Backed by arena.ai  ·  Research Preview

Orchestrate AI agents
from Stanford,
for the world.

Stanford Agent is a research-grade AI orchestration platform powered by arena.ai. Deploy, monitor, and collaborate with intelligent agents — from your phone, desktop, or anywhere in the world.

Self-hosted & open source
E2E encrypted relay
Multi-provider support
Running research agents across 4 nodes…
A ARENA
32+
Agent Providers
<200ms
Relay Latency
100%
End-to-End Encrypted
Open.
Source & Free

Why Stanford Agent

Research-grade orchestration
built for scale

Every feature is designed for developers and researchers who need reliable, transparent, and powerful multi-agent coordination.

🤖

Multi-Agent Orchestration

Run dozens of AI agents in parallel across sessions, branches, and machines — all from one unified dashboard.

📱

Universal Access

Full-parity mobile, web, and desktop apps. Monitor and direct agents from your phone on the go.

🔒

E2E Encrypted Relay

Your code never leaves your machine. End-to-end encrypted relay — Arena.ai cannot read your traffic.

🎙️

Local Voice Control

Fully local speech-to-text and TTS. Direct agents by voice without sending audio to external servers.

Zero Port Conflicts

Each agent worktree gets a unique URL auto-generated from the branch name. No guessing, no conflicts.

🛠️

Fully Scriptable CLI

Every UI action available from the terminal. Build loops, schedules, and automation pipelines with ease.


Live Demo

Ship faster with arena.ai agents

Spin up an agent from the terminal, monitor it from your phone, review the diff inline, then commit and merge — without leaving Stanford Agent.

stanford-agent — bash
stanford-agent run "build REST API for student research data"
🤖 Spawning agent on arena-cluster-1…
📦 Worktree: feat/research-api
🔗 Preview: web.feat-research-api.myapp.localhost
──────────────────────────────────
stanford-agent ls
ID BRANCH STATUS
abc123 feat/research-api ● running
def456 fix/auth-token ● running
ghi789 feat/ml-pipeline ⏸ paused
stanford-agent attach abc123
✓ Compiled routes/research.ts in 290ms
✓ Tests passed (18/18)
# Open PR? [y/n]
SA
ARIA — Stanford Agent Online
Build me a dashboard for tracking ML experiment results across our research team.
You · just now
Understood. I'll break this into planning and parallel implementation tracks. Spinning up sub-agents now.
ARIA · 2s ago
▸ Running plan-ux · arena-claude
▸ Running plan-api · arena-codex
✓ 3 files scaffolded · tests passing
ARIA · 18s ago
Add real-time WebSocket updates and a comparison view.
You · just now
On it — implementing WebSocket server and diff comparison panel. ETA ~40s.
ARIA · now

Supported Providers

Works with your entire stack

Stanford Agent uses each provider's native harness — your subscriptions, skills, config, and MCP servers keep working.


Community

Loved by researchers & developers

@ml_angelopoulos · Founder

Stanford Agent is the most elegant way to orchestrate research-grade AI workflows I've ever built. Arena.ai's infrastructure makes it seamless.

@stanford_ee · Stanford EE

We're running parallel ML experiments across 20+ nodes. The agent dashboard gives our team visibility we never had before.

@researcher_xyz

The mobile app is genuinely full-featured. I directed three agents from my phone during a conference talk. Zero issues.

@devtools_fan

Cross-platform orchestration, E2E encrypted relay, voice control — and it's open source. Nothing else comes close.


FAQ

Common questions

Is Stanford Agent free?+

Yes. Stanford Agent is free and open source. You need your own API credentials for the AI providers you use. The arena.ai relay is included for research preview participants.

Does my code leave my machine?+

Stanford Agent doesn't send your code anywhere. Agents run locally using their own APIs as they normally would. Remote access uses end-to-end encryption — arena.ai cannot read your traffic.

What agent providers are supported?+

Claude Code, Codex, OpenCode, Cursor, GitHub Copilot, arena.ai Pi, and 26+ more. Each runs as its own process using its native CLI — Stanford Agent never wraps or modifies agent behavior.

Do I need the desktop app?+

No. You can run the daemon headlessly with npm install -g @stanford-agent/cli && sagent and connect via web, mobile, or CLI.

How does voice control work?+

Voice runs fully local on your device by default. Speech-to-text transcribes your instruction and sends it to the agent as text. You can optionally configure cloud providers for higher accuracy.


Get started today

The AI agent platform
built for serious research.

Stanford Agent is open source and research-preview ready. Deploy in minutes on your own infrastructure — or connect to the arena.ai cloud.

Launch Agent Console View on GitHub arena.ai