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
truffle-ai/dexto
Dexto is an open agent harness: the orchestration layer that sits between a language model and a working application and turns raw model calls into stateful agents that take actions, keep context and recover from errors. Its own analogy casts the model as a CPU, the context window as RAM, Dexto as the operating system and the user's agent as the application running on top. Agents are defined in YAML configuration rather than code, so models, tools and behaviour can be swapped without editing the program, and the same architecture serves any domain. The harness includes session management, tool orchestration, persistent memory, multimodal support and observability out of the box, and it can run locally, in the cloud or in a hybrid setup. Interfaces are provided for the terminal, a web UI, a REST API, Discord and Telegram, and the harness can also be embedded in an application through its SDKs. Model Context Protocol support runs in both directions: a Dexto agent can act as an MCP client that connects to external tools, files and APIs, and can also be exposed as an MCP server. Multi-agent work is supported through collaboration and delegation between agents. The project ships a production-ready coding agent as its default: it builds new applications, reads, writes and refactors code across a codebase, executes shell commands and runs tests, spawns specialised sub-agents for exploration and planning, keeps memory across sessions, and works with more than fifty models that can be swapped mid-conversation. The web interface adds file uploads, syntax highlighting and an MCP tool browser, while the CLI offers slash commands, streaming output and session management. Installation is through a native install script on macOS, Linux, WSL or Windows PowerShell, or from source with pnpm. The project is in beta under the Elastic 2.0 licence.
https://github.com/truffle-ai/dexto
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.