dao-code

Name: dao-code
Author: tigicion

bytigicion· 1 MCP server

Stars

1.3k

Forks

How to install dao-code?

tigicion/dao-code

$git clone https://github.com/tigicion/dao-code

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install dao-code by running `git clone https://github.com/tigicion/dao-code`, then use it for the current task and follow its documentation at https://github.com/tigicion/dao-code.

Files · 1

View on GitHub

README.md

1	# Dao Code 道
2
3	English · [中文](./README.zh-CN.md)
4
5	[![CI](https://github.com/tigicion/dao-code/actions/workflows/ci.yml/badge.svg)](https://github.com/tigicion/dao-code/actions/workflows/ci.yml)
6	[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)
7	[![Node](https://img.shields.io/badge/node-%E2%89%A520-brightgreen.svg)](./.nvmrc)
8	[![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](./CONTRIBUTING.md)
9
10	> 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.
11
12	![Dao Code demo](docs/assets/demo-en.gif)
13
14	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.
15
16	---
17
18	## Why Dao Code?
19
20	### 🌐 Availability
21
22	A coding agent is only useful if you can actually run it.
23
24	- Claude Code needs an Anthropic account and network access — a high bar to use out of the box in mainland China;
25	- GLM's Coding Plan has scarce quota that's often hard to grab;
26	- 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.
27
28	### 💰 Cost
29
30	- 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.
31	- 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.
32	- 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`.
33	- 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.
34
35	\| Task (real OSS repo) \| Input tok \| Hit % \| DeepSeek Pro \| vs Opus \| vs Sonnet \|
36	\|---\|---:\|---:\|---:\|---:\|---:\|
37	\| t7-sqlglot-sqlite-autoinc \| 1,218,385 \| 97.7% \| ¥0.213 \| 37× \| 22× \|
38	\| t6-sqlglot-comment-on \| 625,772 \| 96.3% \| ¥0.144 \| 32× \| 19× \|
39	\| t9-hono-compress \| 699,479 \| 96.0% \| ¥0.209 \| 31× \| 18× \|
40	\| t8-hono-cookie-dup \| 502,866 \| 94.9% \| ¥0.136 \| 28× \| 17× \|
41	\| t4-estoolkit-omitby \| 445,475 \| 94.4% \| ¥0.159 \| 28× \| 17× \|
42	\| L1-nodeps-toolkit \| 289,989 \| 93.2% \| ¥0.140 \| 27× \| 16× \|
43	\| t5-estoolkit-uniqwith \| 104,071 \| 85.4% \| ¥0.068 \| 21× \| 12× \|
44	\| Total \| 3,886,037 \| 95.8% \| ¥1.07 \| 30× \| 18× \|
45
46	<sub>Prices as of 2026-06 official rates: DeepSeek V4 Pro hit/miss/output = $0.003625 / $0.435 / $0.87 per 1M; Claude Opus 4.8 = $5 / $25 (hits at 0.1× cache-read), Sonnet 4.6 = $3 / $15. Multiples are USD-on-USD, exchange-rate-independent; ¥ converted at ¥7.1/$. Cross-check: re-pricing L1 at current rates gives ¥0.140 ≈ the ¥0.136 the in-log

6 picks

Type

dao-code

bytigicion· 1 MCP server

Stars

1.3k

Forks

How to install dao-code?

tigicion/dao-code

$git clone https://github.com/tigicion/dao-code

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install dao-code by running `git clone https://github.com/tigicion/dao-code`, then use it for the current task and follow its documentation at https://github.com/tigicion/dao-code.

Files · 1

View on GitHub

README.md

1	# Dao Code 道
2
3	English · [中文](./README.zh-CN.md)
4
5	[![CI](https://github.com/tigicion/dao-code/actions/workflows/ci.yml/badge.svg)](https://github.com/tigicion/dao-code/actions/workflows/ci.yml)
6	[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE)
7	[![Node](https://img.shields.io/badge/node-%E2%89%A520-brightgreen.svg)](./.nvmrc)
8	[![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](./CONTRIBUTING.md)
9
10	> 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.
11
12	![Dao Code demo](docs/assets/demo-en.gif)
13
14	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.
15
16	---
17
18	## Why Dao Code?
19
20	### 🌐 Availability
21
22	A coding agent is only useful if you can actually run it.
23
24	- Claude Code needs an Anthropic account and network access — a high bar to use out of the box in mainland China;
25	- GLM's Coding Plan has scarce quota that's often hard to grab;
26	- 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.
27
28	### 💰 Cost
29
30	- 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.
31	- 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.
32	- 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`.
33	- 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.
34
35	\| Task (real OSS repo) \| Input tok \| Hit % \| DeepSeek Pro \| vs Opus \| vs Sonnet \|
36	\|---\|---:\|---:\|---:\|---:\|---:\|
37	\| t7-sqlglot-sqlite-autoinc \| 1,218,385 \| 97.7% \| ¥0.213 \| 37× \| 22× \|
38	\| t6-sqlglot-comment-on \| 625,772 \| 96.3% \| ¥0.144 \| 32× \| 19× \|
39	\| t9-hono-compress \| 699,479 \| 96.0% \| ¥0.209 \| 31× \| 18× \|
40	\| t8-hono-cookie-dup \| 502,866 \| 94.9% \| ¥0.136 \| 28× \| 17× \|
41	\| t4-estoolkit-omitby \| 445,475 \| 94.4% \| ¥0.159 \| 28× \| 17× \|
42	\| L1-nodeps-toolkit \| 289,989 \| 93.2% \| ¥0.140 \| 27× \| 16× \|
43	\| t5-estoolkit-uniqwith \| 104,071 \| 85.4% \| ¥0.068 \| 21× \| 12× \|
44	\| Total \| 3,886,037 \| 95.8% \| ¥1.07 \| 30× \| 18× \|
45
46	<sub>Prices as of 2026-06 official rates: DeepSeek V4 Pro hit/miss/output = $0.003625 / $0.435 / $0.87 per 1M; Claude Opus 4.8 = $5 / $25 (hits at 0.1× cache-read), Sonnet 4.6 = $3 / $15. Multiples are USD-on-USD, exchange-rate-independent; ¥ converted at ¥7.1/$. Cross-check: re-pricing L1 at current rates gives ¥0.140 ≈ the ¥0.136 the in-log

6 picks

Type

dao-code

How to install dao-code?

Related

dao-code

How to install dao-code?

Related