Show HN: VT Code – Rust TUI coding agent with multi-provider support
Open-source coding agent. Multi-model support. Local inference ready. Rust TUI that lets devs pick their AI stack.
Why it matters
A developer-first alternative to closed coding agents (Cursor, GitHub Copilot). VT Code ships with multi-provider flexibility and local inference, positioning open models as viable for agentic coding workflows.
The key facts
14 to knowSupports Anthropic, OpenAI, Gemini, Codex, and all open-source models
Local inference via LM Studio and Ollama (experimental)
Built in Rust on Ratatui TUI framework
Model Context Protocol (MCP) and Agent Client Protocol (ACP) ready
Semantic code understanding via ast-grep and ripgrep
Published on HN with 3 points, 0 comments (low traction at time of analysis)
Open-source with documented architecture and DeepWiki docs
VT Code: Rust-based TUI coding agent
Supports: Anthropic, OpenAI, Gemini, Codex, all SOTA open-source models
Local inference: LM Studio and Ollama support
Built on Ratatui (Rust TUI framework)
Uses ast-grep for structured code search, ripgrep for semantic search
Open-source (GitHub repo public)
Posted on Hacker News (low engagement: 3 points, 0 comments as of publish)
Go to the source
Hacker Newsgithub.com
Publisher excerpt: Hi HN, I built VT Code, a semantic coding agent. Supports all SOTA and open sources model. Anthropic, OpenAI, Gemini, Codex. Agent Skills, Model Context Protocol and Agent Client Protocol (ACP) ready. All open source models are support. Local inference via LM Studio and Ollama (experiment).…