Show HN: TurnZero – Persistent Expert for LLMs

Category: devtools

Tags: llm-context, developer-tools, mcp-server

Score: 7.3/10 (Innovation: 7, Technical: 8, Documentation: 7, Utility: 7)

TurnZero provides persistent context memory for AI coding sessions by injecting personal preferences and domain-specific knowledge before the first turn, reducing repetitive corrections. It uses a local-first, client-side MCP server with embedding-based retrieval to nudge models toward desired behavior. Its innovative combination of personal priors, semantic expert blocks, and a self-improving feedback loop via AI-submitted corrections addresses a real pain point for developers using multiple AI assistants.

Target audience: backend engineers, devops, security engineers, platform engineers

Repository: https://github.com/turnzero-ai/turnzero · Python · MIT

View on Hacker News