vector-search Tools

XERJ is an AI-native search engine that indexes code, documents, logs, and PDFs so AI agents can query the index instead of re-reading files into their expensive context window. It solves the problem of wasteful token consumption from tools like grep and sed, reducing output token usage by 2.7x. It's built for developers and teams using AI agents for coding, security audits, RAG, and agent memory, and it's Elasticsearch-compatible for easy integration.

WeKnora is an open-source platform that turns your raw documents and data into a powerful, queryable knowledge base. It solves the problem of scattered, static information by creating a dynamic system that can answer questions via RAG, reason autonomously, and maintain itself like a wiki. It's built for developers, teams, and organizations who need to unlock the value trapped in their documents and build intelligent knowledge applications.

SIE is an open-source inference server and production cluster that allows developers to run all the models their AI agents need—from embeddings and rerankers to large language models—entirely within their own infrastructure. It solves the problem of vendor lock-in, data privacy concerns, and high costs associated with proprietary model APIs by providing a performant, self-hosted alternative. It's built for teams building production AI agents who require control, data sovereignty, and the ability to compose the best open models.

TencentDB Agent Memory is a centralized memory system for AI agent teams. It solves the problem of fragmented, non-reusable knowledge by converting conversations, documents, and code into four governed, shareable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph). It's designed for teams building and scaling AI agents across different frameworks, enabling consistent knowledge sharing and improved agent capabilities.

A vector index built on TurboQuant, written in Rust with Python bindings