retrieval repositories

Trending repositories tagged retrieval, ranked by trending score. Updated daily.

  1. 1
    qdrant/fastembed

    Fast, Accurate, Lightweight Python library to make State of the Art Embedding

    GitHub · Python · 3,301 stars · 304 forks · +33 stars in 24 hours · Trending score 2.78

  2. 2
    VectifyAI/PageIndex

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

    GitHub · Python · 40,496 stars · 3,472 forks · +32 stars in 24 hours · Trending score 2.63

  3. 3
    MinishLab/semble

    Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

    GitHub · Python · 6,461 stars · 294 forks · +18 stars in 24 hours · Trending score 2.37

  4. 4
    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

  5. 5
    superlinked/sie

    Open-source inference server and production cluster for all the models your agent needs.

    GitHub · Python · 3,533 stars · 339 forks · +8 stars in 24 hours · Trending score 1.98

  6. 6
    embeddings-benchmark/mteb

    MTEB: State-of-the-art evaluation of embeddings across languages and modalities

    GitHub · Python · 3,518 stars · 779 forks · 0 stars in 24 hours · Trending score 0.95

  7. 7
    PerryLink/dsh-library

    Local document knowledge base for DeepSeek Harness: library_add/remove/list, hybrid semantic+keyword library_search with diversity re-ranking, relevance filtering and lost-in-the-middle avoidance, citation-aware injection, library_cite_check and library_diagnose — SQLite-backed index via the storage domain, local embedding, zero model downloads.

    GitHub · TypeScript · 30 stars · 0 forks · +2 stars in 24 hours · Trending score 0.91

  8. 8
    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

  9. 9
    tigerless-labs/agent-memory

    Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

    GitHub · Python · 4,323 stars · 212 forks · −2 stars in 24 hours · Trending score 0.71

  10. 10
    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

  11. 11
    usemoss/moss

    The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.

    GitHub · Python · 807 stars · 104 forks · 0 stars in 24 hours · Trending score 0.30

  12. 12
    memoket/memoket-kite

    An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

    GitHub · Python · 234 stars · 24 forks · 0 stars in 24 hours · Trending score 0.30

  13. 13
    manojmallick/sigmap

    ~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

    GitHub · JavaScript · 647 stars · 53 forks · 0 stars in 24 hours · Trending score 0.29

  14. 14
    pipecat-ai/pipecat-context-hub

    Local-first MCP server providing Pipecat docs, examples, and API context for AI coding agents

    GitHub · Python · 11 stars · 4 forks · 0 stars in 24 hours · Trending score 0.28

  15. 15
    anush008/fastembed-rs

    Rust library for generating vector embeddings and reranking locally!

    GitHub · Rust · 1,053 stars · 150 forks · 0 stars in 24 hours · Trending score 0.27

  16. 16
    mrsladoje/sweet-search

    Local code search for AI agents: cheaper, faster and sweeter. Because maybe grep isn't all you need... 🍬

    GitHub · JavaScript · 121 stars · 3 forks · 0 stars in 24 hours · Trending score 0.26

  17. 17
    HaoDot/Video2BEV-Open

    Official Repo for ICCV25-Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization

    GitHub · Shell · 48 stars · 3 forks · 0 stars in 24 hours · Trending score 0.22

  18. 18
    ohdearquant/lattice

    Run local AI models anywhere

    GitHub · Rust · 46 stars · 6 forks · 0 stars in 24 hours · Trending score 0.19

  19. 19
    nace-ai/drexgrep

    Drex harness for context search: ask a question about a repo, get the files and lines your coding agent should read first.

    GitHub · TypeScript · 13 stars · 1 forks · 0 stars in 24 hours · Trending score 0.16

  20. 20
    ArkanDash/Advanced-RVC-Inference

    Advanced RVC Inference for quicker and effortless model downloads

    GitHub · Python · 90 stars · 40 forks · 0 stars in 24 hours · Trending score 0.14

  21. 21
    ContextFit/cf

    Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.

    GitHub · Python · 13 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14

  22. 22
    zhaoxinghua09-cell/silent-failure-catalog

    15 named silent-failure modes - validation that passes while nothing is being checked. Each with a runnable reproduction, a fixing recipe and a negative control, plus a self-testing linter.

    GitHub · Python · 9 stars · 2 forks · 0 stars in 24 hours · Trending score 0.09

  23. 23
    caseclose/cma-harness

    Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editing — externalizing visual history into episodic memory with selective retrieval. Includes the M2CA-Bench benchmark.

    GitHub · Python · 16 stars · 2 forks · 0 stars in 24 hours · Trending score 0.09

  24. 24
    roomi-fields/rtfm

    The open retrieval layer for AI coding agents. Indexes code, docs, legal, research, data — 24 parsers (incl. EPUB, DOCX, ODT, MIDI, audio), FTS5 + semantic search, knowledge graph. Serves surgical context via MCP. Open source, local, free.

    GitHub · Python · 27 stars · 6 forks · 0 stars in 24 hours · Trending score 0.09