I build VT Code, a Rust coding agent, from it, you can easily switch LLM providers/models and various configs like effort and plan/build/auto mode. Fable 5 included.
Thank you! As creator of VT Code, I think it stands out with other coding harnesses; it is the vast realm of LLM providers and models that it can support. Also, I think the main reason I started VT Code in Rust is also a main `feature`, I believe. Let me know if you have any issues using it.
I have been building my own coding agent, VT Code (https://github.com/vinhnx/vtcode). I have now made it stable and mature enough, and I use it for most of my works.
I have been building coding agent: VT Code and I'm very proud of it.
https://github.com/vinhnx/VTCode > It's an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management.
Recently it just got the 500th tagged release. The project has been started since August 2025, and the coding agent VT Code itself I believe to be stable and ready to use. Thankfully, I got help from the community; recently, we pushed quite a lot of releases, enhancements, and bug fixes.
Applied in March when it first launched for VT Code, a Rust-based terminal coding agent, but haven't heard back from OpenAI. The bar seems high, which makes sense given the fund's limited scope and requirements.
I have been building tools; VT Code is my latest, and I'm very proud of it.
VT Code: https://github.com/vinhnx/VTCode > An open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. => Recently it just got the 500th tagged release. The project has been started since August 2025, and the coding agent VT Code itself I believe to be stable and ready to use. Thankfully, I got help from the community; recently, we pushed quite a lot of releases, enhancements, and bug fixes.
My coding agent VT Code has recently become a Xiaomi Orbit partner. If you want to try out Xiaomi Mimo V2.5 and V2.5 Pro in a different harness, feel free to use my VT Code. VT Code supports Mimo V2.5/Pro via official Xiaomi endpoints and via OpenRouter. Thank you!
Thank you for checking out VT Code! Yes, VT Code supports connecting to local LLMs through two main providers: LM Studio and Ollama. But local LLMs inference is experimenting, as I don't have enough hardware with large VRAM to test it, my main machine is MacBook Pro M4 with just 16 GB Ram. The community always have asked for it and I would love to have sought contributor on these regards. My initial vision is to support open weight and local inference. So LM Studio and Ollama are supported but still have bugs. https://github.com/vinhnx/VTCode/blob/a154162f/docs/provider...
Notes: VT Code also supports custom OpenAI-compatible providers through the custom providers' configuration, allowing you to connect to any local LLM server that exposes an OpenAI-compatible API: https://github.com/vinhnx/VTCode/blob/a154162f/docs/config/C...
Thank you for checking out VT Code! “LLM-native code understanding” refers to VT Code's approach of using LLM as the primary mechanism for semantic code analysis rather than relying solely on traditional static analysis tools. I have tried using ast-grep for structured code parsing understanding as a ground truth before/after the agent executes a code analysis or does a code edit/write operation and code context understanding and symbol analysis. I also tried to use tree-sitter to enhance the user's prompt parser grammar. Example: currently I use tree-sitter bash grammar to check for user input prompts for Unix commands: “run cargo fmt” -> VT Code will detect and understand right away the intent is to run a bash command -> parse and hand it to the harness -> wait for the stdout/err. Then, parse the stdio handle to the LLM as an agent loop. This is to save context and parser roundtrip.
This is just my naive implementation, so as “llm-native code understanding,” VT Code will use LLMs to perform deep code understanding across multiple programming languages as a fallback if my enhance `ast-grep` + ripgrep + tree-sitter implementation is failed, but this relies on the model's intelligent. If you follow end-of last year post-training breakthrough (GPT-5.1 and Opus 4.5 era, November 2025), I read somewhere from Anthropic and OpenAI researchers that now the models are smart enough to understanding code with more context. They even have their own internal monologue so they can reason about code grammars and code context by itself. https://github.com/vinhnx/VTCode/blob/a154162f/docs/README.m...
Note: I don't have enough understanding describing this cleanly as I learn by doing mostly. However, initially when I designed and built VT Code, I had a vision of using and for AST-enhanced grep code for replacement of std grep. I also use my grep tool, called grep. `perg`). I also wanted to parse source code into concrete syntax trees usable in compilers, interpreters, text editors, and static analyzers. Also, I thought of using LSP but still exp. All this might be overhead for a small open source coding harness, but I love to build, so I thought to myself, why not, just build and learn.
DeepSeek's KV cache is impressive and very cost-efficient for long-horizon tasks. I tested on VT Code with DeepSeek V4 Pro, and the cache-hit ratio is high. *I build a coding agent and have recently improved and hardened DeepSeek V4 integration. I registered the DeepSeek API key, topped up just 2 USD, and used just DeepSeek V4 Pro and Flash with max thinking. So far the most visible improvement in both cost and context is the cache improvement; it's quite impressive with this announcement of a permanent price drop. (https://xcancel.com/vinhnx/status/2058748305350557932). Currently, my usage is still at $1.15 after 2 full weekends.
You can use DeepSeek with my coding agent VT Code. Recently I've added DeepSeek V4 Pro and DeepSeek V4 Flash support with all providers, via: Official DeepSeek API, HuggingFace, Ollama Cloud, OpenRouter providers.
I've been building VT Code (https://github.com/vinhnx/vtcode), an open-source coding agent with code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. Written in Rust.
Hi, I’m Vinh (@vinhnx on internet). iOS & Applied AI Engineer. I love to learn, build, and share.
Twitter: https://x.com/vinhnx GitHub: https://github.com/vinhnx HuggingFace: https://huggingface.co/vinhnx90 Personal site: https://vinhnx.github.io CV: https://vinhnx.github.io/cv YouTube: https://www.youtube.com/vinhnx90 Buy me a coffee: https://buymeacoffee.com/vinhnx
Learn by doing. Learn by open source.