Hostile-text normalization, inspection, and cleaning for LLM-adjacent systems.
textguard is a CLI tools & terminal product. It focuses on ensuring text inputs for LLMs are clean, normalized, and free from hostile content. It is built as an open-source project for developers working with LLM and AI systems. textguard is open source under the Apache-2.0 license. textguard is available on the web and the command line.
shisa-ai builds and maintains textguard, and the product first shipped in 2026. Development happens publicly on GitHub with 40 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — textguard occupies a relatively distinct niche. Key capabilities include text normalization, hostile-text cleaning, and unicode inspection.
Latest indexed changes and source events
Other apps tracked under the same category.
