deepclaude: Open-source tool runs Claude Code's agent loop with cheaper AI backends like DeepSeek
By
alattaran
Front-window bakery material. Catches the eye, delivers the goods.
Summary
deepclaude is an open-source tool that replaces the Claude Code autonomous coding agent's underlying AI model (Anthropic's Claude) with cheaper alternatives like DeepSeek V4 Pro or OpenRouter-compatible backends. It maintains the same user experience and autonomous agent capabilities (file editing, bash execution, subagent spawning) while reducing costs by approximately 17x — from $200/month to roughly $0.87/M output tokens. The project provides a quick 2-minute setup guide and aims to make advanced autonomous coding agents more accessible.
Key quotes
· 4 pulledClaude Code is the best autonomous coding agent — but it costs $200/month with usage caps.
DeepSeek V4 Pro scores 96.4% on LiveCodeBench and costs $0.87/M output tokens.
deepclaude swaps the brain while keeping the body
Everything works: file reading, editing, bash execution, subagent spawning, autonomous multi-step coding loops. The only difference is which model thinks.
You might also wanna read
Anthropic Launches Claude Haiku 4.5: Faster, Cheaper AI Model Matching Sonnet 4 Performance
Anthropic launched Claude Haiku 4.5, a small AI model that delivers frontier-level coding performance matching Claude Sonnet 4, but at 2x fa
/dev: Open-Source AI Coding Tool That Turns Claude Code into a Tech Lead with Structured Engineering Process
/dev is an open-source AI coding tool that transforms Claude Code into a Tech Lead with a structured 6-phase engineering process using paral
Claude Code Launches Multi-Agent AI Code Review System for Bug Detection
Anthropic's Claude Code now offers a multi-agent AI code review system that analyzes pull requests to catch bugs, security issues, and logic
Navox Agents: AI Engineering Team Tool for Claude Code with 8 Collaborative Agents
Navox Agents is a specialized AI engineering team tool that integrates with Claude Code, featuring 8 collaborative agents that work sequenti
Anthropic Releases Claude Opus 4.7 AI Model for Complex Reasoning and Agentic Coding
Claude Opus 4.7 is Anthropic's most advanced generally available AI model, designed specifically for complex reasoning and agentic coding ta

Anthropic Releases Claude Opus 4.6 AI Model with Enhanced Multi-Step Task Capabilities
Anthropic has released Claude Opus 4.6, described as a 'direct upgrade' from its predecessor with improved capabilities for handling complex
