About blink-agents
blink-agents provides managed AI agent hosting on Fly.io for teams operating independent agents. Each agent runs in an isolated machine with persistent storage, preinstalled tools, and always-on connectivity; the skill includes tools for agent status and secret management.
Key features
- 01List agents in a workspace
- 02View agent status, machine details, and health
- 03List, set, and delete agent secrets
- 04Run each agent on a separate Fly.io machine
- 05Provide persistent storage and preinstalled tools
Use cases
- 01Check the status of hosted agents
- 02Manage secrets used by an agent
- 03Run agents connected to Telegram, Discord, or Slack
- 04Host agents for research, monitoring, or support
MCP support
It exposes MCP tools to list agents, check their status, and manage agent secrets.
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ blink-new/ blink-plugin --skill blink-agentsAfter installing, type/blink-agentsin Claude Code to confirm it loaded.
Details
From the project READMEWhat is Blink Claw?
Blink Claw provides managed AI agent hosting on Fly.io. Each agent runs in its own isolated Fly machine with persistent storage, pre-installed tools (browser, file system, CLI), and always-on connectivity for platforms like Telegram, Discord, and Slack.
Getting Started
# List all agents in the workspace
blink agent list
# Check agent status
blink agent status <agent-id>
# Manage agent secrets
blink secrets list --agent <agent-id>
blink secrets set MY_API_KEY sk-123 --agent <agent-id>
blink secrets delete MY_API_KEY --agent <agent-id>
MCP Tools
| Tool | Description |
|---|---|
blink_agent_list | List all Claw agents in the workspace |
blink_agent_status | Get agent status, machine info, and health |
blink_agent_secrets_list | List secret names for an agent |
blink_agent_secrets_set | Set a secret on an agent |
blink_agent_secrets_delete | Delete a secret from an agent |
Agent Lifecycle
Agents are created and configured via the Blink dashboard at blink.new. Once created:
- Running — Agent machine is active, processing tasks
- Stopped — Machine paused, can be resumed
- Error — Machine crashed, check logs
CLI Usage
# List agents with status
blink agent list
# Output:
# ID Name Status Platform Created
# ag_a1b2c3d4 Support Bot running telegram 2026-03-15
# ag_e5f6g7h8 Data Scraper stopped none 2026-04-01
# Get detailed status
blink agent status ag_a1b2c3d4
# Output:
# Name: Support Bot
# Status: running
# Platform: telegram
# Machine: blink-claw-a1b2c3d4 (iad)
# Uptime: 3d 14h 22m
# Memory: 512MB / 1GB
# Set environment secrets
blink secrets set OPENAI_API_KEY sk-abc123 --agent ag_a1b2c3d4
blink secrets set TELEGRAM_BOT_TOKEN 123456:ABC --agent ag_a1b2c3d4
# List secrets (values hidden)
blink secrets list --agent ag_a1b2c3d4
# Output:
# OPENAI_API_KEY ****abc123
# TELEGRAM_BOT_TOKEN ****ET:ABC
# Remove a secret
blink secrets delete OPENAI_API_KEY --agent ag_a1b2c3d4
Use Cases
- Telegram/Discord/Slack bots — always-on agents connected to messaging platforms
- Autonomous research agents — web browsing, data collection, report generation
- Scheduled workflows — periodic data processing, monitoring, alerts
- Customer support — AI-powered ticket triage and response
- DevOps automation — deployment monitoring, incident response
Agent Architecture
Each Claw agent runs on a dedicated Fly.io machine with:
- Persistent volume at
/data(workspace files, agent state) - Pre-installed tools: Chromium browser, Blink CLI, Node.js
- Networking: public HTTPS endpoint + WebSocket gateway
- Skills: bundled in Docker image at
/app/skills/
Notes
- Agent creation/configuration is done via the Blink dashboard, not CLI
- Secrets are stored in the Fly machine's
envconfig — not Fly app secrets - Agents are billed per-hour of machine uptime
- Each agent gets its own Fly app:
blink-claw-{last8ofAgentId}