Qwen3 Reranker API

A standalone, GPU-accelerated reranking service using Qwen3-Reranker-0.6B behind a Cohere-compatible /v2/rerank endpoint, so RAG pipelines can swap a hosted reranker for a local one.

October 2025ShippedSource on GitHub ↗

Retrieval pipelines often call Cohere's rerank endpoint. This service exposes the same /v2/rerank contract backed by Qwen3-Reranker-0.6B running locally on the GPU, so an existing pipeline can switch to a self-hosted reranker by changing a base URL. Ships with bash and Python test suites that exercise the API.

Hard parts

Matching the Cohere request/response shape exactly so clients need no changes

More work

Prep: voice coding copilotAn interview-prep IDE with a voice: a Monaco editor, a LeetCode-style problem library, and an AI copilot you can talk to, interrupt and point at your code.
Agent2DBA desktop database agent: connect PostgreSQL, ask in plain language, and let an agent explore the schema, write and run SQL, and remember what it learns, with a human approving every write.
voiceAgentA fully local, real-time voice assistant you can talk over: Parakeet listens, an LLM thinks, Kokoro speaks, SQLite remembers. Sub-second speech-to-speech with two-stage barge-in.