VTCode

I'm building a coding agent, named VT Code [0]. VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter. Supports multiple LLM providers with automatic failover and efficient context management. Support OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, OpenRouter, Z.AI, Moonshot AI, MiniMax, and Ollama (local & Cloud). Agent Client Protocol and Model Context Protocol fully support. VT Code supports a rich set of configuration options, with preferences stored in vtcode.toml. Has both Visual Studio Code and Open VSX extensions so that you can install in VS Code or Cursor, Windsurf, Eclipse. I've been building it for several months now and enjoy the learning process, I also wrote a blog post and learnt a ton about terminal, ANSI processing. The learning has been immense for me, I now have working knowledg

I’ve been experimenting with a coding agent project [0], and ratatui-rs became my framework of choice for building its first TUI. [1] The framework now ships with native list view support and improved terminal capabilities, including smoother mouse interaction and text selection. [0] https://github.com/vinhnx/vtcode [1] https://github.com/ratatui/awesome-ratatui

Hi, for me, I will try my best to answer. In my experience, it all about giving the agent the right tool for job. We give them a grep tool and search, then the accuracy and reliability rely on the capable of the running model. > I ask the agent to generate things like: > { original_sentence: xxxx, improved_sentence: yyyy } > and I use the original_sentence to locate the original content, and replace it with the improved_sentence. To mitigate this, I build the apply patch pattern. [0][1] [0] https://github.com/vinhnx/vtcode/blob/main/vtcode-core/tests... [1] https://github.com/vinhnx/vtcode/blob/main/vtcode-core/src/t...

I’ve been building VT Code, a Rust-based terminal coding agent that combines semantic code intelligence (Tree-sitter + ast-grep) with multi-provider LLMs and a defense-in-depth execution model. It runs in your terminal with a streaming TUI, and also integrates with editors via ACP and a VS Code extension. * Semantic understanding: parses your code with Tree-sitter and does structural queries with ast-grep. * Multi-LLM with failover: OpenAI, Anthropic, xAI, DeepSeek, Gemini, Z.AI, Moonshot, OpenRouter, MiniMax, and Ollama for local—swap by env var. * Security first: tool allowlist + per-arg validation, workspace isolation, optional Anthropic sandbox, HITL approvals, audit trail. * Editor bridges: Agent Conext Protocol supports (Zed); VS Code extension (also works in Open VSX-compatible editors like Cursor/Windsurf). * Configurable: vtcode.

> “You only think you understand how a bicycle works, until you learn to ride one.” This resonates deeply with me. That's why I built one myself [0], I really really love to truly understand how coding agents work. The learning has been immense for me, I now have working knowledge of ANSI escape codes, grapheme clusters, terminal emulators, Unicode normalization, VT protocols, PTY sessions, and filesystem operations - all the low-level details I would have never think about until I were implementing them. [0] https://github.com/vinhnx/vtcode

I’ve been experimenting with a coding agent project [0], and ratatui-rs became my framework of choice for building its first TUI. [1] The framework now ships with native list view support and improved terminal capabilities, including smoother mouse interaction and text selection. [0] https://github.com/vinhnx/vtcode [1] https://github.com/ratatui/awesome-ratatui