Chaty
Active·★ 54·MIT·Updated 2026-10-20
Chaty is a private, 100% offline desktop application that runs open LLMs directly on your machine. It integrates various AI functionalities including a local coding agent, document knowledge base (RAG), deep research capabilities, and hands-free voice interaction, all with GPU acceleration.
#Offline LLM#Desktop App#AI Agent#RAG#Code Assistant#Multimodal AI#Local Inference#GPU Acceleration
01
Features
01Truly private, 100% offline LLM inference with no account, cloud, or telemetry.
02A local coding agent that explores, edits, and verifies codebases on your machine with browser automation and precise edits.
03Integrated knowledge base (RAG) for indexing diverse document types and images, providing strictly grounded answers with citations.
04Deep Research capabilities for multi-round web search and structured, cited report generation.
05Native desktop application with GPU offload (Vulkan/Metal) and support for various GGUF and MLX models, including vision models.
02
Compatibility
Windows
Desktop OS
Verified via docs
macOS
Desktop OS
Verified via docs
Rust
Core Language
Verified via docs
Vulkan
GPU Acceleration
Verified via docs
Metal
GPU Acceleration
Verified via docs
MLX
AI Acceleration
Verified via docs
03
Quick start
1
$ npm install
2
$ npm run tauri build
04
Use cases
↳Secure and private software development and debugging using an AI coding agent that interacts with your local codebase.
↳Personal knowledge management and efficient document Q&A by indexing local files and images into a private knowledge base.
↳Conducting thorough web research and generating cited reports on various topics without cloud dependency.
↳Rapid prototyping and iterative design of web interfaces using the Design Canvas feature with live preview and self-healing.
↳Hands-free interaction with an AI assistant for tasks, discussions, or converting knowledge bases into podcasts.
05
Alternatives
claude_code_vs★ 102
Bring Claude Code to Visual Studio 2026: a native diff with accept/reject, a live debugger Claude can drive, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.
ruvnet-brain★ 76
RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.
code-buddy★ 48
Open-source AI coding agent that runs free on your own machine (local Ollama, $0) — or bring any of 15 providers (Claude, GPT, Gemini, Grok) with automatic failover. Terminal, desktop & 24/7 server.
mermaid-code★ 16
A local-first Mermaid diagram editor built on Mermaid Live Editor, enhanced with AI agent integration and desktop-native features via Tauri.
ref-tools-mcp★ 1.2k
Helping coding agents never make mistakes working with public or private libraries without wasting the context window.
mini-swe-agent★ 8.7k
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Comments
Log in to leave a comment
No comments yet. Be the first!