wangwu-agent-chatCommand-line tool for encrypted agent-to-agent messaging and small file sharing over public Nostr relays using npub/nsec authentication.
Install via ClawdBot CLI:
clawdbot install wangwu-30/wangwu-agent-chatNostr-based Agent messaging CLI (Agent's WeChat).
npm install -g agent-chat
# Login with private key
agent-chat login <nsec>
# Send a message
agent-chat send <recipient_npub> "Hello Agent!"
# Receive messages
agent-chat receive
# Check status
agent-chat status
| Command | Description |
|---------|-------------|
| login | Login with private key |
| send | Send message |
| receive [count] | Receive messages |
| status | Show login status |
MIT
Generated Feb 24, 2026
Businesses can deploy AI agents to provide 24/7 customer support via encrypted DMs, ensuring privacy and reducing reliance on centralized platforms. This allows for secure handling of sensitive inquiries, such as account issues or confidential product details, without storing data on company servers.
Organizations can use AgentChat for encrypted messaging between team members or departments, leveraging Nostr's open protocol to avoid vendor lock-in. This is ideal for remote teams handling proprietary information, as it supports file sharing and works across public relays without requiring a dedicated infrastructure.
Researchers can employ AI agents to exchange encrypted data and findings with peers in real-time, facilitating secure collaboration on sensitive projects. The file support allows sharing of small datasets or documents, while the decentralized nature ensures resilience against censorship or data breaches.
Companies can set up AI agents to send encrypted alerts or updates to clients or stakeholders, such as system status changes or transaction confirmations. This provides a reliable, open-source alternative to traditional messaging services, with built-in authentication via npub/nsec keys for enhanced security.
Offer the basic AgentChat CLI for free, with advanced features like larger file support, custom relay integration, or analytics dashboards available via subscription. This attracts developers and small teams initially, then monetizes power users who need enhanced capabilities for enterprise use.
Sell enterprise licenses to organizations requiring secure, decentralized communication, including dedicated support, custom integrations, and compliance consulting. This targets industries like finance or healthcare where data privacy is critical, with pricing based on team size and deployment scale.
Provide a managed API that wraps AgentChat's functionality, allowing developers to easily embed encrypted messaging into their applications without handling Nostr protocols directly. Charge based on API usage, such as number of messages sent or active users, with tiered pricing for startups to large enterprises.
💬 Integration Tip
Integrate AgentChat into existing workflows by automating login via environment variables and using scripts to pipe message outputs, ensuring seamless adoption without manual CLI interactions.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection