> ## Documentation Index
> Fetch the complete documentation index at: https://hastekit.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> HasteKit — The end-to-end platform for building, deploying, and observing AI agents

**HasteKit** brings everything you need to ship production-grade AI agents into a single, cohesive platform — from model configuration and tool orchestration to durable workflows, multi-channel deployment, and OpenTelemetry observability. No more stitching together LangSmith, n8n, Temporal, and a half-dozen SaaS dashboards.

This guide walks through the platform in the order you'll naturally consume it: configure a model, build an agent, give it tools and memory, test it, deploy it, and observe it in production.

***

## 1. Start with the Agent Builder

The Agent Builder is the heart of HasteKit. Every agent is configured through a dashboard — no code required — across a set of focused tabs covering the model, prompt, tools, memory, and output contract.

<CardGroup cols={2}>
  <Card title="Model & Parameters" icon="microchip">
    Pick from 8 providers (OpenAI, Anthropic, Gemini, xAI, Bedrock, OpenRouter, Ollama, ElevenLabs) and tune temperature, top\_p, reasoning effort, parallel tool calls, max output tokens, and provider-specific extras like Anthropic `cache_control` and `thinking`.
  </Card>

  <Card title="System Prompt" icon="message-pen">
    Write a prompt inline, or reference a **versioned prompt template** with `{{variable}}` interpolation that's reusable across agents.
  </Card>

  <Card title="Structured Output" icon="brackets-curly">
    Enforce a JSON schema on agent responses with a schema builder UI (or raw JSON) so downstream code consumes agent output without ad-hoc parsing.
  </Card>

  <Card title="Conversation History" icon="comments">
    Built-in thread management with configurable summarization strategies to keep context windows — and cost — under control.
  </Card>
</CardGroup>

***

## 2. Give Your Agent Tools

Tools are how agents take action. Every tool — built-in, MCP, OpenAPI, connector, sub-agent, or workflow — has independent **Enabled**, **Requires Approval**, and **Deferred** switches.

### Built-in tools

<CardGroup cols={2}>
  <Card title="Image, Speech & Transcription" icon="wand-magic-sparkles">
    Generate images (xAI grok-imagine, OpenAI gpt-image-1), synthesize speech (ElevenLabs Flash v2.5), and transcribe audio (ElevenLabs scribe\_v2) with configurable provider, model, voice, and language.
  </Card>

  <Card title="Web Search & Code Execution" icon="globe">
    First-class web search and Python/JS code execution — useful tools available out of the box without wiring up MCP servers.
  </Card>

  <Card title="Sandbox" icon="box">
    A Docker-backed bash sandbox with configurable image and environment variables for safe, isolated shell execution.
  </Card>

  <Card title="Todo & Schedule" icon="list-check">
    A built-in todo list for progress tracking on long tasks, and a schedule tool that lets agents schedule themselves via cron or one-off triggers.
  </Card>
</CardGroup>

### Bring your own tools

<CardGroup cols={2}>
  <Card title="MCP Servers" icon="plug">
    Attach Streamable HTTP or SSE MCP servers with custom headers, tool filters, approval requirements, and deferred loading.
  </Card>

  <Card title="OpenAPI → Tools" icon="file-code">
    Import any OpenAPI 3.x spec — each operation becomes an agent tool, with HTTP requests handled automatically.
  </Card>

  <Card title="Connector Actions" icon="link">
    Expose individual actions from GitHub, Gmail, Google Calendar, Jira, Slack, and Telegram as tools your agent can call directly.
  </Card>

  <Card title="Function Tools & Code" icon="code">
    Define custom tools as code when you need full control over execution.
  </Card>
</CardGroup>

***

## 3. Add Memory, Knowledge & Skills

Tools handle *doing*. The next layer is what your agent *knows*.

<CardGroup cols={2}>
  <Card title="Knowledge Bases (RAG)" icon="book">
    Create local knowledge bases with configurable chunking (size, overlap, separators) and embedding provider/model/dimension. Attach any number to an agent for retrieval-augmented answers with citations.
  </Card>

  <Card title="Skills" icon="screwdriver-wrench">
    Author reusable `SKILL.md` packages of prompts, scripts, and docs in the editor or upload a zip. Pinned skills are mounted at `/skills/<name>/` inside the agent's sandbox.
  </Card>

  <Card title="Long-term Memory" icon="brain">
    Attach a memory service with **Semantic** (facts) and **Episodic** (events over time) memory types. Each service has its own model, prompt, and extraction cadence. The `memory_search` and `memory_add` tools are auto-exposed to the agent.
  </Card>

  <Card title="Codebases" icon="code-branch">
    Connect GitHub repositories via the GitHub connector. They're auto-synced and attachable to agents for code-aware reasoning.
  </Card>
</CardGroup>

***

## 4. Compose Multi-Agent Systems

Skip the monolithic prompt. Decompose your agent into focused specialists and have them collaborate.

<CardGroup cols={2}>
  <Card title="Agent as a Tool" icon="people-group">
    Invoke a sub-agent as a tool with **Isolated** or **Shared** context modes. The parent agent stays in control and aggregates results.
  </Card>

  <Card title="Handoffs" icon="people-arrows">
    Hand off the conversation mid-flight to a specialist agent. The user keeps chatting; the right agent answers.
  </Card>

  <Card title="Human-in-the-Loop" icon="user-check">
    Flag any tool (built-in, MCP, connector, sub-agent, workflow) as **Requires Approval**. Sensitive actions wait for a human decision before executing.
  </Card>

  <Card title="Deferred Tools" icon="layer-group">
    Load tools on demand instead of all at once. Keep context windows small even with hundreds of tools available.
  </Card>
</CardGroup>

***

## 5. Orchestrate with DAG Workflows

When logic gets complex enough that you want deterministic control flow — not LLM judgment — build a workflow on the visual canvas and expose it to your agent as a tool.

* **Trigger types** — invoked by an agent, cron schedule, or GitHub events (PR opened/updated/closed, issue opened, issue comment, push).
* **Node types** — HTTP Request, AI Agent, Code (JS), and connector actions for GitHub, Gmail, Google Calendar, Jira, Slack, and Telegram.
* **Control flow** — `If`, `Switch`, `Delay`, and `End` nodes for branching, waiting, and returning structured output.
* **Runtime** — run **Local** for low latency, or back the workflow with **Temporal** so every node runs as a durable activity with automatic checkpointing and retries.

Any saved workflow can be called as a tool from any agent — combining the determinism of a DAG with the flexibility of an LLM.

***

## 6. Test in the Built-in Chat

Iterate without leaving the dashboard. The chat UI supports per-message agent and version selection, file/image/audio attachments, inline tool-call visualizations, editable context JSON, custom request headers, and one-click jumps to the underlying trace. Debug, iterate, and ship without a separate client.

***

## 7. Deploy to Your Users

Once your agent works in the chat, put it in front of users.

<CardGroup cols={2}>
  <Card title="Channels" icon="comment-dots">
    Bind any agent to a **Telegram** or **Slack** channel. Each channel gets a unique webhook URL — paste it into Slack Event Subscriptions or your Telegram bot config and you're live.
  </Card>

  <Card title="Triggers" icon="bolt">
    Auto-invoke agents (or workflows) on a **cron** schedule, a **one-off future time**, or a **connector event** like a new GitHub PR. Status, edit, and delete controls are all visible from the dashboard.
  </Card>

  <Card title="HTTP API" icon="cloud">
    Every agent is also callable via HTTP using a virtual key — drop it into your existing application with a single request.
  </Card>

  <Card title="Versions & Aliases" icon="code-fork">
    Every save creates an immutable version. Point a `production` alias at any version — or **split traffic between two versions** for canary releases — and roll back instantly when needed.
  </Card>
</CardGroup>

***

## 8. Observe Everything

Every agent run, tool call, and LLM request emits **OpenTelemetry traces** — complete with token usage, latency, and cost attribution.

Drill into a hierarchical span tree: `AgentTrigger.HTTP → LoadMessages → GetPrompt → VirtualKeyMiddleware → LLM.StreamingResponses → SaveMessages`. Each span shows duration, status, attributes (`agent_name`, `project_id`, `user_id`, `org_id`), and parent/child links. Aggregate dashboards roll up spans, error rate, average duration, and active services across any time range.

***

## 9. Secure & Govern

<CardGroup cols={2}>
  <Card title="Virtual Keys" icon="key">
    Issue `sk-uno-...` virtual keys scoped to specific providers, models, and rate limits. Hand out one credential and centrally control access.
  </Card>

  <Card title="Secret Manager & Credentials" icon="shield-halved">
    Encrypted per-project vault for OAuth client IDs/secrets, bot tokens, and webhooks. Credentials are masked once saved.
  </Card>

  <Card title="Organisation & Roles" icon="users">
    Owner and Collaborator roles at the org level, with project-scoped resources for clean separation of work.
  </Card>

  <Card title="Project Export" icon="box-archive">
    Export an entire project as a ZIP for portability, backup, or environment promotion.
  </Card>
</CardGroup>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Build an Agent" icon="robot" href="/docs/gateway/agent-builder/agent-runtime">
    Configure your first agent with tools, skills, and structured output.
  </Card>
</CardGroup>