AI 코딩 에이전트 오픈소스 프로젝트
🚀 프로젝트 소개
Dao Code는 DeepSeek V4를 기반으로 한 오픈소스 TypeScript 터미널 코딩 에이전트입니다. 이 프로젝트는 저렴한 비용으로 높은 성능을 제공하며, 코드 작성, 실행 및 버그 수정을 지원합니다.
✨ 주요 기능
- 터미널 내에서 코드 읽기, 작성 및 실행
- 버그 수정 및 지속적인 자기 수정 기능
- 저렴한 비용으로 높은 성능 제공
🛠️ 기술 스택
TypeScript를 사용하여 개발된 이 프로젝트는 DeepSeek V4 모델을 기반으로 하며, CLI 환경에서 원활하게 작동합니다.
💡 활용 방법
개발자는 Dao Code를 통해 터미널에서 직접 코드를 작성하고 실행하며, 버그를 신속하게 수정할 수 있습니다. 또한, 저렴한 비용으로 고성능 AI 코딩 에이전트를 활용할 수 있습니다.
📄 Original (English)
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
Dao Code 道
English · 中文
A terminal coding agent built around cost, experience, and availability — squeezing the most capability and the lowest cost out of the high-value DeepSeek V4.
Dao Code (command dao) is a terminal-native AI coding assistant: it reads code, writes code, runs commands, and fixes bugs right in your terminal — streaming its reasoning and tool calls while executing safely behind an approval gate, until the task is done. It targets DeepSeek V4 (1M context), is Chinese-first, and is inspired by Claude Code — but takes a different road: rather than buying experience with an expensive model, it builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost.
Why Dao Code?
🌐 Availability
A coding agent is only useful if you can actually run it.
- Claude Code needs an Anthropic account and network access — a high bar to use out of the box in mainland China;
- GLM's Coding Plan has scarce quota that's often hard to grab;
- Dao Code is fully open source (MIT), and its base DeepSeek is register-and-go, pay-as-you-go, directly reachable in mainland China — no network gymnastics, no quota grabbing, no waitlist.
💰 Cost
- Low unit price — DeepSeek sits at the lowest price tier among mainstream capable models; both input and output prices are far below the top-tier closed models.
- Cache cuts it further — DeepSeek's prefix-cache hit price is ≈ 1/120 of a miss (~two orders of magnitude). Dao Code keeps the system prefix / tool table / memory byte-stable, and runs reflection & memory on cache-reusing forks, so the hit rate keeps climbing.
- Measured on real OSS bug-fixes (not toy demos) — 7 SWE-bench-style tasks (valibot / date-fns / es-toolkit / sqlglot / hono), 3.89M input tokens total, 95.8% aggregate cache hit (85.4%–97.7% per task). At DeepSeek V4 Pro current pricing, a full feature (read + edit + test + self-review) runs ¥0.07–0.21, avg ¥0.15; all 7 total ¥1.07. Every figure traces back to
evals/runs/<task>/run-1/agent.log; replay any time with/cost.
MIT License