⌨️ local-coder

Run a local AI coding assistant
on the hardware you already have

Stop paying $20/mo for Claude or Copilot. local-coder checks what your machine can run, then generates a benchmark-backed Ollama + Continue.dev config pack — working in under an hour.

$ npx local-coder check # detects CPU / RAM / GPU VRAM, recommends your model tier $ npx local-coder init # writes Continue.dev config + pull script + prompt templates

Hardware-aware picks

Profiles your RAM and GPU VRAM and picks the model that's the sweet spot for your box — not a generic blog default that's too big or too small.

One-command setup

Generates a wired-up Continue.dev config for VS Code, Cursor, and JetBrains, plus an Ollama pull script and ready-to-use prompt templates.

RAG over your repo

Codebase-aware retrieval is configured out of the box, so the assistant answers with context from your actual project.

Curated per hardware class

Benchmark-backed model picks, not guesswork.

TierBudgetPrimary model
Tiny< 6GBqwen2.5-coder:3b
Small8–16GBqwen2.5-coder:7b
Medium16–32GB RAM / 12–16GB VRAMqwen2.5-coder:14b
Large32GB+ / 24GB+ VRAMqwen2.5-coder:32b + deepseek-coder-v2

Pricing

Free forever to try. One-time Pro — no subscription required.

Free

₹0 / $0
  • Hardware compatibility checker
  • Starter config pack
  • Continue.dev config + prompt templates
npx local-coder check

Pro

₹2499 / $29 one-time
  • Everything in Free
  • Tuned presets + alt model wiring
  • Optimized RAG-over-repo retrieval
  • Private Discord
  • Optional ₹999/mo updated model recipes
Get Pro