Graph Compose: Hosted Temporal Workflows with Visual Builder and AI

Graph Compose is a hosted platform for orchestrating API workflows on Temporal's durable execution engine. You define workflows as graphs of nodes (HTTP calls, AI agents, iterators, error boundaries) that run as Temporal workflows without managing infrastructure.
Three Ways to Build the Same Graph
Every workflow uses a consistent JSON format that can be created through:
- A React Flow visual builder
- A typed TypeScript SDK (@graph-compose/client)
- An AI assistant that turns plain English into a graph
How It Works
You submit JSON workflows via API to https://api.graphcompose.io/v1/workflows/execute and they run immediately on hosted Temporal. No deploy step, no Temporal cluster to run, no workers to deploy. The platform handles scheduling, retries, error boundaries, and state persistence.
Workflow Example
const workflow = {
"nodes": [
{
"id": "upload_image",
"type": "http",
"dependencies": [],
"http": {
"method": "PUT",
"url": "https://storage.example.com/{{ context.filename }}",
"headers": {
"Content-Type": "{{ context.contentType }}",
"Authorization": "Bearer {{ $secret('storage_token') }}"
},
"body": "{{ context.imageData }}"
},
"activityConfig": {
"retryPolicy": {
"maximumAttempts": 3,
"initialInterval": "1s",
"backoffCoefficient": 2
},
"startToCloseTimeout": "30 seconds"
}
},
{
"id": "generate_thumbnails",
"type": "http",
"dependencies": ["upload_image"],
"http": {
"method": "POST",
"url": "https://images.example.com/process",
"body": {
"source": "{{ results.upload_image.data.url }}",
"sizes": ["400x400", "200x200"]
}
}
}
],
"context": {
"filename": "profile.jpg",
"contentType": "image/jpeg"
}
}
Key Features
- Durable Execution: Workflows survive server restarts, network failures, and process crashes. Temporal replays from the last checkpoint.
- Automatic Retries: Configure retry policies per node with max attempts, backoff intervals, and non-retryable error types.
- Error Boundaries: Wrap nodes in try/catch-style error boundaries with fallback behavior.
- State Persistence: Query workflow state at any point.
- Template Expressions: Nodes reference results from upstream nodes via
{{ results.node_id.data.field }}syntax.
Licensing
Open-core model: the execution foundations and integrations service are AGPL-3.0, while the platform orchestrator, visual builder, and AI assistant are proprietary.
📖 Read the full source: HN AI Agents
👀 See Also

MCP Slim: Local Embedding Search for MCP Tools Reduces Context Bloat
MCP Slim is a proxy that replaces full MCP tool catalogs with three meta-tools (search, describe, call), using local MiniLM embeddings for semantic search. It achieves 96% context window reduction and works offline without API keys.

Open-sourced self-healing skill for AI agents detects and fixes failures automatically
A new open-source skill enables AI agents to automatically detect failures, diagnose root causes, and implement fixes. It includes a failure scanner for crons, sub-agents, and deploy logs, plus a database that learns from previous fixes.

Context Gateway: An Open-Source Proxy for Compressing AI Agent Context
Context Gateway is an open-source proxy that sits between coding agents and LLMs, compressing tool outputs before they enter the context window. It uses small language models to detect signal in context, performs background compaction at 85% window capacity, and includes spending caps, a dashboard, and Slack notifications.

ClawDeckX: Open-Sourced macOS-Style Web Platform for OpenClaw Agent Management
ClawDeckX is an open-source web platform for installing, configuring, and monitoring OpenClaw agents. It provides visual management tools, real-time monitoring, and supports 13 languages.