Built for how developers actually work

One binary. Every provider. Full visibility. OpenAlloy gives your team the AI tools they need without the infrastructure overhead.

13+ Providers

Multi-Model Orchestration

Switch between LLM providers mid-session without losing context. Use Claude for complex reasoning, GPT for code generation, Gemini for multimodal tasks - all from the same interface.

  • Anthropic, OpenAI, Google, Groq, Mistral, Cohere
  • OpenRouter, AWS Bedrock, Azure OpenAI
  • Local models via Ollama & LMStudio
  • GitHub Copilot integration
# Switch providers mid-session
$ openalloy switch anthropic
✓ Switched to claude-sonnet-4-20250514
$ openalloy switch openai
✓ Switched to gpt-4.1
$ openalloy switch ollama/llama3
✓ Switched to llama3:latest (local)
# Generate a team setup token
$ openalloy team create-token
Token: oalloy_setup_a8f3...
Expires: 7 days
Seats remaining: 11
# New team member joins
$ openalloy join oalloy_setup_a8f3...
✓ Joined team acme-engineering
Enterprise

Team Setup Tokens

Onboard developers in seconds. Generate time-limited setup tokens that automatically configure provider access, team settings, and telemetry for new team members.

  • Time-limited tokens with configurable expiry
  • Automatic provider & permission configuration
  • Seat management and usage caps
Observability

Webhook Usage Monitoring

Every API call generates an HMAC-signed webhook event with token counts, cost estimates, model info, and session metadata. Pipe it to your observability stack or use our built-in dashboard.

  • HMAC-SHA256 signed payloads
  • Per-user, per-model, per-session breakdowns
  • Real-time cost tracking and alerts
// Webhook payload
{
"event": "usage.completed",
"team": "acme-engineering",
"user": "dev@acme.com",
"provider": "anthropic",
"model": "claude-sonnet-4-20250514",
"tokens": {
"input": 1250,
"output": 847,
"cache_read": 3200
},
"cost_usd": 0.0034
}
# Run the WhatsApp daemon
$ openalloy daemon
✓ WhatsApp connected (paired device)
✓ Listening for messages...
[+27821234567] "Summarise this PDF"
↳ attachment: report-q1.pdf (2.4 MB)
✓ Agent processing...
✓ Response sent (1.2s)
Mobile-First

WhatsApp Daemon

Turn any WhatsApp chat into an AI-powered workspace. Run OpenAlloy as a background daemon that listens for messages, processes prompts, and responds — all from your phone. Supports text, voice notes, images, and documents.

  • Scan a QR code to pair — no WhatsApp Business API needed
  • Persistent sessions per chat (DMs and groups)
  • Send images, voice notes, PDFs — the agent sees everything
  • Allowlist phone numbers for security

And much more

LSP Integration

Language Server Protocol support for deep editor integration with VS Code, Neovim, and more.

MCP Extensibility

Model Context Protocol support lets you extend OpenAlloy with custom tools, data sources, and capabilities.

Works Everywhere

Native binaries for macOS (Intel & Apple Silicon), Linux, Windows, Android, and BSD. No runtime required.

Desktop TUI

Beautiful terminal interface built with Charm's Bubble Tea. Full mouse support, markdown rendering, and syntax highlighting.

Terminal Agent

Autonomous agent mode that reads files, runs commands, and writes code. Full tool-use support with approval workflows.

Ready to get started?

Download OpenAlloy and start building with AI today.

View Pricing