DocForge – Multi-Agent RAG That Fact-Checks Its Own Answers
Multi-agent fact-checking loop, but RAG hallucination fixes are table stakes now.

Comment-section triage cuts AI fact-checking costs from $0.15 to nearly zero per post.
X/Twitter users concerned about misinformation
NewsGuard · InVID · Factmata
We waited 6 months before building this because the economics looked impossible. A decent quality AI fact-checking analysis is $0.05-0.15 per post, a typical user scrolls hundreds of posts per seconds.
The only way to make the math work was a pipeline that leverages the comment section to triage posts and analyze in depth only when it's necessary. It works more or less like this:
1. Local filter in-browser (free): short posts, already-seen content. 2. Small-model triage: does this post even make a factual worth checking? 3. Comment analysis (main path): pull the replies, analyze them alongside the post. 4. Full web-search analysis: only when steps 1-3 can't decide.
Average cost landed at ~$0.0015 per post, which looks sustainable with a subscription model, and can definitely be optimized.Multi-agent fact-checking loop, but RAG hallucination fixes are table stakes now.
Local 0.8B model with fact-checking citations — no GPU, no cloud, no API key.
Forces LLMs to debug with AST evidence instead of pattern-matching symptoms.
Fact-checking with web citations is clever, but ollama already does local LLM CLI.
Fact-checking with citations and web search runs entirely on your CPU.
Fact-checks text claims against live web search without sending data to the cloud.