Lynecode
██╗ ██╗ ██╗███╗ ██╗███████╗ ██████╗ ██████╗ ██████╗ ███████╗
██║ ╚██╗ ██╔╝████╗ ██║██╔════╝ ██╔════╝██╔═══██╗██╔══██╗██╔════╝
██║ ╚████╔╝ ██╔██╗ ██║█████╗ ██║ ██║ ██║██║ ██║█████╗
██║ ╚██╔╝ ██║╚██╗██║██╔══╝ ██║ ██║ ██║██║ ██║██╔══╝
███████╗██║ ██║ ╚████║███████╗ ╚██████╗╚██████╔╝██████╔╝███████╗
╚══════╝╚═╝ ╚═╝ ╚═══╝╚══════╝ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝
Lynecode is an AI coding assistant from LyneLabs. It brings a fast terminal UI, built-in project indexing, an opinionated toolset, and optional AI models (OpenAI, Gemini, Azure OpenAI) with your keys. Run it on any folder and work from a powerful chat workflow.
Why Lynecode is different
- Integrated version control safety net: Lyne maintains its own backup snapshots (
time_machinein your target path). You can explore diffs and restore changes without relying solely on git. - Built-in analyzers and guards: Bug and code quality analyzers help spot issues quickly (without exposing internal implementation). Optional static checks are available via extras.
- Context-rich workflow: Attach files/folders inline, fuzzy-find by name, and navigate conversations with a clear menu.
- Model agnostic: Bring your own keys for OpenAI, Google Gemini, or Azure OpenAI and switch models on the fly.
Installation
pip install lynecode
Python 3.9+ is recommended.
Quick start
- Run on a specific path:
lynecode "D:/projects/myrepo"
- Or from your current working directory (Lynecode resolves to an absolute path):
lynecode
Basic usage
Once launched, you’ll see a banner and a prompt. Type your request or use the in-app menus:
- Show navigation menu:
/menu - Help:
/help - Switch conversations:
/chats - Model settings:
/modelor/switch <model> - Quit:
quit
Attach files/folders inline
- Attach a file: add
/file:<name_or_term>inside your message - Attach a folder: add
/folder:<name_or_term>inside your message Lynecode will fuzzy-match and help you pick the right target, then keep attachments visible after responses.
Choosing and switching models
- Open the model menu from navigation (
/menu→ “Model Settings”) or run/model. - Switch directly with
/switch <model_name>. - The default model is used if configured.
Supported providers (bring your own keys):
- OpenAI (e.g.,
gpt-4.1,gpt-5) - Google Gemini (e.g.,
gemini-2.5-flash,gemini-2.5-pro, with optional “-thinking” variants) - Azure OpenAI (your deployment name)
- OpenRouter (e.g.,
x-ai/grok-4-fast:free,openai/gpt-4ovia OpenRouter)
Configure API keys (secure, menu-driven)
Launch the API Configuration from the navigation menu:
/menu→ “API Configuration”
Follow prompts to set keys:
- OpenAI: API key (
sk-...) - Gemini: API key
- Azure OpenAI: API key, endpoint, API version (optional), and deployment name
Keys are stored securely via Lynecode’s config manager and masked in the UI.
Note: After updating any API key or provider configuration, restart Lynecode to apply changes.
Built-in version control workflow
Lynecode automatically creates a hidden time_machine folder inside the target directory. It’s your safety-net:
- Auto snapshots around operations
- View diffs and restore via the Version Control menu
- Works even if the target folder is not a git repo
Open from navigation:
/menu→ “Version Control”
Feature highlights
- Intelligent file edits (create/replace/delete blocks)
- Project-wide searching (grep/AST-backed and fuzzy indexing)
- Web reading and search helpers
- Conversation history with attachments
- Rich terminal output where supported; plain fallback otherwise
Compare: Lynecode vs Cline/Gemini CLI
- Safety first: Lynecode’s built-in snapshotting means quick rollback without external VCS.
- Deep project tooling: File block edits, AST/grep, and fuzzy search integrated in one place.
- Menu-driven UX: Rich menus for models, API setup, attachments, version control.
- Provider-agnostic: Switch between OpenAI, Gemini, or Azure OpenAI at runtime.
Troubleshooting
- If terminal colors aren’t showing, Lynecode falls back to plain text automatically.
- Ensure your API keys are valid (placeholders are detected and blocked with helpful messages).
Uninstall
pip uninstall lynecode
Metadata
Release files for lynecode 0.3.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| lynecode-0.3.1.tar.gz | 150.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| lynecode-0.3.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 319.5 kB
Release files / lynecode-0.3.1.tar.gz
| Download URL | lynecode-0.3.1.tar.gz |
|---|---|
| Size | 150.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
104d9fd61135279608275167f987c3ad5253d5266582e6b607e1d532e9e568a7
|
|
BLAKE2b-256 checksum How to use checksums |
f4fbd7050cde12b21e0d9880079e4272353dd4f10ec73a517e2e3818707a6941
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.4
|
Release files / lynecode-0.3.1-py3-none-any.whl
| Download URL | lynecode-0.3.1-py3-none-any.whl |
|---|---|
| Size | 169.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f3a7a69256925c7c4805352667f6e4172d9321ed509f75b16778ba43978b4d43
|
|
BLAKE2b-256 checksum How to use checksums |
c042a0cdf8e36d236d5ded28814e168635bd3febf1b6ea09fd7c65575b84a34f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.4
|