Lib.rs

ollama-rs

interacting with the Ollama API

servo

A component of the servo web-engine

memvid-core

Core library for Memvid v2, a crash-safe, deterministic, single-file AI memory

velesdb-server

REST API server for VelesDB vector database

cgip

Terminal client for interacting with Chat GPT that allows you to build and manipulate contexts

chromadb

client library for the ChromaDB vector database

uteke-server

HTTP server for uteke — persistent warm memory for AI agents

tokenix

Semantic search, symbol graphs, secrets scanning, output filters, and CLI hooks that save 60-90% LLM tokens

oxidize-pdf

Pure Rust PDF library for AI/RAG: structure-aware chunking with bounding boxes, heading context, and token estimates. No Python, no ML, no C bindings.

rag-rat

CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence

rustyscript

Effortless JS Integration for Rust

llm-kernel

Foundation library for Rust AI-native apps — provider catalog, LLM client, MCP server, search, telemetry, and safety

model2vec-rs

Official Rust Implementation of Model2Vec

kimetsu-brain

Project + user-scope memory, hybrid retrieval (lexical + cosine), ambient context, secret redaction at ingest for kimetsu

anda_db

Anda DB is a Rust library designed as a specialized database for AI Agents, focusing on knowledge & memory

pensyve-cli

Pensyve command-line interface — universal memory runtime for AI agents

embive

interpreter/virtual-machine that leverages RISC-V bytecode, enabling sandboxed code execution on tiny devices (e.g. microcontrollers).

second-brain-cli

Universal memory layer for AI coding agents — ingest, recall, and sync across Claude Code, Cursor, and more

ck-embed

Text embedding providers for ck semantic search

octolib

Self-sufficient AI provider library with multi-provider support, embedding models, model validation, and cost tracking

rqmd

command-line interface (binary rqmd)

sherpa-rs

Rust bindings to https://github.com/k2-fsa/sherpa-onnx

ripvec

Semantic code search CLI — like ripgrep but for meaning

dwbase-engine

DWBase: agent-first immutable atom store, components, and tools

uni-xervo

Unified Rust runtime for local and remote embedding, reranking, and generation models

sqlite-vector-rs

SQLite extension providing PGVector-like native vector types with HNSW indexing

kiromi-ai-cli

Operator and developer CLI for the kiromi-ai-memory store: append, search, snapshot, regenerate, migrate-scheme, gc, audit-tail

codemem

Persistent memory engine for AI coding assistants

opencode-memory

Persistent semantic memory for AI agents — a single self-contained stdio MCP server over SQLite + sqlite-vec with local llama.cpp embeddings

pensyve-mcp

Pensyve MCP server (stdio transport) — universal memory runtime for AI agents

ruvector-postgres

High-performance PostgreSQL vector database extension v2 - pgvector drop-in replacement with 230+ SQL functions, SIMD acceleration, Flash Attention, GNN layers, hybrid search, multi-tenancy…

subsume

Geometric region embeddings (boxes, cones, octagons, Gaussians, hyperbolic intervals, sheaf networks) for subsumption, entailment, and logical query answering

brainwires-storage

Backend-agnostic storage, tiered memory, and document management for the Brainwires Agent Framework

annembed

dimension reduction à la Umap

popsam-cli

CLI for AI-assisted selection of semantically representative texts

encoderfile

Distribute and run transformer encoders with a single file

rig-bedrock

AWS Bedrock model provider for Rig integration

frankensearch-index

FSVI vector index, SIMD dot product, and top-k search for frankensearch

mem7-config

Configuration types for the mem7 memory engine

wasmicro

Tiny transformer inference for the web. BERT, GPT-2 and T5 in a 199 KB WASM bundle.

memme-server

Self-hosted REST API server for MemMe memory engine

mailrs-intelligence

LLM-powered email analysis primitives: structured extraction, importance scoring, spam classification, and embeddings — with a pluggable LlmProvider trait and an OpenAI-compatible reference implementation

toak-rs

A high-performance library and CLI tool for tokenizing git repositories, cleaning code, and generating embeddings

events_once

Efficient oneshot events (channels) with support for single-threaded events, object embedding, event pools and event lakes

elid

Embedding Locality IDentifier - encode embeddings into sortable string IDs for vector search without vector stores, plus fast string similarity algorithms

engram_mcp

MCP server for AI agent persistent memory with SQLite and local embeddings

sqlite-graphrag

Persistent GraphRAG memory for Claude Code, Codex, Cursor, and 24+ AI agents in a single 6 MB Rust binary. LLM-only and one-shot in v1.0.78: every remember / ingest spawns a headless…

tranz

Point-embedding knowledge graph models: TransE, RotatE, ComplEx, DistMult. GPU training via candle.

graphembed

graph embedding

memme-mcp

MCP (Model Context Protocol) server for MemMe memory engine

openai-tools

Tools for OpenAI API

deepthought

Functional wrapper around Llama.cpp with Rust Dynamic datatypes and Vector store support for creating RAG applications

hero_redis

High-performance Redis-compatible server on redb with vector database support

nexus-memory-agent

Always-on memory agent for Nexus Memory System

swamp

script language for embedding

talon-core

Core retrieval engine for Talon: hybrid search (BM25 + semantic + reranker), indexing, and graph-aware ranking over markdown corpora

reasonkit-mem

High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion, and semantic retrieval for AI systems

iqdb-quantize

Vector quantization (scalar, product, binary) for memory-efficient vector search - part of the iQDB family

cerememory-engine

Orchestrator that assembles all Cerememory stores and engines

cartog-rag

Semantic search and RAG pipeline for cartog

ruvector-cnn

CNN feature extraction for image embeddings with SIMD acceleration

embedrs

Unified embedding — cloud APIs (OpenAI, Cohere, Gemini, Voyage, Jina) + local inference, one interface

rong

RongJS runtime and embedding API

git-semantic

Semantic search for git history using natural language

breadchunks

Heading-aware, token-budgeted semantic chunker for Markdown — for RAG and embedding pipelines

memme-llm

LLM abstraction layer for MemMe — OpenAI and Ollama providers

seasoning

Embedding and reranking infrastructure with rate limiting and retry logic

steel-memory

A spatial memory palace for AI agents with semantic vector search, knowledge graphs, and MCP tools

nexus-memory-vectors

Semantic search over storage-backed embeddings for Nexus Memory System

foxstash-core

High-performance local RAG library - SIMD-accelerated vector search, HNSW indexing

everruns-runtime

Public in-process runtime for embedding Everruns harnesses

postrust-core

Core library for Postrust - PostgREST-compatible REST API for PostgreSQL

rig-milvus

Milvus vector store implementation for the rig framework

tsrun

A TypeScript interpreter designed for embedding in applications

kremory

Bi-temporal knowledge graph engine + agent memory orchestration in pure Rust

spl

Stack Pogramming Language: A simple, concise scripting language

converge-knowledge

A self-learning knowledgebase with vector search, gRPC, and MCP interfaces

komando

A command line utility to better organize and keep track of your commands

memory-mcp

MCP server for semantic memory — pure-Rust embeddings, vector search, git-backed storage

nabled-embeddings

Lightweight ndarray-native compute and rerank layer for embedding vectors

heliosdb-codekb-mcp

Local MCP server for code+docs knowledge bases, embedding HeliosDB-Nano as a library

servo-paint

A component of the servo web-engine

satchel-rag

Portable RAG system on a USB drive. Single binary, local embeddings, MCP protocol.

niblits

Token-aware, multi-format text chunking library with language-aware semantic splitting

ripvec-mcp

MCP + LSP server for ripvec — semantic code search, PageRank repo maps, and multi-language code intelligence

ternlang-ruvector

Ternary-optimized Sparse GEMV acceleration for Vector Databases (RuVector Bridge)

ragloom

The minimalist RAG ingestion engine

servo-constellation-traits

A component of the servo web-engine

chat-completions

Generic OpenAI-compatible Chat Completions client for chat-rs. Bring your own server (Ollama, vLLM, llama.cpp, LiteLLM, etc.).

quorumrag

Quorum-based retrieval-augmented generation: fuse multiple retrievers and keep only the evidence they agree on

beni

Typed Rust wrapper over the mruby C API, sitting on the beni-sys bindgen surface

mem7

LLM-powered long-term memory engine — Rust core with Python bindings

veles-cli

CLI binary for Veles code search

rag-module

Enterprise RAG module with chat context storage, vector search, session management, and model downloading. Rust implementation with Node.js compatibility.

lnmp-quant

Quantization and compression for LNMP embedding vectors with minimal accuracy loss

turbo-quant

Experimental vector compression sidecars with PolarQuant, TurboQuant, QJL sketches, wire formats, and benchmark receipts

sift-search

Sift — a DSL for agents to search codebases in faster, deeper, and more sophisticated ways

hyperball

Hyperbolic geometry: Poincare ball, Lorentz model, Mobius operations

monodex

Fast, accurate code search for large Rush monorepos

mdvs

A database of markdown documents — schema validation and semantic search

libbun

Rust facade for hosting JavaScript and TypeScript providers through a replaceable Bun native plugin

manifolds-rs

Embedding methods implemented in Rust: (parametric) UMAP, tSNE, PHATE, Diffusion Map and PacMAP

vipune

A minimal memory layer for AI agents

atomr-agents-embed

EmbeddingActor and pluggable AnnIndex (CPU default via atomr-accel-agents)

tokenuinely

Semantic codebase index for AI agents — replace grep/glob with one smart tool call

stator_jse_ffi

Stator JavaScript engine — stable C FFI layer for embedding

lunaris-embed-native

Native candle-rs ModernBERT FP16 embedder for IBM granite-embedding-311m-multilingual-r2

yantrikdb

Cognitive memory engine for persistent AI systems

neurographrag

Local GraphRAG memory for LLMs in a single SQLite file

sediment-mcp

Semantic memory for AI agents - local-first, MCP-native

embedd

Embedding interfaces + local backends (Candle/HF)

trusty-embedderd

Unified ONNX embedding daemon with HTTP + UDS transports and BatchQueue (issue #164)

oxllm

Minimalist adaptive routing LLM proxy in Rust

servo-constellation

A component of the servo web-engine

json-e

A data-structure parameterization system for embedding context in JSON objects

memme-embeddings

Embedding providers for MemMe — ONNX local inference, OpenAI, and Ollama

lua-rs-hlua-shim

Drop-in replacement for the hlua 0.4 embedding API, backed by the pure-Rust lua-rs VM. Lets hlua-based consumers (authoscope, sn0int) run on lua-rs behind a feature flag.

oramacore-client

Server-side Rust client for OramaCore and Orama Cloud

ruvector-graph-wasm

WebAssembly bindings for RuVector graph database with Neo4j-inspired API and Cypher support

edon

embedding Nodejs (libnode) within Rust

mneme-mcp

MCP-native persistent memory tool for AI agents

nostr-bbs-search-worker

Search Worker: RVF vector store, cosine k-NN, hash embeddings (nostr-bbs)

gitsem

Semantic search and spatial navigation for Git repositories — map, get, and grep for AI coding agents

veles-mcp

MCP (Model Context Protocol) server for Veles code search

claudix

Local semantic search plugin for Claude Code

pyannote-rs

Speaker diarization using pyannote in Rust

transmutation

High-performance document conversion engine for AI/LLM embeddings - 27 formats supported

avocado-cli

CLI tool for AvocadoDB - deterministic context compilation for AI agents

cerememory-adapter-openai

Cerememory LLM adapter for openai

cerememory-adapter-gemini

Cerememory LLM adapter for gemini

ruve-db

A hybrid vector and full-text search database with HNSW approximate nearest-neighbour indexing and BM25

siglip2-naflex

Rust ONNX inference library for SigLIP2 NaFlex (image+text embeddings)

mnemoria

Persistent, git-friendly memory storage for AI agents with hybrid semantic + full-text search

agentroot-mcp

Model Context Protocol server for agentroot - AI assistant integration

open_clip_inference

Run OpenCLIP compatible embedding models via ONNX Runtime

vigil-sdk

Stable public SDK facade for embedding Vigil's local AI safety runtime — typed decisions/audit + firewall execution + redaction scanning

frame-catalog

Vector catalog and semantic indexing subsystem for Frame microservices

omni_search

A unified Rust SDK for multimodal embedding and similarity search

clark-hash

Clark Hash: stateless sparse Johnson-Lindenstrauss sketches for neural embeddings

mongodb-voyageai

A client for generating embeddings and reranking with Voyage AI

agent-riff-v4

Snowball generation 4: musician-soul integration, crates-as-phrases, autonomous spec evolution, generation memory with pruning, self-bootstrapping

finalfusion

Reader and writer for common word embedding formats

rmcp-memex

RAG/memory MCP server with LanceDB vector storage

extendr-engine

Safe and user friendly bindings to the R programming language

llmx-mcp

Fast codebase indexing and semantic search MCP server with BM25 and hybrid embeddings

servo-paint-api

A component of the servo web-engine

localcache

Cache expensive computation results tied to local files — fast, simple, and SQLite-backed

awful_aj

A CLI for interacting with OpenAI compatible APIs

operonx

High-performance Rust execution backend for Operon workflows

servo-embedder-traits

A component of the servo web-engine

pixelflow

Public facade for PixelFlow embedding APIs

luckyshot

A CLI tool for one-shot code generations using RAG and file watching

uteke-core

The Brain for Your AI — persistent memory and smart context management

synaptic-lancedb

LanceDB embedded vector store for Synaptic — serverless embedded vector database

kiromi-ai-memory

Local-first multi-tenant memory store engine: Markdown/text content on object storage, metadata in SQLite, plugin-shaped embedder/storage/metadata, hybrid text+vector search

lmkit

Multi-provider AI API client (OpenAI, Anthropic, Google Gemini, Aliyun, Ollama, Zhipu; chat, embed incl. Gemini, rerank, image, audio stubs)

synaptic-opensearch

OpenSearch vector store for Synaptic

vectorizer-sdk

Rust SDK for Vectorizer — RPC-first (vectorizer://) with HTTP fallback

cartog-watch

File system watcher with auto-reindexing for cartog

synaptic-voyage

Voyage AI embeddings and reranker for Synaptic

oxibonsai-rag

Pure Rust RAG pipeline for OxiBonsai

avocado-core

Core engine for AvocadoDB - deterministic context compilation for AI agents

pizen-lynx-storage

Storage layer for Lynx

indra_db

A content-addressed graph database for versioned thoughts

rust-memex

Operator CLI + MCP server: canonical corpus second: semantic index second to aicx

janetrs

High level binding for Janet programming language

rawq

Context retrieval engine for AI agents — semantic + lexical search, single Rust binary, fully offline

rumpy

A reimplementation of NumPy for use with rustpython in embedded interpreters

synaptic-jina

Jina AI embeddings and reranker for Synaptic

synaptic-milvus

Milvus vector store for Synaptic

slabs

AST-aware code chunking and late chunking for RAG

synaptic-huggingface

HuggingFace Inference API integration for Synaptic: Embeddings

embedvec

Fast, lightweight, in-process vector database with HNSW indexing, E8/H4 lattice quantization (up to 24.8x compression), metadata filtering, and PyO3 bindings

yvdb

Educational in-memory vector DB: WAL + bincode snapshots (TOON header), IVF bucket search, Axum REST API, TOON query responses

aurora-semantic

Local embedded semantic search engine for source code, designed for IDE integration

memvid-cli

Command-line interface for Memvid v2 - AI memory with crash-safe, single-file storage

lean-rs-host

Opinionated Rust host stack for embedding Lean 4 as a theorem-prover capability: typed sessions, kernel-check evidence handles, bounded MetaM services, progress, batching, and session pooling

rune-umap

UMAP dimensionality reduction — project high-dimensional data into 2D or nD embeddings

qdb-rs

Quantum Database with vector store, MPS compression, Grover search, and fault-tolerant storage

rong_cli

Command-line interface for RongJS

satoridb

Embedded vector database for approximate nearest neighbor search (experimental)

pizen-lynx-protocol

Protocol definitions for Lynx

cml-rs

Content Markup Language (CML) v0.2 parser, generator, validator, and embedding store for structured documents

avocado-server

HTTP server for AvocadoDB - deterministic context compilation for AI agents

csep

Cosine Similarity Embeddings Print

piramid

All-in-one binary for distributed model inference, retrieval, and vector search

nndex

In-memory nearest neighbor search engine

ruv-neural-memory

rUv Neural — Persistent neural state memory with vector search and longitudinal tracking

mag-memory

MAG — Local MCP memory server with ONNX embeddings and semantic search

gh-stars

A CLI tool to fetch, cache, and search GitHub stars with vector search

pizen-lynx-embed

Embedding support for Lynx

ai-provider-sdk

Async-first Rust SDK for OpenAI APIs

wef

embedding WebView functionality using Chromium Embedded Framework (CEF3) with offscreen rendering support

nbcl

Configuration language designed to be easy and understandable

totalreclaw-memory

TotalReclaw memory backend — E2EE crypto, LSH, embeddings, reranker (Memory Taxonomy v1)

gatekpr-vector

Qdrant vector database integration for semantic search and RAG

omengrep

Semantic code search — multi-vector embeddings + BM25

monavec-core

Ultra-low resource embedded vector search kernel for edge AI

memex-contracts

Shared serde contracts for rust-memex transports and future frontends

mnem-embed-providers

Embedding-provider adapters for mnem (OpenAI, Ollama). Sync, TLS-via-rustls, tokio-free.

rag_engine

Core Rust RAG engine with optional Flutter Rust Bridge integration

musician-soul

SuperInstance ecosystem crate

search-semantically

Embeddable semantic code search with multi-signal POEM ranking

embedding

CLI for training embeddings from scratch

polarisdb

embedded vector database for local AI and RAG workloads

alpine-ai

A lightweight, low-bulk interface for all major LLM providers

miyabi-knowledge

Knowledge management system for Miyabi - Vector database, embeddings, and search

paperfoot-engram-embed

Embedding providers (Gemini Embed 2, local fallback) for engram v2

chronos-vector

High-performance temporal vector database — treats time as a geometric dimension of embedding space

vecboost

High-performance embedding vector service written in Rust

vectorpin

Verifiable integrity for AI embedding stores

agent-metamorphosis

obra

A fast, semantic search CLI for your Obsidian vault, built in Rust

ceres-client

HTTP clients for Ceres portal harvesters and embedding providers

libpetri-docgen

Build-script helper for embedding Petri net diagrams in rustdoc (DOT + client-side viewer)

sphereql

Project high-dimensional embeddings onto a 3D sphere for semantic search, category enrichment, and visualization

hanzo-embedding

Hanzo AI - Embedding generators (native + remote) for text vectorization

vq

A vector quantization library for Rust

c2pa-structured-text

C2PA manifest embedding for structured text formats using ASCII armour delimiters

interpolize

program that scrapes discord, learns how your friends talk, and generates new messages in their collective voice. yes, this is what we're doing with our lives.

semtree-store

Vector store trait and backends (usearch)

vectorlite

A high-performance, in-memory vector database optimized for AI agent workloads

agentroot

Fast local semantic search for codebases and knowledge bases with AI-powered features

holomap

Deterministic UMAP — the bulk, on the boundary. Same input, same params, same seed: bit-identical embeddings.

ferrum-cuda-kernels

Custom CUDA kernels and decode runner for Ferrum inference

minimemory

Embedded vector database library for Rust - like SQLite for vectors

cloakpipe-vector

Vector encryption (ADCPE) for CloakPipe — future scope

ruv-neural-decoder

rUv Neural — Cognitive state classification and BCI decoding from neural topology embeddings

semtree-embed

Embedding trait and backends (fastembed, openai)

javelin-tui

Display and work with Lance matrices

pim-daemon

Background daemon process for the Proximity Internet Mesh

zotron-types

Shared types for the Zotron Zotero bridge (OCR/embedding providers, RPC protocol, PDF evidence)

rlx-sam3

SAM 3 for RLX

fierros-core

Provider-neutral core primitives for Fierros

node2vec-rs

A node2vec implementation in Rust via the Burn tensor framework