npm
docmd-io/docmd-search
Offline semantic search engine that runs anywhere.
MITJul 18, 2026 · metrics 2.10.0
All tags
Catalogue tag
#vector-search
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
112 records
Go
gandazgul/mnemosyne
Local-first memory and document retrieval CLI built in Go. Store short notes, messages, and documents in SQLite, then retrieve them with local embeddings, vector-first BM25 hybrid search, and optional local reranking. All ML inference runs on-device via ONNX Runtime. No cloud APIs required.
MITJul 29, 2026 · metrics 2.10.0
PyPI
intersystems-community/iris-vector-graph
High-performance graph database + vector search powered by InterSystems IRIS
Custom licenseJul 19, 2026 · metrics 2.10.0
PyPI
nevenincs/vaultspec-rag
GPU-accelerated semantic search for your docs and source code - hybrid dense + sparse RAG on a local Qdrant backend, served to Claude Code and other MCP clients. The search companion to vaultspec-core.
MITJul 28, 2026 · metrics 2.10.0
PyPI · Go · npm
qataruts/monlite
The complete backend for AI agents in one SQLite file : Documents, vectors, cache, queue, and cron.
MITSep 5, 2026 · metrics 2.10.0
crates.io
visorcraft/MongrelDB
A fast embedded+server columnar database with SQL, vector search, full-text search, and AI-native retrieval. Dozens of languages supported. Written in Rust.
Apache-2.0Aug 22, 2026 · metrics 2.10.0
npm
damoqiongqiu/mcp-local-rag
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
MITAug 2, 2026 · metrics 2.10.0
PyPI
lucagattoni/pinakes
Pinakes — a portable, agent-first knowledge base. One directory = one KB.
Apache-2.0Aug 23, 2026 · metrics 2.10.0
crates.io · npm
YASSERRMD/Verdex
Jurisdiction-aware judicial reasoning platform — a model-agnostic AI engine that produces citation-backed, adversarially-tested draft case analyses for human sign-off. Non-binding by design.
Apache-2.0Jul 17, 2026 · metrics 2.10.0
RubyGems
patterns-ai-core/weaviate-ruby
Ruby wrapper for the Weaviate vector search database API
MITJul 20, 2026 · metrics 2.10.0
npm
ruvnet/agentdb
Vector memory that gets smarter every time your agent uses it.
MITJul 23, 2026 · metrics 2.10.0
PyPI
aetna000/aetnamem
AetnaMem /ET-nuh-mem/ is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.
AGPL-3.0Aug 1, 2026 · metrics 2.10.0
Go
dotcommander/reliquary
Go toolkit for document ingestion and retrieval.
MITJul 24, 2026 · metrics 2.10.0
Go
alxxpersonal/stardust
Local-first markdown context engine for AI coding agents. Indexes a repo's docs into SQLite (FTS5 + local vectors) and exposes CLI, HTTP, and MCP over one service core. Ships a docs registry, skills/agents sync, and code-to-doc governance.
MITJul 17, 2026 · metrics 2.10.0
Go
BarqDB/barq-go
Go SDK for BarqDB — an embedded local-first database with HNSW vector search built in.
Apache-2.0Sep 5, 2026 · metrics 2.10.0
crates.io
RecursiveIntell/turbo-quant
Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (ICLR 2026)
MITAug 22, 2026 · metrics 2.10.0
npm
holgerreppert/opencode-fractal-memory
A fractal memory plugin and mcp server for opencode.
MITJul 17, 2026 · metrics 2.10.0
npm
johnsonfash/forge-orm
No repository description published.
MITJul 24, 2026 · metrics 2.10.0
PyPI
Veedubin/memini-ai-dev
No repository description published.
No licenseAug 1, 2026 · metrics 2.10.0
PyPI
antonyrag/ragleap-core
The open-source core of RagLeap — a self-hosted RAG chat engine (document ingestion, retrieval, citations) powering RagLeap's full AI business manager: Voice AI, WhatsApp/Telegram/Discord bots, database & CRM integrations, workflow automation, and a private executive assistant. Foundation layer — hosted platform at ragleap.com
MITJul 26, 2026 · metrics 2.10.0
Go
altSeneca/picoqmd
Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.
MITJul 23, 2026 · metrics 2.10.0
PyPI
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
MITAug 12, 2026 · metrics 2.10.0