base on Local CLI Copilot, powered by Ollama. 💻🦙 # tlm - Local CLI Copilot, powered by Ollama. 💻🦙
[](https://sonarcloud.io/project/overview?id=yusufcanb_tlm)
[](https://github.com/yusufcanb/tlm/releases)
tlm is your CLI companion which requires nothing except your workstation. It uses most efficient and powerful open-source models like [Llama 3.3](https://ollama.com/library/llama3.3), [Phi4](https://ollama.com/library/phi4), [DeepSeek-R1](https://ollama.com/library/deepseek-r1), [Qwen](https://ollama.com/library/qwen2.5-coder) of your choice in your local environment to provide you the best possible command line assistance.
| Get a suggestion | Explain a command |
| -------------------------------- | -------------------------------- |
|  |  |
| Ask with context (One-liner RAG) | Configure your favorite model |
| -------------------------------- | ------------------------------ |
|  |  |
## Features
- 💸 No API Key (Subscription) is required. (ChatGPT, Claude, Github Copilot, Azure OpenAI, etc.)
- 📡 No internet connection is required.
- 💻 Works on macOS, Linux and Windows.
- 👩🏻💻 Automatic shell detection. (Powershell, Bash, Zsh)
- 🚀 One liner generation and command explanation.
- 🖺 No-brainer RAG (Retrieval Augmented Generation)
- 🧠 Experiment any model. ([Llama3](https://ollama.com/library/llama3.3), [Phi4](https://ollama.com/library/phi4), [DeepSeek-R1](https://ollama.com/library/deepseek-r1), [Qwen](https://ollama.com/library/qwen2.5-coder)) with parameters of your choice.
## Installation
Installation can be done in two ways;
- [Installation script](#installation-script) (recommended)
- [Go Install](#go-install)
### Installation Script
Installation script is the recommended way to install tlm.
It will recognize the which platform and architecture to download and will execute install command for you.
#### Linux and macOS;
Download and execute the installation script by using the following command;
```bash
curl -fsSL https://raw.githubusercontent.com/yusufcanb/tlm/1.2/install.sh | sudo -E bash
```
#### Windows (Powershell 5.5 or higher)
Download and execute the installation script by using the following command;
```powershell
Invoke-RestMethod -Uri https://raw.githubusercontent.com/yusufcanb/tlm/1.2/install.ps1 | Invoke-Expression
```
### Go Install
If you have Go 1.22 or higher installed on your system, you can easily use the following command to install tlm;
```bash
go install github.com/yusufcanb/
[email protected]
```
You're ready! Check installation by using the following command;
```bash
tlm
```
## Usage
```
$ tlm
NAME:
tlm - terminal copilot, powered by open-source models.
USAGE:
tlm suggest "<prompt>"
tlm s --model=qwen2.5-coder:1.5b --style=stable "<prompt>"
tlm explain "<command>" # explain a command
tlm e --model=llama3.2:1b --style=balanced "<command>" # explain a command with a overrided model
tlm ask "<prompt>" # ask a question
tlm ask --context . --include *.md "<prompt>" # ask a question with a context
VERSION:
1.2
COMMANDS:
ask, a Asks a question (beta)
suggest, s Suggests a command.
explain, e Explains a command.
config, c Configures language model, style and shell
version, v Prints tlm version.
help, h Shows a list of commands or help for one command
GLOBAL OPTIONS:
--help, -h show help
--version, -v print the version
```
### Ask - Ask something with or without context
Ask a question with context. Here is an example question with a context of this repositories Go files under ask package.
```
$ tlm ask --help
NAME:
tlm ask - Asks a question (beta)
USAGE:
tlm ask "<prompt>" # ask a question
tlm ask --context . --include *.md "<prompt>" # ask a question with a context
OPTIONS:
--context value, -c value context directory path
--include value, -i value [ --include value, -i value ] include patterns. e.g. --include=*.txt or --include=*.txt,*.md
--exclude value, -e value [ --exclude value, -e value ] exclude patterns. e.g. --exclude=**/*_test.go or --exclude=*.pyc,*.pyd
--interactive, --it enable interactive chat mode (default: false)
--model value, -m value override the model for command suggestion. (default: qwen2 5-coder:3b)
--help, -h show help
```
### Suggest - Get Command by Prompt
```
$ tlm suggest --help
NAME:
tlm suggest - Suggests a command.
USAGE:
tlm suggest <prompt>
tlm suggest --model=llama3.2:1b <prompt>
tlm suggest --model=llama3.2:1b --style=<stable|balanced|creative> <prompt>
DESCRIPTION:
suggests a command for given prompt.
COMMANDS:
help, h Shows a list of commands or help for one command
OPTIONS:
--model value, -m value override the model for command suggestion. (default: qwen2.5-coder:3b)
--style value, -s value override the style for command suggestion. (default: balanced)
--help, -h show help
```
### Explain - Explain a Command
```
$ tlm explain --help
NAME:
tlm explain - Explains a command.
USAGE:
tlm explain <command>
tlm explain --model=llama3.2:1b <command>
tlm explain --model=llama3.2:1b --style=<stable|balanced|creative> <command>
DESCRIPTION:
explains given shell command.
COMMANDS:
help, h Shows a list of commands or help for one command
OPTIONS:
--model value, -m value override the model for command suggestion. (default: qwen2.5-coder:3b)
--style value, -s value override the style for command suggestion. (default: balanced)
--help, -h show help
```
## Uninstall
On Linux and macOS;
```bash
rm /usr/local/bin/tlm
rm ~/.tlm.yml
```
On Windows;
```powershell
Remove-Item -Recurse -Force "C:\Users\$env:USERNAME\AppData\Local\Programs\tlm"
Remove-Item -Force "$HOME\.tlm.yml"
```
", Assign "at most 3 tags" to the expected json: {"id":"8588","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"