62 models · Built-in · OpenAI · Anthropic

Composable
Intelligence.

RAG · Agents · Workflows · MCP — one API.
Edge-native, multi-tenant, starting free.

quickstart.ts
import { Neureus } from '@neureus/sdk'

const client = new Neureus({ apiKey: 'nai_...' })
const { text } = await client.ai.chat({
  model: 'meta/llama-3.3-70b',
  messages: [{ role: 'user', content: prompt }]
})

One API.
The complete AI backend.

Stop stitching together OpenRouter, Pinecone, LangChain, and Datadog. Neureus is the backend — RAG, agents, workflows, and multi-model orchestration in a single, tenant-isolated API.

1
API key
<5 min
to first request
$715
saved vs. DIY stack
62
AI models

Everything your AI app needs.
Built in.

AI Gateway
Multi-provider routing across built-in models, OpenAI, and Anthropic. Streaming, BYOK encryption, and per-tenant cost tracking.
RAG Pipeline
Ingest URLs or raw content, chunk, embed, and query semantically. Per-tenant isolated — no cross-boundary leakage.
Agent Framework
ReAct-loop agents with tool use, memory, and full audit logging. 20 production templates across 5 verticals — deploy in one click.
Workflow Engine
Durable, stateful workflows with human-in-the-loop approval gates, role-based assignment, and configurable timeouts.
MCP Server
Every Neureus capability exposed as MCP tools over Streamable HTTP. Any AI agent, IDE, or framework can call them with zero extra wiring.
Composite Intelligence
7 multi-model orchestration patterns — Generate+Verify, Cascade, Fan-out — for outputs that no single model can match alone.

Mix models. Compose patterns.
Get better answers.

No single model is best at everything. Neureus lets you orchestrate multiple models in coordinated patterns — so your app always uses the right model for each step.

01 Generate + Verify Draft then critique for higher-quality output
02 Parallel Specialists Multiple domain experts answer simultaneously
03 Consensus Aggregate answers across models for reliability
04 Chain Sequential pipeline with context passing
05 Cascade Escalate to more capable models only when needed
06 Hierarchical Orchestrator delegates to specialist subagents
07 Fan-out / Fan-in Split work, process in parallel, recombine
Industry profiles
HealthcareLegalFinancialCodingContentSupport

Each profile includes domain-specific system prompts and PHI/PII compliance guards.

Start from a template.
Ship it anywhere.

20 production-ready agents across 5 verticals. Deploy in one click, then surface via widget, REST API, or MCP.

Finance
KYC screening · Statement analysis · Investment memos · Loan risk review
Legal
Contract redlining · RFP drafting · Due diligence Q&A · Patent summaries
Healthcare
Patient FAQ · Clinical notes · Claim risk · Drug interactions
Support
Helpdesk triage · Policy Q&A · Escalation routing · Sentiment analysis
Operations
Meeting prep · HR policy bot · IT ticket triage · Budget Q&A
Chat widget
One <script> tag embeds a streaming chat drawer on any page.
REST API
OpenAI-compatible endpoint for any HTTP client or SDK.
MCP server
Every capability available as MCP tools. Any AI agent or framework can call them with zero extra wiring.

Human oversight and
tenant isolation. Built in.

Everything regulated industries require — approval gates, SSO, granular roles, and boundaries that never cross.

Human-in-the-Loop
Pause workflows at high-stakes steps for human review — role-based assignment, configurable timeouts, full audit trail.
Tenant Isolation
Every tenant gets its own gateway, RAG index, and encrypted BYOK keys. Logs, costs, and queries never cross boundaries.
SSO & RBAC
OIDC SSO with Okta, Azure AD, and Google. Four-tier RBAC: owner, admin, developer, viewer. Passkey-only auth, zero passwords.
Edge Infrastructure
300+ edge locations worldwide. &lt;80ms p95, 99.99% uptime SLA, 0 cold starts. No container management.

Start building with
Composable Intelligence.

Free tier includes 5M AI tokens, RAG, agents, workflows, and all 7 composition patterns. No credit card required.