Skip to content
Migration Guide

Migrating from Helicone?
We’ve Got You Covered.

Helicone was acquired by Mintlify on March 3, 2026 and is now in maintenance mode -- security patches only. This guide walks you through migrating to Curate-Me in under 5 minutes with zero code changes.

One environment variable. One header. Full governance from day one.


What happened to Helicone

Mintlify, a documentation platform company, acquired Helicone on March 3, 2026. Helicone is now in maintenance mode -- the core team has been reassigned to Mintlify products, and only security patches are being shipped. No new features are planned.

Helicone (Maintenance Mode)

Acquired by Mintlify, March 2026

  • Security patches only -- no new features
  • Core team reassigned to Mintlify documentation products
  • No governance chain, personal data scanning, or cost enforcement
  • No managed runners or sandbox execution
  • Community support winding down

Curate-Me (Active Development)

Independent platform, weekly releases

  • Everything Helicone had, plus governance built-in
  • 5-step governance chain on every request
  • Real-time cost enforcement with daily budgets
  • Managed OpenClaw runners with sandbox execution
  • Weekly releases with new features and improvements

Feature mapping: Helicone to Curate-Me

Every Helicone feature has a direct equivalent in Curate-Me -- plus governance capabilities that Helicone never built.

Helicone FeatureCurate-Me Equivalent
Request loggingGateway audit trail (built-in)
Every proxied request is recorded with full request/response payloads, latency, and cost in an immutable audit log.
Cost trackingReal-time cost dashboard + budget alerts
Redis-backed real-time accumulator plus MongoDB audit log. Per-org daily budgets actively deny requests that would exceed limits.
Prompt templatesModel allowlists + governance policies
Instead of managing prompts, control which models each org can call. Governance policies enforce cost caps, personal data scanning, and rate limits.
User trackingPer-org, per-key, per-fleet cost attribution
Every API key maps to an org. Costs are attributed at the org, key, and fleet level with full drill-down in the dashboard.
CachingResponse cache (built-in)
Semantic response caching at the gateway level. Identical requests return cached responses without hitting the upstream provider.
Rate limiting5-step governance chain
Rate limiting is step 1 of a 5-step governance pipeline: rate limit, cost estimate, personal data scan, model allowlist, human approval gate.
AlertsWebhook alerts + CloudEvents
Budget threshold alerts, governance denials, and runner lifecycle events delivered via webhooks in CloudEvents format.

Migrate in 5 steps

The migration takes under 5 minutes. No SDK changes, no code refactoring -- just swap your base URL and auth header.

Sign up at dashboard.curate-me.ai

Create your account in 30 seconds. Free tier includes 10K requests per month. No credit card required.

Get your API key from Settings

Navigate to Settings, then API Keys. Your gateway API key (cm_sk_xxx) and base URL are displayed immediately.

Replace HELICONE_BASE_URL with OPENAI_BASE_URL

Change your environment variable from HELICONE_BASE_URL=https://oai.helicone.ai/v1 to OPENAI_BASE_URL=https://api.curate-me.ai/v1/openai.

Replace Helicone-Auth header with X-CM-API-Key

Swap the Helicone-Auth: Bearer sk_xxx header for X-CM-API-Key: cm_sk_xxx. If you used the base URL proxy method, this is the only header change.

(Optional) Set up governance policies in the dashboard

Configure daily budgets, model allowlists, personal data scanning rules, and rate limits. Default policies are applied automatically on signup.

Before and after: the entire migration

Before (Helicone)
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://oai.helicone.ai/v1", defaultHeaders: { "Helicone-Auth": "Bearer sk_xxx", }, }); const res = await client.chat.completions .create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello" }], });
Logging + cost tracking only. Maintenance mode.
After (Curate-Me)
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.curate-me.ai/v1/openai", defaultHeaders: { "X-CM-API-Key": "cm_sk_xxx", }, }); const res = await client.chat.completions .create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello" }], });
Full governance chain. Active development. Weekly releases.

Two lines changed. Everything else stays the same.


5-Minute Migration

Start Free Migration

Swap two lines. Get cost enforcement, personal data scanning, model allowlists, human approvals, managed runners, and an immutable audit trail -- all actively developed and supported.

10K requests/month free·No credit card required·Zero code changes