Cognition Claude Proxy — AI skill for Claude Code
Use Devin CLI's model catalog (SWE-2, GLM-5.2, DeepSeek, 200+) with Claude Code as the backend.
How to install Cognition Claude Proxy
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open coderexpert123/cognition-claude-proxy and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cognition Claude Proxy does
Use Devin CLI's model catalog (SWE-2, GLM-5.2, DeepSeek, 200+) with Claude Code as the backend.
Alternatives in AI
- Opencodex — Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama… 12.3k ★
- EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
- J Space Cognition Suite V3.7 — J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r 3k ★
README
cognition-claude-proxy
A local proxy that lets **Claude Code** (or any Anthropic-API client) use **Devin's model catalog** — SWE-2, GLM-5.2, DeepSeek V4.1 Flash, and 200+ others — as its backend. It translates the Anthropic Messages API to the Connect-RPC format that the Devin CLI uses, and translates the streaming responses back to Anthropic SSE.
How it works
graph LR
CC[Claude Code] -->|POST /v1/messages\nAnthropic JSON| PX[Proxy :8765]
PX -->|Connect-RPC protobuf\nauthenticated| UP[Devin CLI backend\nserver.codeium.com]
UP -->|streaming events| PX
PX -->|Anthropic SSE| CC
PX -->|GET /v1/models| UP
style PX fill:#4d94ff,stroke:#333,stroke-width:2px
style CC fill:#e066ff,stroke:#333
style UP fill:#2eb82e,stroke:#333
Plain-text flow
claude (ANTHROPIC_BASE_URL=http://localhost:8765)
-> POST /v1/messages (Anthropic Messages API, JSON)
-> proxy: translate to Connect-RPC protobuf
-> POST https://server.codeium.com (authenticated via local Devin CLI credentials)
<- Connect server-stream of events (text/thinking/tool-call/usage)
<- Anthropic SSE events (message_start/content_block_*/message_delta)
The proxy authenticates using your local Devin CLI credentials (`%APPDATA%\devin\credentials.toml` on Windows, `~/.config/devin/credentials.toml` on Linux/macOS). No API keys to manage — if `devin` works, `dclaude` works.
Prerequisites
- Node.js 18+
- Devin CLI installed and authenticated (
devincommand works) - Claude Code installed (
claudecommand works)
Quick start
git clone https://github.com/coderexpert123/cognition-claude-proxy.git
cd cognition-claude-proxy
# Option A: use the wrapper (auto-starts the proxy)
bin\dclaude.bat -p "hello"
# Option B: start the proxy manually
node src/server.js # starts on 127
Related Skills
WindsurfAPI
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A
Cc Portkey
A CLI tool for quickly switching Claude Code between different model providers (Claude, DeepSeek, GLM, MiniMax
V Models
Refresh the Compound V tier→model map — discover the concrete models each backend (claude, codex, antigravity,
Claude Model Sync
Portable Claude-compatible model catalog synchronization and strict alias proxy for Agent Skills
Free Claude Code Nix
Free Claude Code packaged for NixOS - Anthropic-compatible local proxy fronting Claude Code with any model bac
Devo
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible mode
Related Agents
ChatGPT On Wechat
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
Swe Dev Conceptual Intelligence Architect
Deep concept creation, cross-domain analogy, creative cognition, scientific discovery, design intelligence, ex
External LLM
When a request mentions external LLM model names (Kimi, K2, Grok, GLM, Gemini, GPT-5)