Skip to content
#

bm25-search

Here are 30 public repositories matching this topic...

XERJ is the new way for AI to search data. Its autoindex capability activates agents to know your data without the token waste of grep and sed. One command indexes code, docs, logs and PDFs for search, RAG, security audits and agent memory, using 40x fewer tokens than grep. Elasticsearch compatible, so existing clients just work.

  • Updated Sep 10, 2026
  • Rust

A Knowledge Graph-Infused RAG framework for multi-hop reasoning over Türkiye-related entities. It utilizes Neo4j for graph storage, Wikidata5M for structured data, and Ollama (Qwen 2.5) for agentic spreading activation to outperform traditional text-based RAG baselines.

  • Updated Apr 25, 2026
  • Python

Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.

  • Updated May 12, 2026
  • Python

Read-only MCP server for 1C BSL: hybrid BM25 + vector search over procedures & functions in Elasticsearch, dedup + rerank — feeds relevant context to code LLMs. | Только чтение: MCP-сервер для BSL (1С) — гибридный BM25 + векторный поиск по процедурам и функциям в Elasticsearch, дедупликация и rerank. Релевантный контекст для code-моделей.

  • Updated Aug 31, 2026
  • Python

Add this topic to your repo

To associate your repository with the bm25-search topic, visit your repo's landing page and select "manage topics."

Learn more