> ## Documentation Index > Fetch the complete documentation index at: https://pinata-mintlify-a8f2129e.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Overview > Hosted AI agents that can run code, manage files, and connect to other services Pinata Agents gives you a hosted AI agent in its own sandboxed container. The agent has a workspace it can read and write to, a terminal it can run commands in, and connectors for the outside world — chat apps, web servers, scheduled jobs. You talk to it through the dashboard, the CLI, or whichever messaging platform you connect it to. Each agent runs on an **Agent Engine** — `openclaw` (default) for full configurability, `hermes` for an opinionated smoother out-of-the-box experience, or `super-builder` (beta), a headless coding agent built for [issue-board work](/agents/issues). You pick one when you create the agent. The default OpenClaw engine is documented at [openclaw.org](https://openclaw.org); for the differences see [Concepts → Engine](/agents/concepts#engine). New accounts get a **10-hour free trial** of agents — no payment and no LLM key required, thanks to the free-tier model available throughout your account. After the trial, agents require a paid plan. [Upgrade here](https://app.pinata.cloud/billing). ## Get your first agent running It takes a couple of minutes. You'll pick an LLM provider, create the agent, and start chatting. ### 1. Pick an LLM provider Your agent needs an LLM to think. You have three options: * **Free tier — no key, zero config.** Select the **Free tier** card in the Create Agent wizard and skip provider setup entirely. Your agent runs on a shared, rate-limited model (OpenRouter's free pool, e.g. `openrouter/free`) that's available throughout your account. Expect lower quality, smaller context, and occasional rate limits compared with a paid provider — but it's a real agent, free, today. * **Pinata-hosted models — no key, pay as you go.** Connect the **Pinata** card in the [Secrets Vault](https://agents.pinata.cloud/secrets). It's first-party, so there's no API key to paste — connecting just turns on [Pinata Inference](/inference/overview) for your account. Your agent gets full-quality hosted models, billed per token from your [credit balance](/inference/credits). The same models are also callable directly over an OpenAI-compatible [API](/inference/chat-completions). * **Bring your own key.** Go to the [Secrets Vault](https://agents.pinata.cloud/secrets). At the top of that page you'll see a row of provider cards: **Anthropic**, **OpenAI**, **OpenRouter**, **Venice**, and **Custom**. Click **Connect** on whichever one you use, paste your API key (or run through OAuth if you're using an OpenAI Codex subscription), and save. Start free, upgrade whenever — adding a provider key in Secrets later unlocks full model capabilities for the same agent, no re-create needed. You can connect more than one provider — useful so you have a fallback if one is down. ### 2. Create an agent Head to [My Agents](https://agents.pinata.cloud/agents) and click **Create Agent**. You have two paths: * **Start from a template** — fastest. Templates come pre-wired with skills, settings, and a personality. Pick one from the [Marketplace](https://agents.pinata.cloud/marketplace) (others' templates) or [My Templates](https://agents.pinata.cloud/templates) (your own). Add the secrets it needs, deploy. * **Build from scratch** — full control. The wizard walks you through naming the agent, choosing an **Agent Engine** (OpenClaw, Hermes, or Super Builder), picking an AI provider (including the free tier), a personality preset, skills, and optionally channels before deploy. Either way, the agent takes about 30 seconds to provision. When it's ready you land on its Chat tab. Plans cap how many agents you can run at once. If a deploy fails with "Agent limit reached", delete an agent you're not using or upgrade your plan. ### 3. Start a conversation Say hello. Ask it to write some code, summarize a webpage, or set up a workflow. It can use a terminal, edit files, search the web, and call any skills you've attached. Image ## Finding your way around The sidebar on the left is the same on every page. Top half is the workspace itself; bottom half is account and support. | Section | What's in it | | ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **My Agents** | Every agent you've created. Click one to expand its tabs (Chat, Channels, Files, Skills, etc.). The **ⓘ** on each agent card opens a floating info peek — live status, the default-model picker, skill/secret/task counts, and live CPU, memory, disk, and network meters. | | **My Issues** | Kanban boards for assigning work to agents — file an issue, the agent runs it, you review the diff. See [Issues & Boards](/agents/issues). | | **Skills Library** | Skills you've installed, plus a community catalog under **Browse ClawHub**. | | **Secrets Vault** | All your encrypted credentials, in one place, shared across agents. | | **My Templates** | Templates you've created or imported. | | **Marketplace** | Published templates from Pinata and other builders, ready to deploy in one click. | | **Account** | **Workspaces** (switch teams), **Integrations** (e.g. GitHub OAuth), **Activity** (audit log). | | **Support** | Docs, the OpenAPI reference, changelog, and a way to chat with the Pinata team. | **⌘K** (or **Ctrl+K**) opens a command palette for jumping to any agent, page, or action. ## The agent dashboard Click any agent and you'll see tabs across the top of the page. Each tab is a slice of how the agent works: * **Chat** — your conversation with the agent * **Channels** — wire it up to Telegram, Slack, or Discord * **Files** — a file browser for the agent's container, workspace snapshot history, content diffs, git URL * **Skills** — capabilities attached to this specific agent (pulled from your Skills Library) * **Secrets** — provider connections and env vars this agent can see * **Models** — which models from your providers it's allowed to use, and which is the default * **Routes** — path routes and custom domains for any web service it runs * **Tasks** — cron jobs and one-off scheduled prompts * **Console** — a terminal inside the container * **Logs** — real-time log stream * **Danger** — full configuration overview, plus restart and delete That last one is named "Danger" deliberately — restart and delete live there, but so does most of the inventory data, so it's also the page you'll open when you need to know exactly how an agent is configured. ## Editing the workspace locally Your agent's workspace is a git repo you can clone and push to. ```bash theme={null} git clone https://agents.pinata.cloud/v0/agents/{agentId}/git my-agent ``` On the Files tab, **Copy with Token** gives you a URL with authentication built in so you don't have to manage credentials. Edit locally, push, and the agent picks up your changes — the build script (if you've defined one) runs automatically. See [Files & Snapshots](/agents/snapshots) for the full flow. ## Working from the terminal Everything in the dashboard is in the CLI too: ```bash theme={null} pinata agents list # See your agents pinata agents create # Create a new agent pinata agents get # Get agent details pinata agents chat # Talk to it from your terminal ``` Full reference: [Agents CLI](/tools/cli/agents). ## Going deeper Glossary, file layout, and how the pieces relate Every field in `manifest.json`, the source of truth for an agent's config Auth model and endpoint reference for building against the platform What to do when something doesn't work Assign work on a kanban board and review the diff Deploy a pre-built agent in one click Let people talk to your agent on Telegram, Slack, or Discord Add capabilities — IPFS storage, memory, on-chain identity, more Expose a web app or API from inside the agent