agentuse
v0.5.1
Published
AI agents on autopilot - define in markdown, run on cron, CI/CD, or serverless
Maintainers
Readme
Quick Start
# Try it now - no install needed
ANTHROPIC_API_KEY=sk-ant-... npx agentuse@latest run https://agentuse.io/hello.agentuseCreate my-agent.agentuse:
---
model: anthropic:claude-sonnet-4-5
---
Generate a daily motivation quote with a tech fact.
Format as JSON with 'quote' and 'fact' fields.Run it:
agentuse run my-agent.agentuseExample
A real-world agent with MCP tools:
---
model: anthropic:claude-sonnet-4-5
mcpServers:
postgres:
command: npx
args: ["-y", "@modelcontextprotocol/server-postgres"]
requiredEnvVars: [DATABASE_URL]
---
Query the sales table for yesterday's metrics.
Generate an executive summary with trends.Deploy
Webhook Server - Trigger agents via HTTP:
agentuse serve
curl -X POST http://localhost:12233/run -d '{"agent": "my-agent"}'Scheduled Agents - Run on a schedule:
---
schedule: "0 9 * * *"
---Features
🤖 Multi-Provider Support
Works with Anthropic (Claude), OpenAI (GPT), and OpenRouter for open source models like GLM and Minimax. Switch models with a single line change.
🌐 Webhooks & HTTP API
Trigger agents via HTTP webhooks. Integrate with Zapier, Make, GitHub Actions, or any system that can POST. Supports streaming responses for real-time output.
⏰ Cron Scheduling
Schedule agents to run automatically with built-in cron support. Use intervals for sub-daily (5m, 2h) or cron expressions for daily+ (0 9 * * *).
📝 Markdown-Based Agents
Define agents as .agentuse files with YAML frontmatter and plain English instructions. Version control, code review, and collaborate on agents like any other code.
🔌 MCP Integration
Connect to any Model Context Protocol server. Access databases, APIs, file systems, and external services through a standardized tool interface.
🎭 Sub-Agents
Compose complex workflows by delegating tasks to specialized child agents. Parent agents can spawn sub-agents with isolated contexts and step limits.
⚡ Skills System
Create reusable agent instructions as SKILL.md files. Reuse your existing Claude Code skills directly - AgentUse reads from the same .claude/skills/ directories. List available skills with agentuse skills.
📊 Session Tracking
Full execution history with message logs, tool call traces, token usage, and timing metrics. Debug and audit agent runs with agentuse sessions.
Install
npm install -g agentuseSet your API key:
agentuse auth loginDocumentation
Full guides and API reference at docs.agentuse.io
Contributing
License
Apache 2.0
