Loading repository data…
moderato713 / repository
Production-grade terminal code agent (Python)
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
生产级终端代码 Agent(Python 实现)
⚠️ 当前状态: 规划完成,GitHub 已就绪,M0-A 待开始。详见
STATE.md。🚀 要开新对话继续工作? 直接到
docs/conversation-starters.md复制对应模板粘贴即可,永远不要自己造开场白。
| 文件 | 用途 |
|---|---|
USAGE.md | 用户使用说明(忘了怎么操作就看这个) |
docs/conversation-starters.md | 新对话开场白速查表(开新对话前先来这里) |
AGENTS.md | 项目宪法,AI 助手开新对话必读 |
STATE.md | 当前状态指针 |
PLAN.md | 总体规划(22 个里程碑) |
GITHUB_SETUP.md | GitHub 仓库初始化指南(已完成) |
docs/decisions/ | 架构决策记录(ADR,18 份) |
docs/progress/ | 里程碑详细拆分 |
docs/conversations/ | 历史对话纪要 |
docs/invariants/ | 关键不变量(主循环 12 条) |
legacy/ | 原 demo 备份(只读) |
用 Python 完整复刻一个生产级终端代码 Agent 产品,包含:
详见 PLAN.md。
# 安装
uv sync
# 启动开发服务
make dev
# 跑 CLI
python -m apps.cli chat
# Docker 一键起 stack
make docker-up
如果你是 AI(Claude / GPT / 其他模型)在 Cursor 里看到这个项目:
不要重新规划,不要换技术栈,不要简化业务能力。规划已经定好,你的任务是按计划推进。
Apache-2.0(见 ADR 0009;LICENSE 文件由 M0-D 子对话生成)
Selected from shared topics, language and repository description—not editorial ratings.
pageton /
Production-grade AI skill for designing and building polished terminal user interfaces. Works with Claude Code and OpenCode.
55/100 healthGgboykxz /
Production-grade terminal AI coding agent with 85+ models support, multi-agent system, and rich terminal UI. Built in Gabon 🇬🇦 for the world.
45/100 healthMazigaming /
A production-grade, terminal-based decompiler that converts x86-64 executables into readable pseudo-code, C, and Rust with Themes ,scripting , keybinds systems and a premade compiler/assembler for all your needs
benclawbot /
Medusa is a production-grade autonomous coding agent written in Rust. It combines an interactive terminal experience with a persistent agent runtime, repository-aware tools, durable Markdown memory, guarded execution, multi-worker coordination, browser verification, and release-grade validation.
58/100 healthliwuhou /
A collection of production-grade agent skills for Claude Code and other AI agent terminals.
69/100 healthMohammedAl-sultani /
🔓 The full source code of Anthropic's Claude Code CLI on 2026-03-31. A production-grade masterclass in AI Agent architecture, MCP protocol implementation, and terminal-native LLM orchestration.
42/100 health