CalibratedDecisions.

Repo · Search & RAG

nocap

No evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks.

Open github.com ↗

From the repository

No evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks. MCP server, Python SDK, CI route tests.

ai-agentsclaude-codedecision-modeldeepseekevaluationguardrailshallucinationjevlangchainlayallamaindexllmlocal-firstmcpmcp-serverollamaopenaipythonragsystem-one

How builders describe it

No evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks. MCP server, Python SDK, CI route tests.

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects