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

# Ensemble Edge

> AI orchestration, edge-native — built exclusively for Cloudflare

**AI orchestration, edge-native — built exclusively for Cloudflare.**

Build AI workflows that you actually control. No proprietary platforms, no vendor lock-in, no serverless sprawl. Just Git, YAML, and Cloudflare Workers—with zero cold starts across 300+ global locations.

You're an engineer. You deserve tools that treat you like one.

## The Problem

You've got 50+ prompts, 20+ agents, dozens of SQL queries scattered across your codebase. Change one, break three others. Rollback means Git archaeology. A/B testing means deployment hell.

And every "AI orchestration platform" wants you to hand over control to some black box that the head of sales bought because the pitch deck looked good.

**You know there's a better way.**

## Components  Agents  Ensembles

The building blocks are simple:

<CardGroup cols={3}>
  <Card title="Components" icon="cube">
    Versioned artifacts: prompts, configs, queries, scripts. Each gets its own version history. Mix and match optimal versions from different points in time.
  </Card>

  <Card title="Agents" icon="robot">
    Workers that execute: AI reasoning, database queries, HTTP calls, business logic. Each agent uses operations and components to get work done.
  </Card>

  <Card title="Ensembles" icon="network-wired">
    Orchestration workflows: YAML files that coordinate agents into complex workflows. Execute at the edge in \<50ms cold starts.
  </Card>
</CardGroup>

## Edgit: Git-Native Component Versioning

Version every AI component independently. Deploy any combination from any point in history. Rollback in \<50ms globally.

```bash theme={null}
# Each component versions independently
edgit tag create extraction-prompt v1.0.0
edgit tag create company-agent v2.1.0
edgit tag create validation-query v0.5.0

# Deploy the optimal combination - cherry-pick from history
edgit tag set extraction-prompt prod v0.1.0  # Ancient but perfect
edgit push --tags --force

edgit tag set company-agent prod v3.0.0      # Latest stable
edgit push --tags --force

edgit tag set validation-query prod v2.5.0   # Best performance
edgit push --tags --force

# Instant rollback
edgit tag set extraction-prompt prod v0.1.0  # &lt;50ms globally
edgit push --tags --force
```

**Edgit creates and manages git tags. That's it.** GitHub Actions handles deployment.

All version data lives in Git tags. Your CI/CD deploys to Cloudflare KV. Every version ever created is instantly accessible at the edge.

<Card title="Get Started with Edgit" icon="rocket" href="/edgit/overview">
  Start versioning components in 5 minutes
</Card>

## Conductor: YAML-Driven Edge Orchestration

Define AI workflows in YAML. Execute at 300+ global locations on Cloudflare Workers. Zero cold starts via V8 isolates. No DAG builders, no UI-driven workflows, no central orchestrator bottleneck.

```yaml theme={null}
# ensembles/company-intelligence.yaml
name: company-intelligence

agents:
  - name: fetch-company-data
    operation: http
    config:
      url: https://api.example.com/companies/${input.domain}
      cache_ttl: 3600

  - name: analyze-financials
    operation: think
    component: financial-analysis-prompt@v2.1.0
    config:
      model: claude-3-5-sonnet-20241022
    input:
      company_data: ${fetch-company-data.output}

  - name: generate-report
    operation: think
    component: report-generation-prompt@v1.5.0
    input:
      analysis: ${analyze-financials.output}
```

**Define workflows in Git. Deploy to Cloudflare Workers. State management, caching, parallelization built-in.**

<Card title="Learn About Conductor" icon="network-wired" href="/conductor/overview">
  Edge orchestration for AI workflows
</Card>

## The Versioning Multiverse

With independent versioning of components AND agents, you unlock infinite combinations:

```yaml theme={null}
# Same ensemble, different realities running in parallel
ensemble: analysis-pipeline

agents:
  # Production: stable + conservative
  - name: prod-analyzer
    agent: analyzer@v1.0.0        # Stable agent version
    component: prompt@v1.0.0      # Conservative prompt

  # Experimental: new everything
  - name: exp-analyzer
    agent: analyzer@v2.0.0-beta   # New agent logic
    component: prompt@v2.1.0      # Aggressive prompt

  # Hybrid: stable agent, new prompt
  - name: hybrid-analyzer
    agent: analyzer@v1.0.0        # Stable agent
    component: prompt@v2.1.0      # New prompt only
```

**Test: 2 agent versions  3 prompt versions  2 configs = 12 variants running simultaneously.**

Perfect for A/B testing, progressive rollouts, and reproducing bugs from last Tuesday at 2:47 PM.

## Why This Exists

Modern AI development is broken:

1. Ship v1.0.0 of your app
2. Change a prompt
3. Everything becomes v2.0.0
4. Original prompt trapped in Git history
5. Can't A/B test old vs new
6. Can't mix optimal versions
7. Rollback means reverting the entire codebase

**This is insane for systems with 100+ independently evolving components.**

Ensemble Edge treats AI components like they deserve: individually versioned, independently deployable, infinitely composable.

Then orchestrates them at the edge where they execute fast and scale infinitely.

## Architecture Principles

<AccordionGroup>
  <Accordion icon="globe" title="Edge-First">
    Purpose-built for Cloudflare's edge infrastructure: Workers, Workers AI, KV, D1, R2, Durable Objects, Queues, and Vectorize. No centralized compute. No single point of failure.
  </Accordion>

  <Accordion icon="git-alt" title="Git-Native">
    Configuration and orchestration and versioning live in Git. No proprietary storage. You own the source of truth.
  </Accordion>

  <Accordion icon="bolt" title="Cache-Central">
    Multi-layer caching with TTL control. Agent-level cache settings. Cache-first thinking reduces costs and latency by 10x.
  </Accordion>

  <Accordion icon="check-square" title="Structured Outputs">
    AI operations produce machine-readable and type-safe output validated via JSON schema. No string parsing and no hallucinated JSON.
  </Accordion>

  <Accordion icon="chart-line" title="Observable by Default">
    Every execution emits structured logs and metrics. Debugging and monitoring are effortless and not afterthoughts.
  </Accordion>

  <Accordion icon="code-branch" title="Open by Default">
    Core tooling (Edgit and Conductor) is open source. We charge for managed services and not lock-in.
  </Accordion>
</AccordionGroup>

## Quick Start

<CardGroup cols={2}>
  <Card title="Get Started" icon="download" href="/introduction/ensemble-cli">
    ```bash theme={null}
    npx @ensemble-edge/ensemble
    # Or: npx @ensemble-edge/ensemble conductor init my-project
    ```
  </Card>

  <Card title="Version Components" icon="tags" href="/edgit/guides/versioning-components-agents">
    ```bash theme={null}
    npx @ensemble-edge/edgit tag create my-prompt v1.0.0
    npx @ensemble-edge/edgit tag set my-prompt prod v1.0.0
    npx @ensemble-edge/edgit push --tags --force
    ```
  </Card>

  <Card title="Deploy to Edge" icon="rocket" href="/conductor/getting-started/your-first-deployment">
    ```bash theme={null}
    npm run build
    npx wrangler deploy
    # Live at https://your-worker.workers.dev
    ```
  </Card>
</CardGroup>

## Status

<CardGroup cols={3}>
  <Card title="Edgit" icon="cube">
    Active development

    Component & agent versioning
    Deployment management
    Git-native tags
    Discovery tools
  </Card>

  <Card title="Conductor" icon="network-wired">
    Production-ready

    Edge orchestration
    10+ operations
    8+ pre-built agents
    State management
    A/B testing
    276 tests passing
  </Card>

  <Card title="Cloud" icon="cloud">
    Design phase

    Managed service with generous free tier (coming soon)
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={3}>
  <Card title="Core Concepts" icon="book" href="/introduction/core-concepts">
    Understand the building blocks
  </Card>

  <Card title="5-Minute Quick Start" icon="play" href="/introduction/quick-start">
    Get running in 5 minutes
  </Card>

  <Card title="Edgit Docs" icon="cube" href="/edgit/overview">
    Component versioning and deployment
  </Card>

  <Card title="Conductor Docs" icon="network-wired" href="/conductor/overview">
    Edge orchestration framework
  </Card>

  <Card title="Playbooks" icon="lightbulb" href="/conductor/playbooks/rag-pipeline">
    Real-world patterns and recipes
  </Card>

  <Card title="Community" icon="comments" href="https://github.com/ensemble-edge/edgit/discussions">
    GitHub discussions and support
  </Card>
</CardGroup>

<Note>
  Built by engineers who believe AI tooling should be as solid as the infrastructure it runs on.

  No buzzwords. No hand-holding. Just tools that work.
</Note>