Back to browse
GitHub Repository

Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command

17 starsPython

A CLI that fact-checks text using a 500MB local model and web search

by mrkn1·Jun 10, 2026·1 point·0 comments

AI Analysis

●●SolidSolve My ProblemShip It

Fact-checks claims with web search citations using a 500MB local model — no GPU needed.

Strengths
  • 0.8B Qwen3.5 quantized model runs on CPU via llama.cpp — no CUDA required.
  • Fact-check mode extracts claims, searches web, labels SUPPORTED/REFUTED with sources.
  • Lean dependencies — no PyTorch, LangChain, or cloud SDKs in the stack.
Weaknesses
  • 0.8B model limits reasoning depth compared to larger alternatives.
  • Local LLM CLI space getting crowded with Ollama and similar tools.
Category
Target Audience

Developers who want local AI without API keys or cloud dependencies

Similar To

Ollama · llama.cpp · GPT4All

Similar Projects

AI/ML●●●Banger

fftext - quick summary, fact check, ELI5 on CPU

Fact-check command extracts claims and cites sources—rare for local AI.

Dark HorseBig Brain
mrkn1
101d ago