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
langwatch/better-agents
Better Agents is a command line tool and an accompanying set of standards for structuring agent projects. Installed globally through npm or run with npx, its init command walks the developer through choosing a programming language, an agent framework such as Agno, Mastra or LangGraph, a coding assistant, an LLM provider and API keys, then generates a project laid out according to the Better Agent Structure. That structure places agent code under app or src following the chosen framework, end-to-end scenario tests and Jupyter evaluation notebooks under tests, versioned prompt files in YAML under prompts with a prompts.json registry, an .mcp.json file wiring up MCP servers, and an AGENTS.md file holding development guidelines. The generated AGENTS.md and MCP configuration are the core idea: they turn a general coding assistant such as Claude Code, Cursor, Antigravity or the Kilocode CLI into one that knows the conventions of the selected agent framework and knows how to write tests for it, so that every new feature added by the assistant arrives with tests, evaluations and versioned prompts. Scenario tests, from the related Scenario project, simulate conversations with the agent to check that it behaves as expected, while evaluation notebooks hold datasets for measuring individual pipeline stages such as retrieval or classification. Prompts are synced through the LangWatch prompt management CLI so a team can iterate on them in a playground and keep history. Generated projects are instrumented for observability from the start. Requirements are Node.js 22 or newer, a supported coding assistant, a LangWatch API key and a provider key. Anonymous telemetry is on by default and can be disabled with an environment variable. Licensed MIT.
https://github.com/langwatch/better-agents
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.