GitHub Copilot has introduced several new models including Anthropic Claude 3.7 Sonnet, Claude 3.5 Sonnet, OpenAI o3-mini, and Google Gemini Flash 2.0. These models are now available in Copilot Chat and agent mode, offering enhanced capabilities and performance.
This repository provides reference OpenAPI Tool Server implementations, making it easy and secure for developers to integrate external tooling and data sources into LLM agents and workflows.
- Filesystem Access (servers/filesystem) - Manage local file operations safely with configurable restrictions.
- Git Server (servers/git) - Expose Git repositories for searching, reading, and possibly writing via controlled API endpoints.
- WIP: Database Server (servers/database) - Query and inspect database schemas across common DB engines like PostgreSQL, MySQL, and SQLite.
- Memory & Knowledge Graph (servers/memory) - Persistent memory management and semantic knowledge querying using popular and reliable storage techniques.
- WIP: Web Search & Fetch (servers/web-search) - Retrieve and convert web-based content securely into structured API results usable by LLMs.
This article details the Model Context Protocol (MCP), a new approach to integrating Large Language Models (LLMs) like Azure OpenAI with tools. MCP focuses on structured data exchange to improve reliability, observability, and functionality, moving beyond simple text-in, text-out interactions. It aims to standardize how LLMs interact with tools, enhancing their ability to utilize those tools effectively.
Powering the future of open-source AI agent development. Discover, run, and compose AI agents from any framework. Build production-grade AI agents in both Python and Typescript. Join our community on Discord, BlueSky, and YouTube.
This article explores the Model Context Protocol (MCP), an open protocol designed to standardize AI interaction with tools and data, addressing the fragmentation in AI agent ecosystems. It details current use cases, future possibilities, and challenges in adopting MCP.
This tutorial demonstrates how to build a powerful document search engine using Hugging Face embeddings, Chroma DB, and Langchain for semantic search capabilities.
The article discusses the OVON agentic framework for mitigating hallucinations in Large Language Models (LLMs). It explains the structured, collaborative pipeline involving front-end and reviewer agents, the use of 'Conversation Envelopes' and 'Whispers' for efficient data exchange, and novel KPIs for measuring success. The article also addresses future directions and the importance of trust in AI systems.
This paper introduces a multi-agent NLP framework to address prompt injection vulnerabilities in generative AI systems. The framework utilizes specialized agents for generating responses, sanitizing outputs, and enforcing policy compliance, evaluated using novel metrics like Injection Success Rate (ISR), Policy Override Frequency (POF), Prompt Sanitization Rate (PSR), and Compliance Consistency Score (CCS). The system employs OVON for inter-agent communication.
Model Context Protocol (MCP) is a bridging technology for AI agents and APIs. It standardizes API access for AI agents, making it a universal method for AI agents to trigger external actions.
Browser Use is a library that enables AI agents to interact with web browsers, making websites accessible for automated tasks. It includes features for browser automation, agent memory, and various demos showcasing its capabilities.
