AIAny
AI API2026
Icon for item

Meridian

Exposes the Claude Code SDK as a local Anthropic/OpenAI-compatible HTTP proxy so third-party tools can use Claude Max. Adds session management, streaming, multi-profile routing and OpenAI-format endpoints while respecting Anthropic's SDK auth, rate limits and prompt caching.

Introduction

Most tools expect an HTTP-compatible Anthropic or OpenAI endpoint, but Anthropic's Claude Max is primarily accessible via the Claude Code SDK. Meridian's core insight is simple: translate the SDK's programmatic access into the standard HTTP protocols editors and agents already speak, without bypassing Anthropic's authentication or usage controls. That makes Claude available to UIs and CLIs that otherwise only speak Anthropic or OpenAI APIs.

What Sets It Apart
  • Protocol translation with fidelity: Meridian uses the official Claude Code SDK for every request and converts responses into Anthropic/OpenAI formats — no credential interception, binary patches, or undocumented hacks. This preserves Anthropic-side caching, compaction, rate-limiting, and billing behavior.
  • Session & profile ergonomics: built-in conversation session management (LRU + on-disk persistence), multi-profile OAuth handling, automatic token refresh, and a telemetry dashboard let you run long-lived interactive workflows across accounts and restarts.
  • Interoperability first: provides both Anthropic Messages and OpenAI /v1/chat/completions endpoints, plus adapters for many client tools (OpenCode, Crush, Droid, Cline, Aider, Pi). Streaming, subagent concurrency, and tool passthrough are supported so existing tools can adopt Claude with minimal changes.
Who It's For and Trade-offs

Great fit if you run a Claude Max subscription and want to connect your preferred editor/agent or CI tools to Claude without changing frontends. It’s also useful for teams needing multi-profile routing or session persistence across restarts. Look elsewhere if you need an alternative that bypasses provider controls (Meridian explicitly does not) or if you require an upstream-hosted API key–style deployment — Meridian is designed as a local proxy tied to the Claude Code SDK and user OAuth sessions.

Where It Fits

Use Meridian when you need to integrate Claude into tools that accept an Anthropic/OpenAI base URL or when you want richer local session semantics than simple stateless API calls. It sits between client UIs and Anthropic's SDK, translating formats and managing session state while leaving authentication, billing, and token management to Anthropic.

Information

  • Websitegithub.com
  • Authorsrynfar
  • Published date2026/01/20

Categories

More Items

GitHub
AI Infra2026

Provides a unified tool catalog and proxy for AI agents: one team token lets agents call thousands of third-party endpoints (and your team’s keys) with per-call pricing. Injects credentials server‑side so agents never hold provider secrets, and exposes CLI/skill recipes and OAuth tools for team-wide use.

GitHub
AI API2026

Captures an app's network traffic, extracts its authentication/session bundle, and auto-generates an editable Python client to call the app's API. Supports mitmproxy, cURL and HAR capture backends and provides Session helpers for replay and token refresh.

GitHub
AI API2025

Gateway that pools multiple AI subscription accounts and issues platform API keys while handling authentication, token-level billing, load balancing, rate limits, and per-user/account concurrency—enables shared subscriptions for Claude, OpenAI, Gemini and Grok.