VT Code
Rust TUI coding agent with multi-provider support
Details
- External ID
- 47898308
- Source
- HN
- Company
- —
- Product
- VT Code
- Website domain
- github.com
- Launched
- April 25, 2026
- Cohort
- —
- Upvotes
- 18
- Upvotes percentile
- 0.7326478149100257
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
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). Semantic context understanding is supported by ast-grep for structured code search and ripgrep for powered grep.I built VT Code in Rust on Ratatui. Architecture and agent loop documented in the README and DeepWiki.Repo: https://github.com/vinhnx/VTCodeDeepWiki: https://deepwiki.com/vinhnx/VTCodeHappy to answer questions!I believe coding harnesses should be open, and everyone should have a choice of their preferred way to work in this agentic engineering era.
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- rust tui coding agent supporting multiple providers
- Manually corrected
- False
Could you build this?
Partial While terminal UIs and LLM API integrations are straightforward to scaffold, building a reliable semantic coding agent with full protocol support (MCP, ACP) and local inference coordination requires non-trivial systems engineering.
What it would actually take: Built in Rust using Ratatui/Crossterm for the TUI, with async runtimes (Tokio) handling streaming tool-use loops against diverse provider APIs and MCP client specifications. The hard parts are AST-based semantic code indexing, token-budget context window compaction, and safe tool-execution sandboxing across platforms. Requires expertise in systems programming, compiler toolchains (tree-sitter), and agent orchestration.
Discussion
2 comments analyzed.
Competitors mentioned: Codex (CLI tool with OpenAI API wrapper), MCP (protocol alternative to ACP), Embedding-based retrieval systems
Concerns raised: Local models below 70B struggle with multi-turn tool use, Local inference support still early/experimental, Benchmarks missing for open models on tool-calling workflows, VRAM limitations for testing local inference
Feature requests: Benchmark open models for tool-calling workflows, Community help testing local inference configurations
Competitors
Other products that read as similar to this one — 373 launches clear the similarity bar, closest 8 shown.
Attention rank: #118 of 374 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 172 days after the earliest competitor.
- VT Code · ph · 2026-09-18 · 4 upvotes · similarity 0.66
- Outline Driven Development · hn · 2025-11-19 · 11 upvotes · similarity 0.47
- Alphacode · ph · 2026-09-06 · 1 upvotes · similarity 0.47
- A Context Registry for AI coding agents · hn · 2026-09-03 · 9 upvotes · similarity 0.46
- Sandbox Agent SDK · hn · 2026-01-28 · 41 upvotes · similarity 0.45
- Agentic Copilot · hn · 2026-03-19 · 9 upvotes · similarity 0.45
- Sigil · hn · 2026-04-05 · 5 upvotes · similarity 0.44
- Keen Code · hn · 2026-08-10 · 6 upvotes · similarity 0.44
Other launches for this product
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.