Ross ROSS = Recommend OSS · open-source software intelligence for agents

ErlichLiu/DeepClaude

Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨ observed · 2026-08-28

github.com/ErlichLiu/DeepClaude · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

52/100

  • Activity 69
  • Release rhythm 35
  • Longevity 41

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 578
  • days_rel: n/a
  • days_push: 191
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2936 stars · 494 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

DeepClaude is a self-hostable service that chains DeepSeek R1's reasoning output with Claude Sonnet or Gemini models to produce a combined response, exposed through an OpenAI-compatible API. It supports streaming and non-streaming responses, a graphical configuration UI, Docker deployment, and providers like OpenRouter and OneAPI.

Use cases

  • combine deepseek r1 reasoning with claude sonnet for code generation
  • use deepseek r1 with gemini for content creation
  • expose an openai-compatible endpoint backed by multiple model providers
  • self-host a hybrid reasoning model api with docker
  • use deepclaude models in cherry studio or dify
  • route claude requests through openrouter or oneapi

When to choose

  • you want the deepseek r1 + claude or gemini hybrid pipeline behind a single OpenAI-compatible API
  • you need a self-hosted proxy with a web config UI and Docker deployment
  • your client tools only speak the OpenAI API format but you want multi-model chaining

When to avoid

  • you need a single-model API gateway or full multi-model router rather than a fixed reasoning-plus-output chain
  • you require accurate token usage accounting, which is not yet implemented
  • you want a managed hosted service without self-hosting

Facets

service · maturity active

llm-inference api-framework http-server chatbot rag large-language-models artificial-intelligence apis self-hosted python self-hosted cross-platform openai-compatible-api model-chaining deepseek-r1 claude-sonnet gemini reasoning-models streaming api-proxy docker web-server

2 sources

Member repositories

RepositoryRoleHealth v2
ErlichLiu/DeepClaudemain52

For agents

markdown · JSON · MCP: product_card(name="ErlichLiu/DeepClaude")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem