영어 · 中文

**비용, 경험, 가용성을 중심으로 구축된 터미널 코딩 에이전트 — 고가가치 DeepSeek V4에서 가장 많은 기능과 최저 비용을 최대한 끌어내는 것.

Dao Code(명령어 dao)는 터미널 네이티브 AI 코딩 어시스턴트로, 코드를 읽고, 코드를 작성하며, 명령을 실행하고 버그를 수정하며, 승인문 뒤에서 안전하게 실행하면서 추론과 도구 호출을 스트리밍하여 작업이 완료될 때까지 지원합니다. 이 도구는 DeepSeek V4(1M 컨텍스트)를 목표로 하며, 중국 우선이고 Claude Code에서 영감을 받았지만 다른 길을 택합니다: 비싼 모델로 경험을 구매하는 대신, DeepSeek의 강력한 가격 경쟁력과 초저가 캐시 가격 책정, 바이트 안정 접두사 설계와 캐시 재사용 포크를 통해 크로스 세션 메모리와 지속적인 자기 수정 계층이 거의 토큰 비용을 부담하지 않도록 합니다.

---

왜 도암호?

🌐 이용 가능성

코딩 에이전트는 실제로 실행할 수 있을 때만 유용합니다.

• Claude Code는 Anthropic 계정과 네트워크 접근이 필요한데, 이는 중국 본토에서 기본 조건을 충족시키기 위한 높은 기준입니다;
• GLM의 코딩 계획은 할당량이 부족해 얻기 어려운 경우가 많습니다;

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//run-1/agent.log; replay any time with /cost.
• Cost vs Claude Code — pricing the same token trace of these 7 tasks under each vendor’s official rates (and crediting Dao Code’s high hit rate to Claude too, in its favor), total cost is still ~30× cheaper than Claude Opus 4.8, ~18× cheaper than Sonnet 4.6.