Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

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.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.