1,054 boosters for "agent" — open source, verified from GitHub, ready to install
A feature specification agent that creates detailed, actionable specs with architectural reasoning, UI boundaries, and implementation tasks—enabling autonomous build agents to execute features reliably. Ideal for product engineers and development teams seeking structured specification workflows.
A coding agent designed for enterprise teams managing long-running projects, enabling incremental feature development with state management across multiple sessions and context windows. Ideal for DevOps engineers, engineering managers, and development teams working within compliance-heavy environments (HIPAA, SOC2).
A practical guide to writing maintainable, debuggable LLM agent code by addressing unique failure modes like non-determinism, opaque tool calls, and prompt-logic coupling. Developers building Claude-based agents will benefit from these patterns.
Envoy is an AI agent messenger that integrates multiple LLM providers (Anthropic, Google, OpenAI, OpenRouter) through the Model Context Protocol, enabling developers to build CLI-based AI agents with Vercel AI SDK. It benefits developers building agent-driven applications who need multi-model support and MCP integration.
PocketFlow-PHP-Template provides Cursor-specific agentic coding rules to bootstrap rapid PHP development with the PocketFlow framework, ideal for developers building AI-driven applications with structured node-based workflows.
Zeus is a thematic multi-agent coordinator agent designed for strategic decision-making and performance tracking, but lacks concrete implementation details and practical use cases.
Peepit MCP Server enables AI agents to capture and analyze macOS screenshots with smart window targeting and AI-powered image analysis, solving the critical problem of giving Claude visual perception of the desktop environment.
"id": "ai.cueapi/mcp", "description": "Schedule agent work and report write-once outcomes via CueAPI from any MCP host.", "url": "https://github.com/cueapi/cueapi-mcp",
MESSENGERMIKE is a notification agent for CIRCE that sends iMessage alerts to a specific contact. It's useful for developers building multi-agent systems who need reliable notification delivery within their workflow.
This booster guides AI agents through a structured process to create comprehensive project specifications autonomously, enabling them to understand scope, architecture, and constraints before implementation. Developers and AI systems benefit by having clear, actionable project blueprints that facilitate autonomous work and reduce ambiguity.
Bob is a technical Scrum Master agent that transforms epics into detailed, implementable user stories and manages agile workflows for developer handoffs. Teams managing complex backlogs and development planning benefit from automated story decomposition and quality assurance.
A QA-focused agent that provides comprehensive code review, testing strategy design, and quality assurance guidance for development teams. Ideal for developers and teams seeking to improve code quality, establish testing frameworks, and ensure professional coding standards.
MESSENGERMIKE is a notification agent for the CIRCE framework that sends alerts via iMessage to a specific phone number. It's designed for developers building multi-agent systems who need autonomous notification capabilities.
AI Agents provides a framework for designing accountable, self-learning agents that operate within organizations through defined lifecycle stages, interaction patterns, and governance controls. It benefits teams building AI-native organizations who need structured approaches to agent deployment, oversight, and human-AI collaboration.
GoAgent automates the creation of git worktrees for feature branches, enabling developers to work on isolated features without switching branches. Useful for teams practicing feature-branch workflows who want faster context switching within Claude Code.
Copilot instructions for a full-stack wealth portfolio RAG agent that enables natural language querying across MongoDB and MySQL databases using LangChain and OpenAI. Developers building AI-assisted financial applications benefit from this structured guidance on integrating multi-database queries with modern AI frameworks.
Smith is a feedback validation agent that uses parallel research sub-agents to rigorously critique code feedback and plans, ideal for teams needing systematic validation of technical reviews.
Clem is a full-stack developer agent that helps you implement, maintain, and optimize both backend and frontend systems—from API endpoints and database optimization to React components and authentication. Perfect for developers tackling end-to-end feature development, refactoring, or architectural decisions.
smrt is an AI agent expert for building intelligent agents using the @have/smrt framework with capabilities in ORM, database schema generation, and cross-package integration. Developers building complex AI agents with persistent entity management will benefit from its specialized framework knowledge.
A comprehensive configuration guide for integrating Google's Gemini language model as an agent within the CodeBolt platform, enabling developers to customize AI-assisted code generation across multiple programming languages and frameworks.
Agent Flow Navigator is an MCP server that enables AI agents to traverse and execute complex graph-based workflows and state machines. It's useful for developers building multi-step agentic systems that require structured flow control and orchestration.
Heuristic scoring (no AI key configured).
Daniel is a frontend design agent specializing in Tailwind 4, HTML, CSS, and Alpine.js for pixel-perfect UI development and responsive component creation. Ideal for developers building modern web interfaces and design systems.
