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
Agenta is an open-source workspace for building, running and sharing AI agents that automate work. Agents are created conversationally: the user describes the task, connects the applications the agent needs and improves behavior through feedback, then works with the agent directly in chat or hands it to teammates. For recurring work, background agents run on a schedule or start when an event occurs in a connected application. Agents are defined with open standards, namely an AGENTS.md file, skills and MCP servers, so existing skills and MCP servers from the wider ecosystem can be reused inside the platform. The harness and the model are independent of the agent definition and can be switched without rebuilding it; Claude Code, Pi and Codex are supported as harnesses today, with more planned, and nearly any model can be used, whether self-hosted or reached through an API. When Agenta is self-hosted, agents can run locally against an existing Claude or ChatGPT subscription instead of moving every task to metered API billing. Reliability features include tracing of every run, a version history of each agent configuration for comparing changes and diagnosing failures, and inspection of individual model and tool calls with token usage and estimated cost per agent. Permissions are set per tool, so each action a background agent might take is either automatic, gated behind human approval, or blocked. Shared workspaces let a person and an agent work on the same files, for example to write documents, organize research or maintain a wiki, and the open-source edition supports sharing agents with a team and controlling access by role. Integrations reach connected applications through MCP, or through Composio for more than one thousand apps including Gmail, Slack, Notion and GitHub. The project is MIT licensed and also offers a hosted cloud option.
https://github.com/Agenta-AI/agenta
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...
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.
This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.
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.
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.
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.
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 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.