# yusufcanb/tlm

Local CLI Copilot, powered by Ollama. 💻🦙

Repository: https://github.com/yusufcanb/tlm
Canonical: https://ross.abutalabs.com/products/tlm
Language: Go
License: Apache-2.0
License Family: permissive
Topics: llm, bash, powershell, llama3, zsh, deepseek-r1, qwen2-5, phi4
Last push: 2026-02-22T20:05:44+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 68, release rhythm 40, longevity 66
- inputs: {"age_days": 931, "days_push": 192, "days_rel": 568, "gap_med": 11, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1489, forks 53 (observed 2026-08-28T04:04:52.297714+00:00)

## What it is
tlm is a local CLI copilot powered by Ollama that suggests shell commands, explains them, and answers questions with context using open-source LLMs like Llama 3, Phi4, DeepSeek-R1, and Qwen. It runs entirely offline with no API keys, auto-detects the user's shell (Bash, Zsh, PowerShell), and works on macOS, Linux, and Windows.

## Use cases
- generate shell commands from natural language
- explain what a terminal command does
- get CLI assistance offline without an API key
- ask questions about local files with RAG
- try different local LLMs in the terminal

## When to choose
- you want a GitHub Copilot-style CLI helper that runs fully locally
- you cannot send code or commands to cloud APIs for privacy reasons
- you use Bash, Zsh, or PowerShell and want automatic shell-aware suggestions

## When to avoid
- you need top-tier code generation quality from frontier cloud models
- your machine lacks the resources to run local LLMs via Ollama
- you want a GUI assistant rather than a terminal tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, llm-inference, rag, chatbot, developer-tools
- domain: developer-tools, large-language-models, artificial-intelligence
- platform: cli, windows, go
- tags: ollama, shell-assistant, local-llm, copilot, command-suggestion, offline, command-line, macos, linux

## Member repositories
- yusufcanb/tlm (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:52.297714+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:33:43.078433+00:00, confidence not recorded.
  - readme: https://github.com/yusufcanb/tlm (fetched 2026-08-28T04:04:52.297714+00:00, sha 258670cb59f5)
- Data as of 2026-08-30T08:39:29.467469+00:00.