Deploy Agents in Seconds
Host OpenClaw and Hermes agents on managed containers. Deploy in seconds, expose live web apps with one route, and connect to Telegram, Discord, Slack, and WhatsApp from one dashboard.
Simple, Transparent Plans
Free
- 1 Agent
- 10 Hours of Agent Runtime
- 1 Workspace Member
- 10 Skills
- 10 Secrets
- 5 Templates
Picnic
- 1 Agent
- Unlimited Runtime
- 3 Workspace Members
- 30 Skills
- 30 Secrets
- 100 Templates
Fiesta
- 3 Agents
- Unlimited Runtime
- 5 Workspace Members
- 30 Skills
- 30 Secrets
- 100 Templates
Everything to Run Your AI Agents
Agent Management
Create and manage containerized OpenClaw and Hermes agents with full lifecycle control. Start, stop, configure, and monitor from a single dashboard.
Templates
Start from a pre-built template or submit your own. Templates ship with a pinned workspace, skills, and config — deploy a copy in one click.
ClawHub Marketplace
Discover community-built skills across categories like Trading, DeFi, NFTs, Social, and Analytics. One-click install to any of your agents.
Encrypted Secrets
Store API keys and credentials securely with encrypted-at-rest secret management. Scope secrets to specific agents or share across your workspace.
Multi-Channel
Connect your agents to Telegram, Discord, Slack, and WhatsApp. Your agent, everywhere your users are. One agent, all platforms.
Routes
Expose any port from your agent's container to the web. Map URL paths to services, ship apps and APIs with public or protected access.
OpenClaw or Hermes
Pick the agent harness that fits your workflow. OpenClaw and Hermes are both first-class runtimes on Pinata — deploy either, swap per agent, and manage them side by side from the same dashboard.
Git Integration
Push and pull your agent's workspace with standard Git. Every agent is a repo — use your own editor, CI pipeline, or collaborate with your team.
Chat, Browse, and Manage — All in One Place
Pinata Agents vs. the alternatives
Side-by-sides against the tools you're probably also evaluating — what we do better, what they do better, and when to pick which.
Content-Addressed Infrastructure
Every agent workspace, skill, and template is content-addressed and pinned to Pinata. Unique hashes guarantee integrity at every layer.
Immutable Snapshots & Rollback
Every change to your agent's workspace is captured as a CID — a unique, content-addressed fingerprint. Browse the full history timeline and roll back to any previous state with one click. Because CIDs are deterministic, you can always verify that a snapshot hasn't been tampered with.
QmXo...7kF3→QmR9...2aB1→QmTv...9eD4Tamper-Proof Skills
Skills are stored and distributed by their content hash. When you install a skill from ClawHub, the CID is verified against the published hash. If a single byte changes, the CID changes — making supply-chain attacks detectable by design. What you pin is what you run.
Pinned Templates
Agent templates ship with a pinned snapshot CID and a set of skill CIDs baked in. Deploy a template and get an exact, reproducible copy of the original workspace — same files, same skills, same configuration. No drift, no surprises.
Everything You Need to Ship
Your agent isn't just a chatbot — it's a full container. Have it create a web app, then expose it to the world with a route. Our edge network handles the rest.
Create It
Tell your agent what to build — a React app, API server, dashboard, anything. It writes the code inside its own container with full filesystem access.
Add a Route
Map a URL path to your app's port. /app → port 3000, /api → port 8080. Up to 10 routes per agent, public or token-protected.
Live on the Edge
Your app is live at your-agent.agents.pinata.cloud/app — served through our global edge network with TLS, DDoS protection, and static asset caching built in.
Each route can be public (no auth) or protected behind your gateway token. Expose an API publicly while keeping admin routes locked down.
Requests to /app/dashboard arrive at your server as /dashboard. Clean routing with zero config on your app side.
Full bidirectional WebSocket proxying. Build real-time dashboards, live data feeds, or collaborative tools — all running inside your agent's container.
Static assets cached at 300+ edge locations. TLS termination, DDoS mitigation, and HTTP/3 — production infrastructure without the ops work.
Three Steps to Your First Agent
Create
Sign up, name your agent, and pick a model. Or start from a template with everything pre-configured.
Equip
Add skills from the library, configure secrets, and connect to your favorite messaging channels.
Deploy
Hit deploy and your agent goes live on Pinata's container infrastructure. Monitor logs and chat in real-time.
Built by People Who Use It Every Day
Trusted by 800,000+ Developers
Pinata powers file infrastructure for thousands of apps across web3 and beyond. Agents inherit the same battle-tested platform.
Frequently asked questions
Is there a free plan?
Yes. The free tier includes ten hours of agent runtime with no credit card required, so you can build and deploy a working agent before paying anything.
Which AI models are supported?
Pinata Agents supports Claude (Anthropic), GPT (OpenAI), and any model exposed through OpenRouter. You can switch models per agent at any time.
Can I bring my own API key?
Yes. Add your Anthropic, OpenAI, or OpenRouter key as an encrypted secret and your agent will use it for inference. Keys never leave your workspace and stay encrypted at rest.
Is self-hosting an option?
Yes — the agent runtimes are OpenClaw and Hermes, both open-source and self-hostable. Pinata Agents is the managed platform for running OpenClaw and Hermes — you skip Kubernetes setup, container builds, and TLS, and only pay for the time your agent is actually running.
How is this different from Replit Agent or Cursor?
Replit Agent and Cursor are coding assistants. Pinata Agents are persistent containerized agents that keep state across sessions, expose live web apps via routes, connect to messaging channels, and run scheduled tasks — closer to a managed Claude Code or Devin than an IDE plugin.
Can my agent run a real web app?
Yes. Any port your agent’s container exposes can be mapped to a public URL via Routes. Up to 10 routes per agent, public or token-protected, served through Pinata’s global edge with TLS and DDoS protection.
How do skills and the marketplace work?
Skills are pluggable capabilities — trading, DeFi monitoring, scraping, social posting — installed in one click from ClawHub. Each skill is a content-addressed package, so versions are pinned and reproducible.
Is everything versioned?
Yes. Every workspace change is captured as a content-addressed snapshot with a unique hash. You can browse history, diff between snapshots, and roll back to any prior state with one click.
Ready to Build?
Try it free with 10 hours of agent runtime — no credit card required. Or pick a paid plan for unlimited runtime and more agents.