thedaviddias/Front-End-Checklist
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
Awesome AI Agents › MCP Server Framework
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.
Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.
c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.
Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...
MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).
Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.
Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.
Helicone is an open-source LLM observability platform that enables developers to monitor, evaluate, and experiment with large language model applications through easy integration and comprehensive tools.
AgentOps is a Python SDK providing observability, cost tracking, benchmarking, and security tools for AI agents and large language models, integrating with major agent frameworks to support developers from prototype to production.
Klavis AI is an open-source project offering production-ready MCP integration and scalable infrastructure for AI applications across multiple platforms with built-in authentication and extensive tool support.
Casibase is an open-source enterprise-level AI Cloud OS that provides a knowledge base and agent management platform with admin UI, user management, Single-Sign-On, and support for multiple AI models including ChatGPT and Claude.
Local-first MCP server giving AI agents keyless web search, fetch, crawl, extract, cache, find-similar and research tools that run on device and return cited, scored evidence.
ACI.dev is an open-source platform that connects AI agents to over 600 tool integrations with multi-tenant authentication, granular permissions, and access via direct function calls or a unified MCP server, enabling production-ready AI agent development without infrastructure complexity.
kagent is a Kubernetes native framework for building, deploying, and managing AI agents with extensibility, observability, and declarative configuration features.
DBHub is a minimal, token-efficient MCP server providing a unified interface for secure and efficient management and exploration of multiple databases including PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite.
Jenkins Kubernetes plugin enables dynamic provisioning and management of Jenkins build agents as Kubernetes pods, automating scaling and integration for efficient CI/CD workflows.
Remote MCP server hosted by Microsoft that gives MCP-compatible agents semantic search, page fetch and code-sample lookup over official Microsoft Learn documentation without any API key.
PostgreSQL expertise for AI coding agents, delivered as curated agent skills plus a public MCP server offering version-aware semantic search over the PostgreSQL, TimescaleDB and PostGIS manuals.
Python SDK, CLI and MCP server from Harvard that gives LLM agents standardized access to more than 1000 scientific tools, datasets, APIs and machine learning models.
An MCP server that gives AI assistants privacy-respecting web search and URL reading through a self-hosted or trusted SearXNG instance, with replica failover, caching and SSRF protection.
Xata Agent is an open-source AI-powered expert system that monitors, troubleshoots, and optimizes PostgreSQL databases by analyzing logs and metrics, suggesting improvements, and integrating with cloud services and notifications.
Agentica is an open-source TypeScript framework that simplifies building reliable AI agents with Large Language Models by providing schema-driven function calling, automatic error correction, and seamless OpenAPI integration.
Octocode is an evidence-first code research platform exposed as both an MCP server and a CLI, searching local repositories and GitHub with a Rust engine, ripgrep, AST search and LSP.
Citra is a local-first MCP server and CLI that gives agents structured PDF text, tables, OCR and visual crops together with page-level citations backed by geometry and provenance.
Rust CLI that turns local files and regex-constrained shell commands into self-describing Markdown data apps which agents can read and execute over HTTP or through an MCP bridge.
Council is an open-source platform that enables rapid development and robust deployment of customized generative AI applications with a unified interface for multiple Large Language Model providers and built-in monitoring and error handling features.
mcpc is a universal command-line client for the Model Context Protocol that maps every MCP operation to a shell command, so humans can debug servers and agents can use MCP through one Bash tool.
Go-based context engineering infrastructure that aggregates MCP tools and third-party integrations behind one API, handling OAuth credentials, vault storage and tool discovery for AI agents.
AnyTool is a Python tool-use layer that gives any AI agent fast retrieval, caching and quality-aware selection over large MCP, shell, GUI and web-API tool collections through a single execute call.
An MCP server exposing fourteen tools and three resources that let AI agents read, write, search, tag and surgically patch notes and frontmatter in an Obsidian vault over STDIO or streamable HTTP.
Official Model Context Protocol server from SonarSource that gives AI agents access to SonarQube Server and Cloud code quality and security data, and can analyse code snippets in the agent context.
Overture is a locally running MCP server that intercepts an AI coding agent's planning phase and renders it as an interactive flowchart for review and approval before the agent writes any code.
AgentLabs is an open-source universal frontend platform that enables developers to deploy and manage AI agents with real-time streaming, authentication, analytics, and payment features, supporting both cloud and self-hosted environments.
Go MCP server that exposes any existing PostgreSQL database to AI assistants, translating natural language questions into read-only SQL and streaming the results back as table, JSON or CSV.
TypeScript MCP server that acts as an oversight layer for coding agents, interrupting pattern inertia with metacognitive questions so the agent stops over-engineering and stays on the minimal viable path.
Tiger is an open-source, community-driven tool ecosystem that enables AI agents to control and interact with computer systems and online resources through integrations with popular AI frameworks like crewAI, LangChain, and AutoGen.
Skillz is an MCP server that exposes Claude-style Agent Skills as callable tools to any MCP client, discovering SKILL.md packages from a directory, zip or .skill archive and serving their instructions, resources and helper scripts.
Stride AI Agents is an open-source repository providing tools and knowledge to build, implement, and master autonomous AI systems for diverse applications across industries.
Apache SkyWalking Go is a Golang auto-instrumentation agent that provides native tracing, metrics, and logging capabilities for Golang projects, enabling effective observability and performance monitoring in distributed systems.
Terrarium is a secure, low-latency Python sandbox environment for executing untrusted code using Pyodide, designed for easy deployment on cloud platforms like Google Cloud Run.
Connery SDK is an open-source SDK and CLI that streamlines the development of AI plugins and actions by providing a standardized REST API and tools for easy plugin server creation.
The Jenkins EC2 Plugin enables Jenkins to dynamically provision and manage Amazon EC2 instances as build agents, optimizing build infrastructure scalability and cost efficiency.
Claude Artifacts React is an open-source tool that enables quick and easy deployment of React code snippets generated by Claude Artifacts to Vercel or Cloudflare Pages for prototyping and sharing.