crates.io
SeekStorm/SeekStorm
SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.
Apache-2.02026年9月9日 · 指标 2.10.0
全部标签
目录标签
#retrieval
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
61 条记录
NuGet
iyulab/lm-supply
.NET library for on-demand local AI model inference — zero bundled models, lazy loading, hardware-aware GPU/CPU selection, 10 task types including embeddings, generation, vision, and audio.
MIT2026年9月10日 · 指标 2.10.0
PyPI
xhluca/bm25s
Fast BM25 search in Python, powered by Numpy and Numba
MIT2026年9月12日 · 指标 2.10.0
PyPI · crates.io · Go
The-Billy-Company/relate
Code similarity search by compression - find near-duplicate files, clone families, and where a pasted snippet came from. No embeddings, no model, no vector database.
Apache-2.02026年10月1日 · 指标 2.10.0
Go
dorukardahan/nole
Free local web search/extraction router for AI agents. Go CLI + MCP, BYOK/free-first routing, keyless DDGS/Scrapling fallback, setup writers and client guides.
Apache-2.02026年9月10日 · 指标 2.10.0
Go
marcus/recall
Federated, evidence-first retrieval for personal AI agents
Apache-2.02026年9月19日 · 指标 2.10.0
NuGet
iyulab/FluxIndex
Production-ready .NET 10 RAG library with hybrid vector + keyword search, multi-backend storage (SQLite, PostgreSQL, Neo4j, Qdrant), and MCP server integration.
MIT2026年9月15日 · 指标 2.10.0
npm · PyPI
mrsladoje/sweet-search
Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬
Apache-2.02026年9月11日 · 指标 2.10.0
npm · Go · crates.io
use-crux/crux
Typed building blocks for everything around your LLM call.
Apache-2.02026年9月18日 · 指标 2.10.0
PyPI
bgokden/reasongraph
Graph memory for AI agents: facts in, entities and cause->effect relations extracted with small open models, multi-hop recall with a cited chain. Library, HTTP/MCP service, LangChain, hosted at memory.primaxiom.ai
MIT2026年9月18日 · 指标 2.10.0
PyPI · npm
docmancer/docmancer
Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.
MIT2026年9月16日 · 指标 2.10.0
PyPI
wallter/trw-memory
Standalone AI agent memory engine — hybrid search (BM25 + vectors), Q-learning scoring, Ebbinghaus decay, tiered storage, knowledge graph. Part of TRW Framework.
自定义许可证2026年10月10日 · 指标 2.10.0
PyPI · npm
surendranb/wikipedia-mcp-server
Progressive-retrieval MCP server for Wikipedia
MIT2026年9月15日 · 指标 2.10.0
PyPI
EverMind-AI/EverAlgo
EverAlgo is the algorithm library behind EverMind's memory system — stateless, storage-free, focused on extraction and ranking only. Orchestration, persistence, and routing live upstream in evermem.
Apache-2.02026年10月13日 · 指标 2.10.0
crates.io
L-Defraiteur/lucivy
BM25 full-text search that actually finds what you type — fuzzy substrings across token boundaries, accent-insensitive, with byte-offset highlights. Python + Rust, built for hybrid search with vector DBs.
自定义许可证2026年9月18日 · 指标 2.10.0
npm · PyPI · crates.io +1
muthuishere/citenexus
Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/
MIT2026年9月5日 · 指标 2.10.0
PyPI
Florian-BARRE/DocForge
该仓库未发布描述。
GPL-3.02026年9月7日 · 指标 2.10.0
PyPI · npm
bernatch22/megabrain
Code retrieval for AI agents: one call returns the exact code, verbatim with true line numbers, instead of 20 greps. The whole index is one SQLite file — no vector DB, no daemon. MCP server for Claude Code, Cursor and Codex.
MIT2026年9月12日 · 指标 2.10.0
PyPI
ruzgarkanar/Lmm
A verifiable memory layer for language models — facts in a graph, every claim with its source.
Apache-2.02026年9月24日 · 指标 2.10.0
PyPI
lucagattoni/pinakes
Pinakes — a portable, agent-first knowledge base. One directory = one KB.
Apache-2.02026年8月23日 · 指标 2.10.0
Go
bright-interaction/mesh
Sovereign single-binary knowledge mesh for coding agents (MCP): index, search and serve your notes + code as context. Fair-code (no reselling).
自定义许可证2026年9月9日 · 指标 2.10.0
—
DanceNitra/ramr
RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)
MIT2026年9月14日 · 指标 2.10.0
npm
NHTIO/ADK
A read-only, sanitized GitHub mirror of the open source release for @nhtio/adk
MIT2026年9月13日 · 指标 2.10.0
NuGet · npm
scottgal/styloflow
An ephemeral workflow engine which acts as the basis for the StyloBot, Wall & Workflow as well as the lucidRAG system
Unlicense2026年9月11日 · 指标 2.10.0
npm
augmem/cortext.ts
TypeScript and JavaScript bindings for Cortext — npm package @augmem/cortext
Apache-2.02026年9月16日 · 指标 2.10.0
npm
qwertymuzaffar/chunklet
Token-aware text chunking for RAG - exact source offsets, sentence and markdown modes, zero dependencies.
MIT2026年10月20日 · 指标 2.10.0
Go
dotcommander/reliquary
Go toolkit for document ingestion and retrieval.
MIT2026年9月13日 · 指标 2.10.0
PyPI
jorgell23-sys/mdcx
Convert a document collection to verified Markdown, package it into a single encrypted archive with its search index and provenance, and serve it to agents over the Model Context Protocol. Python 3.11+, Apache-2.0.
Apache-2.02026年10月21日 · 指标 2.10.0
PyPI · crates.io
zhlhaohao/doclens
doc index\search\exploer\aiask utility
Apache-2.02026年8月27日 · 指标 2.10.0
Go
codysnider/tagmem
Structured local memory storage and retrieval for LLM agents
MIT2026年9月19日 · 指标 2.10.0