The NeuralHub API provides programmatic access to agents, compute, and knowledge. Use it to build autonomous workflows, integrate agents into your apps, or manage infrastructure.
All requests must be authenticated. We support both Bearer Tokens (API Keys) and Session Cookies (Browser).
https://api.neuralhub.xyzFor agents and scripts, use the API Key:
The core of NeuralHub. Use this endpoint to run any Agent, Tool, or Workflow. It handles queuing, persistence, and state management.
Pro Tip: This is the preferred way to interact with agents. It replaces legacy endpoints like /agent-loop.
/v1/runThe Unified Execution Engine. Trigger an Agent, Tool, or Workflow.
{
"target": "agent_default",
"type": "agent",
"input": {
"goal": "Find the latest news on AI agents"
},
"async": true
}{
"runId": "550e8400-e29b-41d4-a716-446655440000",
"status": "pending"
}/v1/run/{runId}Poll the status of an execution run.
{
"runId": "550e8400...",
"state": "SUCCESS",
"result": "The internet started in the 1960s with ARPANET...",
"events": [
{
"tool": "web_search",
"input": "ARPANET history",
"output": "..."
}
],
"createdAt": "2026-02-06T12:00:00Z"
}Manage your fleet of autonomous agents.
/v1/agentsList all agents in the workspace.
[
{
"id": "agent_1",
"name": "Research Assistant",
"model_id": "google/gemini-2.5-flash-lite"
}
]/v1/agents/{id}Get details of a specific agent.
{
"id": "agent_1",
"name": "Research Assistant",
"system_prompt": "You are a helpful researcher..."
}Long-term semantic memory for agents. Content is automatically embedded (OpenAI text-embedding-3) and stored in vector database.
/v1/memoryStore a memory (automatically embedded).
{
"content": "The user prefers Python over JavaScript.",
"metadata": {
"source": "chat_session_1"
}
}{
"id": "mem_123",
"created_at": "..."
}/v1/memory/searchSemantic search over memories.
[
{
"id": "mem_123",
"content": "User prefers Python...",
"similarity": 0.89
}
]Workspace-isolated object storage (Vercel Blob). Use this for large assets, datasets, or agent outputs.
/v1/storage/uploadUpload a file to workspace isolated storage.
Binary File Content
{
"url": "https://...public.blob.vercel-storage.com/workspace-id/file.png",
"pathname": "workspace-id/file.png"
}/v1/storage/listList files in workspace storage.
{
"blobs": [
{
"url": "...",
"pathname": "..."
}
]
}Stateless LLM inference. Proxies to best-in-class models via OpenRouter/Google. Fully compatible with OpenAI SDKs.
/v1/modelsGet list of supported AI models and their capabilities.
{
"models": [
{
"id": "google/gemini-2.5-flash-lite",
"input_cost": 0.1,
"output_cost": 0.3
}
]
}/v1/chat/completionsOpenAI-compatible chat completion. Supports streaming.
{
"model": "google/gemini-2.5-flash-lite",
"messages": [
{
"role": "system",
"content": "You are an assistant."
},
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}{
"id": "chatcmpl-123",
"object": "chat.completion",
"choices": [
{
"index": 0,
"message": {
"content": "Hello!"
}
}
]
}On-demand serverless resources. Execute python or nodejs code securely.
/v1/resourcesList active resources.
[
{
"id": "sbx-1",
"template": "python-data",
"url": "https://..."
}
]/v1/resourcesLaunch a new MicroVM resource.
{
"template": "python-data",
"env": {
"MY_VAR": "value"
}
}{
"id": "sbx-1",
"url": "https://..."
}/v1/resources/{id}Terminate a resource immediately.
Endpoints for agents to discover capabilities. Compliant with the Model Context Protocol standards.
/llms.txtStandardized capability discovery file for AI agents.
{
"content": "# NeuralHub Capabilities\n- Web Search..."
}/v1/mcp/manifestModel Context Protocol (MCP) manifest for tool discovery.
{
"tools": [
{
"name": "web_search",
"description": "Search Google"
}
]
}Manage programmatic access credentials.
/v1/keysCreate a new API key for your workspace. Returns the raw key only once.
{
"name": "Agent Production Key",
"scopes": [
"chat:write",
"run:write",
"memories:read"
]
}{
"key": "nh_a1b2c3d4...",
"id": 42,
"prefix": "nh_a1b2",
"created_at": "2026-02-06T12:00:00Z"
}/v1/keysList active API keys (masked).
{
"keys": [
{
"id": 42,
"name": "Agent Key",
"prefix": "nh_a1b2",
"last_used_at": null
}
]
}