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
blob42/Instrukt
Instrukt is an integrated AI environment designed to be used directly within the terminal, providing a powerful platform for building, testing, and instructing AI agents. It offers a modular approach where users can create custom AI agents as simple Python packages, which can be extended, shared, and enhanced with document indexes and tools. The environment supports natural language instructions to interact with these agents, which run securely inside sandboxed containers using Docker for safety and privacy. The project leverages popular frameworks such as Langchain for AI workflows, Textual for a rich terminal user interface, and Chroma for managing document indexes. Users can generate document indexes for question-answering, attach tools to agents, and interact with agents through a keyboard and mouse terminal interface that supports colorful markdown and source code outputs. The environment is designed for power users who prefer terminal-based workflows and supports running on bare metal or Docker containers with CUDA support, including remote access via SSH and terminal multiplexers. Key features include a prompt console for quick interaction, integrated REPL for development and testing, and a developer console with an IPython shell for debugging. The system supports indexing of codebases and documents with automatic language detection and optimized chunking strategies, enabling retrieval-augmented generation (RAG) for coding assistance and conversational agents. Currently, it supports OpenAI models with plans to integrate private local LLM models. The project is open to contributions and aims to empower users by providing an open, extensible AI tool that minimizes reliance on external APIs and services. It is licensed under AGPL, ensuring that any public deployment must share source code modifications. The project also offers consulting services and has a Patreon for supporters. Overall, Instrukt is a comprehensive terminal-based AI assistant environment focused on modularity, security, and user empowerment.
https://github.com/blob42/Instrukt
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.