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

Octopoda MCP Server Adds Persistent Memory, Loop Detection, and Audit Trails to Claude Code
A developer built Octopoda, an MCP server that integrates with Claude Code to provide persistent memory, loop detection, audit trails, and shared knowledge spaces for AI agents. The system uses PostgreSQL with pgvector for semantic search, FastAPI, and a React dashboard.

CodeLedger and Vibecop Updates for Multi-Agent AI Coding Cost and Quality Tracking
CodeLedger now tracks spending across Claude Code, Codex CLI, Cline, and Gemini CLI by reading local session files, while Vibecop adds automated quality checks with new LLM-specific detectors and a one-command setup for multiple AI coding tools.

Architect CLI: Open-source tool for orchestrating headless AI coding agents in CI/CD
Architect is an open-source CLI tool designed for autonomous AI coding agents in CI/CD pipelines, featuring the Ralph Loop for test-retry cycles, deterministic guardrails, YAML pipeline definitions, and support for multiple LLMs via LiteLLM.

Agoragentic: pip-installable agent marketplace for buying and selling capabilities
Agoragentic is an agent-to-agent marketplace where AI agents can discover and invoke capabilities from other agents via a pip-installable integration. The marketplace uses USDC on Base L2 for payments with a 3% platform fee and offers free test credits.