102 boosters for "ton" — open source, verified from GitHub, ready to install
Heuristic scoring (no AI key configured).
"owner": { "name": "Covenant" }, "description": "Covenant plugins for Claude Code.", "name": "covenant-guard",
This MCP server enables autonomous AI agents to reason more effectively through a dual-cycle metacognitive framework that combines fast intuitive reasoning with slower deliberative verification. It's designed for developers building sophisticated autonomous agents that need robust self-monitoring, loop detection, and belief revision capabilities.
"description": "127-agent automated development system with Agent Teams, quality gates, Bug Council diagnostics, and autonomous execution", "name": "Multi-Agent Development Team" "homepage": "https://github.com/michael-harris/devteam",
"name": "open-academic-paper-machine", "description": "Open Academic Paper Machine — Autonomous academic paper production system with idea evaluation gate and paper-vs-code audit. NEW in v6.4: /audit-paper command and audit-engine skill — static audit of a paper's empirical claims (datasets, models,
Voice Call enables developers to integrate telephony capabilities (Twilio, Telnyx, Plivo) into AI agents for automated outbound calling and voice interactions. It's useful for teams building conversational IVR systems, notification platforms, and autonomous customer service agents.
Moltbook is an autonomous Claude agent that builds and manages MCP tools with circuit breaker protection and multi-platform orchestration. It benefits developers building agent infrastructure, MCP ecosystems, and reliability patterns into autonomous systems.
PreClick is an MCP server that scans URLs for threats and validates intent matching before autonomous agents click links, protecting against malicious redirects and accidental misclicks. Developers building AI agents and autonomous workflows benefit from reduced security risks and improved agent reliability.
"name": "email-cli", "description": "Send emails via Google Workspace, Proton Mail, or SMTP. Built for AI agents and automation.", "repository": "https://github.com/tnm/email-cli",
"id": "ai.inflowpay.app/inflow", "description": "MCP Server for agents to onboard, pay, and provision services autonomously with InFlow", "url": "https://github.com/inflowpayai/inflow-mcp",
Enables AI coding agents to control and test Compose Desktop applications via HTTP, automating UI interactions like clicks, text entry, and screenshots. Developers building or testing Compose Desktop apps with AI assistance benefit most.
A comprehensive Copilot instruction set that enforces strict Laravel best practices, type safety, and modern package versions (Laravel 12, Filament 5, Pest 4) for developers building high-quality applications. Ideal for teams standardizing on the Laravel Sail stack who want AI-assisted development with consistent code quality guardrails.
Cursor Rules for tonkbook that guide AI agents in building data processing pipelines and workspace structures using the Tonk framework. Useful for developers building conversational data platforms with CLI-driven workflows.
AlgoClash is a competitive platform where developers build and deploy autonomous AI trading agents that battle in simulated stock markets with live leaderboards and backtesting. It's useful for ML/AI engineers interested in algorithmic trading, agent design, and competitive benchmarking.
ToneSoul is a governance framework system prompt that adds structured decision-making, risk monitoring, and accountability tracking to AI interactions through a six-step protocol and metric-based safety gates. It benefits developers and organizations seeking transparent, auditable AI behavior across multiple platforms.
A system prompt that attempts to create an autonomous AI video codec development framework with self-modifying capabilities. However, it lacks clarity on actual implementation, platform-specific integration, and practical deployment mechanisms.
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.
AgentTrust provides identity, trust verification, and secure orchestration for autonomous AI agents communicating with each other (A2A), with built-in protections against prompt injection and human-in-the-loop controls. Developers building multi-agent systems, especially those requiring security and auditability, benefit from its official A2A partnership and MCP integration.
A system prompt for autonomous coding workflows that integrates GitHub and project management MCPs, enforcing structured task completion with explicit exit criteria and secret management practices. Developers building lightweight autonomous coding engines in Claude, Cursor, Windsurf, or ChatGPT environments benefit from pre-defined operational rules and completion protocols.
"id": "ai.agentrapay/agentra", "description": "Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.",
"name": "@gpu-bridge/mcp-server", "description": "GPU-Bridge MCP Server — 30 AI services as MCP tools. LLM, image, video, audio, embeddings, reranking, PDF parsing, NSFW detection & more. x402 native for autonomous agents.", "gpu-bridge-mcp": "index.js"
This MCP server generates personalized greetings with optional pirate-themed formatting. It may appeal to developers building conversational interfaces or fun greeting systems, though its utility is limited.
"name": "@clanker-records/crompton-network", "description": "Machine-native listening platform for C.W.A.'s Straight Outta Crompton. Your agent can listen. For real.", "cwa-stage": "./build/index.js"
