MushyBook
dao-code logo

dao-code

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.

Ai AgentAI AgentsCliCoding AgentDeepseekDeveloper ToolsTerminalTypeScriptMIT 1.5k 52Health 87
node ≥20PRs welcome
Website GitHub

What is it?

What it is

Dao Code is a terminal‑native AI coding assistant that reads, writes, runs commands, and fixes bugs directly in your terminal, streaming reasoning and tool calls while staying safe behind an approval gate.

Why it exists

It was created to offer a low‑cost, highly available, and open‑source coding agent that works well in mainland China, leveraging DeepSeek V4’s cheap pricing and cache, while providing reliable memory, reflection, and long‑task robustness.

Who should use it

Developers in mainland China, cost-conscious developers, and users needing a terminal-native AI coding assistant with memory, reflection, and long-task capabilities.

Who should avoid it

Users without a DeepSeek API key, those preferring GUI tools, or non-technical audiences.

How it works

A quick walkthrough in plain English

How dao-code works

Step 1 of 3

You interact with it

Open dao-code, send a request, or connect it to your stack.

Features

Ai Agent
Cli
Coding Agent
Deepseek
Llm
Terminal

Advantages

  • Open source (MIT)
  • Active TypeScript ecosystem
  • Self-hosted deployment options

Disadvantages

  • Requires operational ownership for self-hosted setups
  • Community support varies by project maturity

Installation

native

git clone https://github.com/tigicion/dao-code.git && cd dao-code
npm install && npm run build && npm link   # then dao is global
# or run directly in dev: npm run dev

FAQ

What is dao-code?

dao-code is an open-source project licensed under MIT.

What language is dao-code built with?

Primary language: TypeScript.

Is it free to use?

Yes. Licensed under MIT. Check the license for commercial use.

Loading documentation…
View on GitHub

Featured in Videos

YouTube tutorials and walkthroughs for dao-code

sd

80,246 views

Starts at 00:00

Share

Alternatives

Similar projects ranked by category, topics, and text overlap.

Compare
gemma-chat logo

gemma-chat

TypeScript

Gemma Chat combines Electron, Vite, React, and TypeScript with an auto‑provisioned Python venv running MLX‑LM to deliver a local-first coding agent. It offers Build Mode (live‑preview multi‑file code generation), Chat Mode with tool use, model switching, voice input via in‑browser Whisper, and zero‑config setup. After a one‑time ~3 GB model download, everything works offline, producing a distributable .dmg via npm run dist.

1.4k·Health 80

Compare
lottie logo

lottie

TypeScript

The repository provides a skill that agents can invoke to generate Lottie JSON from SVG or other assets, stores each animation as a scene in a project, and serves it through a local player that live‑updates as the agent edits the file. Generated animations can be used directly on web, React Native, iOS, Android, or Flutter.

4.9k·Health 90

Compare
agent-as-a-router logo

agent-as-a-router

TypeScript

ACRouter provides a system for routing coding tasks to various backend models, balancing accuracy and cost. The repository includes the CodeRouterBench dataset, reproducible implementations for in-distribution and out-of-distribution (OOD176) testing, and runtime integrations for tools like Claude Code and Codex. It supports both offline reproduction using cached results and live inference-time integration with verifiers.

881·Health 77

Compare
tokenspeed logo

tokenspeed

Python

TokenSpeed combines a local-SPMD modeling layer with a static compiler that generates collective communication from annotations, a C++ control plane and Python execution plane scheduler modeled as a finite-state machine for safe KV cache reuse, a pluggable layered kernel system featuring one of the fastest MLA implementations on Blackwell, and an SMG-integrated AsyncLLM entrypoint for low-overhead CPU request handling. It achieves up to 580 TPS on Qwen3.5-397B-A17B for agentic workloads and offers comprehensive documentation and getting-started guides.

1.6k·Health 85

Compare
ollama logo

ollama

Go

Run open LLMs locally with one command. CLI and REST API included.

177.1k·Health 90

Compare
dao-code | MushyBook