llm-hallucination-detector
Color-codes an AI chat answer token by token based on model confidence, and separately checks each factual claim against your own source documents, flagging guesses vs. supported claims.
View syasj/llm-hallucination-detector on GitHub- GitHub stars
- 2
- Forks
- —
- Language
- JavaScript
Project details
- Repository
- syasj/llm-hallucination-detector
- Licence
- MIT
- Primary language
- JavaScript
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
Free, open-source LLM hallucination detector. See token-level confidence as a heatmap and check every claim against your own sources (RAG). Works with any OpenAI-compatible API, ChatGPT & Claude. Zero dependencies, runs locally.
Explore by topic
More tools in Knowledge & documents
- headroom
headroomlabs-ai · Apache-2.0
Headroom shrinks everything an AI agent reads (logs, files, RAG chunks, tool output) before sending it to the LLM, cutting token costs without changing the answers.
- ai-engineering-from-scratch
rohitg00 · MIT
A free, open-source course that walks you through building modern AI systems from scratch, 511 lessons spanning LLMs, RAG, agents and transformers.
- semantica
semantica-agi · MIT
A graph-based infrastructure layer that gives AI systems structured context and an audit trail for their reasoning.
- code-graph-rag
vitali87 · MIT
code-graph-rag builds a knowledge graph of a codebase so an AI assistant can query, understand, and edit it more accurately.