No vendor lock-in. Any model. Any editor.

Don't leave your IDE.
Just make it smarter.

Pyckle plugs deep codebase context into the editor you already use — via MCP. Keep your tools. Keep your model. Pay half what walled-garden platforms charge.

Why developers make the switch

The tools you already use are great. The context layer underneath them shouldn't cost twice as much or lock you into one AI provider.

Model freedom

Pyckle is a context layer, not a walled garden. Switch between Claude, GPT, Gemini, or a local model without re-indexing or reconfiguring anything.

Your code stays yours

Embeddings are generated locally using PyckLM — your source code never leaves your machine. No compliance risk. No proprietary training on your codebase.

Half the price

Pyckle Pro is $10/month. Transparent pricing, no "Contact Sales" wall, no per-seat enterprise contracts. Start free. Upgrade when you need to.

The old way vs the Pyckle way

AI-assisted coding tools shouldn't require you to abandon your workflow to use them.

The Old Way Pyckle
Monthly price $20+/mo $10/mo
Model lock-in One provider only Any model
Editor support Proprietary IDE required Any MCP-compatible editor
Code privacy Cloud upload required Local-first, code stays on-device
Personalized embeddings Generic model PyckLM — trained on your patterns
Cross-project context Single repo only Unified workspace index
Setup time Platform migration required 2 minutes, no migration

Up and running in 2 minutes

No platform migration. No dependency nightmare. Your editor just gets smarter.

1

Install Pyckle MCP

One command. No Homebrew chains, no manual config files.

# Install the MCP server
pip install pyckle-mcp
2

Index your codebase

PyckLM runs locally and builds a semantic index of your project. One repo or ten — it handles both.

# Index from your project root
pyckle index .
3

Connect your editor

Add Pyckle as an MCP server in your editor's config. Works with Claude Code, Windsurf, Continue, VS Code, Zed, JetBrains, and more.

# Generate editor config automatically
pyckle config --editor cursor
PyckLM — Pyckle's proprietary embedding model

A model that knows your codebase

Generic embedding models retrieve code. They find the file that contains a keyword. That's search.

PyckLM retrieves your code — trained on your naming conventions, your architectural patterns, your team's implicit relationships between modules. The longer you use it, the better it knows your codebase.

That specificity compounds. A context layer that improves with your codebase is a moat against any tool that resets when you switch providers.

Runs entirely on your machine

ONNX runtime, no GPU required. Inference happens locally before any query leaves your device.

Cross-project context

Index multiple repos into a unified workspace. Your AI sees the full picture — not just the file you have open.

Session memory across editors

Switch from Claude Code to Windsurf mid-session without losing context. The index follows you, not the tool.

Improves over time

PyckLM is continuously fine-tuned. Updates deploy automatically — your context gets better without any action on your part.

Transparent pricing. No surprises.

Start free. Upgrade when your codebase scales.

Free

$0

No account required to start.

  • 500 queries / month
  • 1 project index
  • All MCP-compatible editors
  • Local PyckLM inference
  • stdio + SSE transport
Install Free

Runs entirely on your machine