Berry: A Workflow Verification System for Detecting AI Hallucinations in Code Generation
By
jadelcastillo
Warm and crisp on the edges. A bagel with a bit of bite.
Summary
Berry is a workflow verification system that helps detect hallucinations in AI-generated code and content. It provides playbooks with before/after examples (uncited vs evidence-backed outputs), runs a local MCP server with repo-scoped tools, and includes verification tools like detect_hallucination and audit_trace_budget. The project is hosted on GitHub under leochlon/hallbayes and focuses on improving AI output reliability through structured verification workflows.
Key quotes
· 3 pulledEach playbook includes a before/after worked example (uncited output vs evidence-backed + verifier).
Berry runs a local MCP server with a safe, repo-scoped toolpack plus verification tools (detect_hallucination, audit_trace_budget).
Berry ships a single MCP surface: classic.
You might also wanna read
Sup AI: Ensemble System Using 339 LLMs to Reduce Hallucinations Scores 52.15% on Humanity's Last Exam
Sup AI is an AI ensemble system that runs 339 different large language models in parallel to reduce hallucinations. It measures confidence o
Product Hunt·2mo ago
MakeHub.ai: OpenAI-Compatible API for LLM Provider Arbitrage and Optimization
MakeHub.ai offers an OpenAI-compatible API endpoint that automatically routes requests to the cheapest and fastest LLM provider for each mod
Product Hunt·11mo ago