameworks like LangChain and LangGraph in plain JavaScript to deepen understanding of framework internals. The project requires Node.js 18+ and sufficient RAM to run local models, which users must download and place in a specified folder. It includes utilities like a PromptDebugger for inspecting prompts sent to the LLM. Overall, this repository is a valuable resource for developers and researchers interested in AI agent development, providing hands-on experience with local LLMs, function calling, memory systems, and advanced agent architectures such as ReAct, all aimed at demystifying AI agents and empowering users to build their own from scratch.
https://github.com/pguso/ai-agents-from-scratch
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.