smartlizi GitHub avatar

claude_web2api

smartlizi

A proxy service that wraps Claude.ai web models into OpenAI and Anthropic API-compatible endpoints with tool calling, streaming, multi-account management, and load balancing.

Stars

17

7-day growth

No data

Forks

7

Open issues

0

License

No data

Last updated

2026-07-12

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

Offers dual-format API compatibility (OpenAI and Anthropic) with ReAct-based tool calling, robust anti-detection via cf_clearance automation, and intelligent key pool management for high availability.

Who it is for

  • Developers integrating Claude web models into existing applications
  • Users needing OpenAI SDK/Anthropic SDK compatible endpoints for Claude
  • Teams managing multiple Claude accounts for load balancing and fallback
  • Developers exploring tool-calling capabilities without native function calling support

Use cases

  • Build chat applications using OpenAI SDK with Claude models
  • Run automated agents with tool calling via Anthropic Messages API
  • Monitor and manage multiple Claude accounts through a web panel
  • Test Claude models for various tasks with streaming and dynamic model list

Strengths

  • Dual-format API (OpenAI v1/chat/completions and Anthropic v1/messages) for seamless integration
  • ReAct-based tool calling with 100% trigger rate claimed (30 requests tested)
  • cf_clearance auto-fetch using DrissionPage for high anti-detection success (100% vs 20% without)
  • Intelligent KeyPool with automatic failure detection, 429 cooldown, load balancing, and per-key RPM limits

Considerations

  • Cookies (cf_clearance) are IP-bound and may expire across environments
  • No official refresh token mechanism; keys require manual replacement
  • Claude.ai web API may change without notice, requiring code updates

README quick start

快速开始

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482