CodingBuddy is a terminal-native coding agent written in Rust. It combines chat, planning, tool execution, patch workflows, indexing, and long-running autopilot loops in one cross-platform CLI.
# CodingBuddy An open-source, multi-model AI coding agent for the terminal. Written in Rust. Connect any LLM — DeepSeek, OpenAI, Anthropic, Google, Groq, Ollama, OpenRouter — and get a production-grade coding assistant with tool execution, planning, code search, and safety guardrails. ## Why CodingBuddy? - **Any model, any provider.** 7 providers preconfigured. Any OpenAI-compatible endpoint works. - **Fast.** Rust binary, no runtime dependencies. Sub-100ms startup with profiling. - **Safe.** 0 production unwraps. Tree-sitter bash AST analysis, 4-stage permission system, default deny rules. - **Smart.** 7-strategy fuzzy editing, coordinator mode for parallel agents, per-turn RAG, doom loop detection. - **Extensible.** MCP servers, 12 lifecycle hooks, custom skills with model/effort metadata, SendMessage for inter-agent communication. ## Installation ### One-liner (recommended) **macOS / Linux:** ```bash curl -fsSL https://raw.githubusercontent.com/aloundoye/codingbuddy/main/scripts/install.sh | bash ``` **Windows (PowerShell):** ```powershell irm https://raw.githubusercontent.com/aloundoye/codingbuddy/main/scripts/install.ps1 | iex ``` The installer downloads the correct binary for your platform, verifies the SHA-256 checksum, and adds it to your PATH. ### Other methods **npm** (any platform with Node.js): ```bash npm install -g codingbuddy ``` **Homebrew** (macOS / Linux): ```bash brew install aloundoye/tap/codingbuddy ``` **From source** (requires Rust 1.94.1+): ```bash cargo build --release --bin codingbuddy # Binary at target/release/codingbuddy — move it to a directory in your PATH ``` ### Installer options The install scripts accept flags to customize behavior: ```bash # Install a specific version curl -fsSL .../install.sh | bash -s -- --version v0.3.0 # Install to a custom directory curl -fsSL .../install.sh | bash -s -- --install-dir ~/.local/bin # Dry run (show what would happen) curl -fsSL .../install.sh | bash -s -- --dry-run ``` On Win
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型