{"name":"Mercury Agent: A Soul-Driven AI with Hardened Permissions and Multi-Channel Access","description":"Mercury Agent is a sophisticated, soul-driven AI agent designed for continuous 24/7 operation, offering robust permission-hardened tools, intelligent token budgeting, and versatile multi-channel access. It remembers what matters, asks for permission before acting, and runs seamlessly from the CLI, Telegram, or a web dashboard. With 31 built-in tools, Kanban boards, and a SQLite-backed Second Brain memory, Mercury provides a comprehensive and secure AI assistant experience.","github":"https://github.com/cosmicstack-labs/mercury-agent","url":"https://osrepos.com/repo/cosmicstack-labs-mercury-agent","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/cosmicstack-labs-mercury-agent","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/cosmicstack-labs-mercury-agent.md","json":"https://osrepos.com/repo/cosmicstack-labs-mercury-agent.json","topics":["ai-agent","ai-assistant","llm","TypeScript","open-source","developer-tools","automation"],"keywords":["ai-agent","ai-assistant","llm","TypeScript","open-source","developer-tools","automation"],"stars":null,"summary":"Mercury Agent is a sophisticated, soul-driven AI agent designed for continuous 24/7 operation, offering robust permission-hardened tools, intelligent token budgeting, and versatile multi-channel access. It remembers what matters, asks for permission before acting, and runs seamlessly from the CLI, Telegram, or a web dashboard. With 31 built-in tools, Kanban boards, and a SQLite-backed Second Brain memory, Mercury provides a comprehensive and secure AI assistant experience.","content":"## Introduction\n\nMercury Agent is a sophisticated, soul-driven AI agent developed by cosmicstack-labs, designed for continuous 24/7 operation. It offers a unique blend of permission-hardened tools, intelligent token budgeting, and versatile multi-channel access, including CLI, Telegram, and a dedicated web dashboard. Mercury remembers crucial information, always seeks permission before executing actions, and integrates 31 built-in tools, Kanban boards, extensible skills, and a SQLite-backed Second Brain memory for a truly comprehensive AI assistant experience.\n\n## Installation\n\nGetting started with Mercury Agent is straightforward. The recommended method involves a simple one-liner script that downloads the latest standalone binary for your operating system, requiring no prior Node.js installation.\n\n**For macOS / Linux:**\nbash\ncurl -fsSL https://mercuryagent.sh/install.sh | sh\n\n\n**For Windows:**\npowershell\nirm https://mercuryagent.sh/install.ps1 | iex\n\n\nAlternatively, if you have Node.js 20+ installed, you can use npm:\nbash\nnpx @cosmicstack/mercury-agent\n\n\nUpon first run, Mercury will guide you through a setup wizard to configure your agent's name, provider, and optional Telegram integration. You can reconfigure settings at any time using the `mercury doctor` command.\n\n## Examples\n\nMercury Agent provides a rich set of commands for interaction, both from the command line and directly within chat conversations.\n\n**CLI Commands:**\n*   `mercury up`: Installs the service, starts the daemon, and ensures Mercury is running persistently.\n*   `mercury doctor`: Reconfigure setup, including name, providers, channels, and permissions.\n*   `mercury upgrade`: Upgrade Mercury to its latest version.\n*   `mercury skills install <id>`: Install community-contributed skills from the registry.\n\n**In-Chat Commands (CLI and Telegram):**\n*   `/help`: Display the full manual for in-chat commands.\n*   `/status`: Show agent configuration, budget, and usage statistics.\n*   `/budget`: Check your daily token budget status, override it for a request, or reset usage.\n*   `/permissions`: Change the agent's permission mode between \"Ask Me\" and \"Allow All\".\n*   `/memory`: View and manage your Second Brain memory.\n\n## Why Use Mercury Agent?\n\nMercury Agent stands out with several core principles that enhance its utility and security:\n\n*   **Permission-hardened**: It prioritizes security by implementing a shell blocklist, folder-level read/write scoping, and a pending approval flow, ensuring no actions are taken without explicit consent.\n*   **Second Brain**: Features a persistent, structured memory powered by SQLite + FTS5, enabling Mercury to learn your preferences, goals, and habits automatically without manual entry.\n*   **Soul-driven**: Its personality is defined by markdown files you own, such as `soul.md` and `persona.md`, offering a truly personalized AI experience free from corporate wrappers.\n*   **Token-aware**: Enforces daily token budgets, automatically becoming concise when usage is high, and provides commands to manage your budget.\n*   **Live streaming**: Offers real-time token streaming on the CLI with cursor-save/restore and markdown re-rendering, and editable status messages on Telegram.\n*   **Always on**: Can run as a background daemon on any OS, with auto-restarts on crashes, starting on boot, and proactive notifications.\n*   **Extensible**: Supports installing community skills with a single command, based on the Agent Skills specification, allowing for broad functionality expansion.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/cosmicstack-labs/mercury-agent](https://github.com/cosmicstack-labs/mercury-agent){target=\"_blank\" rel=\"noopener noreferrer\"}\n*   **NPM Package**: [https://www.npmjs.com/package/@cosmicstack/mercury-agent](https://www.npmjs.com/package/@cosmicstack/mercury-agent){target=\"_blank\" rel=\"noopener noreferrer\"}\n*   **Skills Registry**: [https://skills.mercuryagent.sh](https://skills.mercuryagent.sh){target=\"_blank\" rel=\"noopener noreferrer\"}\n*   **Discord Community**: [https://discord.gg/5emMpMJy5J](https://discord.gg/5emMpMJy5J){target=\"_blank\" rel=\"noopener noreferrer\"}","metrics":{"detailViews":0,"githubClicks":0},"dates":{"published":null,"modified":"2026-08-12T11:30:03.000Z"}}