Venastine Research

Working on open-source and open-weight AI and AI-adjacent research to contribute to the advancement of AI for general use, and more specifically math, CS, and domain science research to help benefit humanity.

Creators of the Venastine Research Harness 🤖: https://github.com/YahyaHammad/Venastine-Research-Harness

Venastine Research Harness is an agentic harness built from scratch — no LangChain, no agent framework — with two modes that share the same machinery:

Chat — a normal tool-using assistant loop.
Research — a ten-pass pipeline that writes an answer, then independently fact-checks and critiques its own claims, audits the assumptions hiding underneath them, scores every claim by a fixed formula rather than by asking the model how sure it is, and revises only what came back flagged.

Works with Anthropic, any OpenAI-compatible provider (OpenAI, DeepSeek, Groq, Mistral, local endpoints), and Google Gemini.

The design premise is that a model's own confidence is not evidence. Everything in the research pipeline exists to replace "the model said it was sure" with something you can audit: which claims were checked against sources, which critique survived, which assumptions were never stated, and which numbers produced the final tier.

Learn more on the official GitHub repo at: https://github.com/YahyaHammad/Venastine-Research-Harness