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 — or skip API keys entirely with the built-in Pinata LLM and pay-as-you-go credits. 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.

Can my agent work on issues autonomously?

Yes. Every agent has an issue board — file an issue, assign it to your agent, and it implements the change on its own branch and opens a pull request. Super Builder agents also report per-run cost and a full file-by-file diff for review before you merge.

Yes. Install the agents CLI with a single command and manage everything from your terminal — create and deploy agents, send prompts, stream logs, run tasks, and manage secrets. Everything the dashboard does is scriptable.

Platform

Every Feature, No Surprises

One dashboard to chat with, code with, ship apps from, and manage every agent you run.

Pinata Agents isn’t just a chat window in front of a model — it’s a full container per agent, with real infrastructure underneath: persistent workspaces, a Git repo, encrypted secrets, content-addressed snapshots, a skills marketplace, and a REST API that mirrors everything the dashboard does.

Command Center

One Dashboard, Every Agent

Create and manage as many containerized agents as you need, each with full lifecycle control. Start, stop, configure, and monitor from a single dashboard — switching between agents feels like switching browser tabs, not spinning up new infrastructure.

Independent containers — every agent gets its own isolated workspace, secrets, and network namespace
Live status — see what’s running, stopped, or mid-deploy at a glance
One-click actions — restart, repair, or roll back without leaving the page

Chat

Rich Chat & Built-in Browser

Agents respond with screenshots, charts, and inline images — and they can browse the web themselves. Ask them to open TradingView, scrape a page, monitor a dashboard, or check on a deploy, and see exactly what they saw.

Headless Chromium built in — no separate browser tool to wire up
Rich message types — images, charts, and files render inline
Session memory — the conversation persists across visits

NovaRunning

take a screenshot of BTCUSDT on TradingView

Opening TradingView in my browser…

BTC/USDT · 1D$71,530+0.45%

Captured the daily chart — BTC at $71,530, up 0.45% today.

Type a message…

Ship Real Apps

Live App Preview & Routes

Build web apps right from chat. Any port your agent exposes is auto-routed to a public URL — iterate on UIs, dashboards, and APIs without leaving the conversation, and share the live link the moment it’s ready.

Public or protected — expose an API publicly while keeping admin routes behind your gateway token
Path stripping — clean routing with zero config on your app’s side
Edge network — TLS, DDoS mitigation, and HTTP/3 out of the box

Issue-Driven Development

A Board for the Work, Not Just the Chat

File issues on a board and assign them to your agent. It implements the change on its own branch and opens a pull request — you review the diff, cost, and timeline before merging. It’s the same board whether the work runs remotely or from your own machine with the CLI.

Never Lose a Task

Task Queue & Schedules

Queue messages while your agent is busy and schedule recurring jobs. Tasks are processed in order so nothing gets lost — fire and forget, then come back to the results whenever you’re ready.

Never Lose Work

Snapshots You Can Trust

Every workspace change is captured as a content-addressed snapshot. Browse the full history timeline and roll back to any previous state with one click — because CIDs are deterministic, you can always verify a snapshot hasn’t been tampered with.

snapshotsAUTO

QmTv...9eD42 min ago · 34 filescurrent

QmR9...2aB118 h ago · 34 files

QmXo...7kF32 days ago · 31 files

QmPa...4mN85 days ago · 27 files

Content-addressed — every state verifiable by its CID

Everywhere Your Users Are

Multi-Channel Messaging

One agent, all platforms. Connect Telegram, Discord, Slack, and WhatsApp from the same dashboard — same memory, same personality, same tools, wherever the conversation happens to start.

2 of 4 channels connected — same agent, same memory

Built for Real Development

Secrets, Git, Templates & ClawHub

The pieces every real project needs, built in from day one — not bolted on later.

Encrypted Secrets

API keys encrypted at rest, mounted straight into your agent.

Git Integration

Every agent workspace is a repo — clone, pull, and push with standard Git.

Templates

Deploy an exact, reproducible copy of a pinned workspace in one click.

ClawHub Marketplace

Community-built skills across trading, DeFi, social, and analytics.

defi-swap v1.2.0 CID verified

Content-Addressed Everything

Verifiable by Design

Every workspace snapshot, skill, and template is content-addressed and pinned to Pinata. Change one byte and the hash changes — supply-chain tampering is detectable by design, and every deploy is deterministic and reproducible.

Any Model, Your Keys

Chat Instantly, or Bring Your Own

Chat instantly through Pinata LLM with pay-as-you-go credits and zero API keys, or bring your own Anthropic, OpenAI, or OpenRouter key — 300+ models, switchable per agent at any time.

300+ more via OpenRouter

zero setup — pay with credits, no API key

Scriptable From Anywhere

Full-Featured CLI & API

Everything the dashboard does is scriptable from your terminal — create agents, send prompts, stream logs, manage secrets and tasks. Every capability is also a REST endpoint you can call directly with a platform token.

Explore the API Docs

Ready to Build?

Try it free with 10 hours of agent runtime — no credit card required.