Overview
Crowdsourced, inline LLM investigations of the things you're reading.
OpenErrata fact-checks posts on Wikipedia, X, LessWrong, and Substack using frontier AI models with web search. When you visit a post that's been investigated, incorrect claims get a red underline. Hover for a summary of what's wrong. Click for full reasoning and source links. Posts with no issues show nothing — the extension stays out of your way. How it works: - The AI reads the full post, searches the web, and identifies claims that are demonstrably incorrect - Only flags things with concrete evidence against them — disputed claims, jokes, and ambiguity are left alone - Every investigation is public and auditable: the prompt, reasoning, and sources are all inspectable You can trigger investigations yourself with your own OpenAI API key, or wait for the community-driven queue to pick up popular posts. Once an investigation is completed Supported platforms: LessWrong, Substack (including custom domains), X/Twitter (Sort of), OpenErrata is fully open source. Code, spec, and design goals are public at https://github.com/ZeroPathAI/OpenErrata.
Details
- Version0.3.2
- UpdatedMarch 5, 2026
- Size217KiB
- LanguagesEnglish (United States)
- DeveloperZeroPath
2261 Market Street San Francisco, CA 94114 USEmail
dean@zeropath.comPhone
+1 424-459-4845 - TraderThis developer has identified itself as a trader per the definition from the European Union and committed to only offer products or services that comply with EU laws.
- D-U-N-S138386129
Privacy
OpenErrata has disclosed the following information regarding the collection and usage of your data. More detailed information can be found in the developer's privacy policy.
OpenErrata handles the following:
This developer declares that your data is
- Not being sold to third parties, outside of the approved use cases
- Not being used or transferred for purposes that are unrelated to the item's core functionality
- Not being used or transferred to determine creditworthiness or for lending purposes
