bm25 repositories
Trending repositories tagged bm25, ranked by trending score. Updated daily.
-
1
SparkofSpike/Brain4Agent
Committed to building the world’s most cutting-edge, CJK-first memory module for all mainstream agents. Any issues and PRs are welcome.
GitHub · Python · 181 stars · 26 forks · +8 stars in 24 hours · Trending score 2.27
-
2
paradedb/paradedb
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
GitHub · Rust · 9,543 stars · 516 forks · +6 stars in 24 hours · Trending score 2.00
-
3
zvec-ai/zvec-grep
Local-first search across your workspace, built for humans and AI agents.
GitHub · Rust · 4,367 stars · 269 forks · +3 stars in 24 hours · Trending score 1.78
-
4
manticoresoftware/manticoresearch
Open-source search database for full-text, vector, and hybrid search with real-time indexing and SQL.
GitHub · C++ · 12,098 stars · 655 forks · +7 stars in 24 hours · Trending score 1.58
-
5
serenedb/serenedb
The First Real-Time Search Analytics Database
GitHub · C++ · 1,111 stars · 83 forks · −1 stars in 24 hours · Trending score 1.36
-
6
smart-mcp-proxy/mcpproxy-go
Supercharge AI Agents, Safely
GitHub · Go · 427 stars · 74 forks · +2 stars in 24 hours · Trending score 1.32
-
7
timescale/pg_textsearch
PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.
GitHub · C · 4,063 stars · 132 forks · 0 stars in 24 hours · Trending score 1.21
-
8
infiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
GitHub · C++ · 4,770 stars · 460 forks · +2 stars in 24 hours · Trending score 1.13
-
9
VeraTools/vera
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.
GitHub · Rust · 145 stars · 19 forks · 0 stars in 24 hours · Trending score 0.79
-
10
shekharmaheshwari/intelligent-search-platform
Self-hosted AI search + chat platform that keeps LLM costs low: hybrid (BM25 + vector) search, RAG product chat, and rule-based query understanding that skips the LLM when it isn't needed. Works with OpenAI, Claude, Gemini, Groq, Ollama, or LiteLLM. Built on Typesense + FastAPI.
GitHub · Python · 44 stars · 0 forks · 0 stars in 24 hours · Trending score 0.78
-
11
XBlueSky/cortexes
Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.
GitHub · Python · 25 stars · 5 forks · 0 stars in 24 hours · Trending score 0.72
-
12
398894496-arch/TDHarness
Self-hosted AI workbench for a company LAN. One command on a Windows server sets up login, roster, model gateway, company disk and knowledge base; each employee's agent works on their own PC while model keys stay on the server. 一键安装的局域网 AI 工作台。
GitHub · JavaScript · 43 stars · 6 forks · +1 stars in 24 hours · Trending score 0.68
-
13
IvenKooLab/loci
Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.
GitHub · Python · 102 stars · 2 forks · +1 stars in 24 hours · Trending score 0.65
-
14
flupkede/codesearch
Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.
GitHub · Rust · 105 stars · 21 forks · +1 stars in 24 hours · Trending score 0.63
-
15
infino-ai/infino
Search library built on Parquet. Fast, efficient, and scalable.
GitHub · Rust · 157 stars · 31 forks · 0 stars in 24 hours · Trending score 0.61
-
16
memtomem/memtomem
Local-first long-term memory for AI coding agents, kept as Markdown you own. Hybrid keyword + semantic search over your notes and code via MCP — one store shared across Claude Code, Codex, Cursor, OpenCode, and more. Hook-free by default.
GitHub · Python · 26 stars · 49 forks · 0 stars in 24 hours · Trending score 0.60
-
17
nczz/pi-knowledge
Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.
GitHub · TypeScript · 36 stars · 9 forks · +1 stars in 24 hours · Trending score 0.55
-
18
ropensci-review-tools/pkgmatch
Find R packages matching either descriptions or other R packages
GitHub · R · 11 stars · 1 forks · +1 stars in 24 hours · Trending score 0.51
-
19
Liyuze0422/EarShot
实时面试提词器:本地 ASR + BM25 检索 + LLM 快答,说完 1.3~1.5 秒出答案(Windows)
GitHub · Python · 17 stars · 1 forks · +1 stars in 24 hours · Trending score 0.46
-
20
SeekStorm/SeekStorm
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
GitHub · Rust · 1,938 stars · 74 forks · 0 stars in 24 hours · Trending score 0.43
-
21
olivier-ls/php-fts
A self-contained full-text search engine in pure PHP. No extensions, no dependencies.
GitHub · PHP · 147 stars · 3 forks · 0 stars in 24 hours · Trending score 0.39
-
22
Dicklesworthstone/frankensearch
Two-tier hybrid local search for Rust and the fsfs CLI: sub-millisecond first-pass results from a Potion/Model2Vec fast tier, then MiniLM quality refinement. Fuses native pure-Rust BM25 (Quill engine) and semantic vector search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.
GitHub · Rust · 96 stars · 23 forks · 0 stars in 24 hours · Trending score 0.37
-
23
CodeBendKit/codeseek
Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.
GitHub · Rust · 762 stars · 44 forks · 0 stars in 24 hours · Trending score 0.29
-
24
derkinL/dsh-remembers
Long-term memory for DeepSeek Harness, built for companion AI. It says it does not remember instead of making things up. 情感陪伴向记忆插件:向量 + 中文 BM25 + 分层衰减。
GitHub · JavaScript · 21 stars · 1 forks · 0 stars in 24 hours · Trending score 0.27