-
swiftide-indexing
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
swiftide
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
trueno-rag
Pure-Rust Retrieval-Augmented Generation pipeline built on Trueno
-
ratatoskr-cli
Trace-first, deterministic execution for language model workflows
-
reasonkit-mem
High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion, and semantic retrieval for AI systems
-
helix-db
HelixDB is a powerful, open-source, graph-vector database built in Rust for intelligent data storage for RAG and AI
-
oxirag
A four-layer RAG engine with SMT-based logic verification and knowledge graph support
-
luckyshot
A CLI tool for one-shot code generations using RAG and file watching
-
rank-refine
SIMD-accelerated MaxSim, cosine, diversity (MMR/DPP) for vector search and RAG pipelines
-
gemini-ai
based Gemini AI API, enabling access to advanced natural language processing and multimodal models
-
markdown-harvest
designed to extract, clean, and convert web content from URLs found in text messages into clean Markdown format. Originally created as an auxiliary component for Retrieval-Augmented Generation (RAG)…
-
swiftide-docker-executor
A docker executor for swiftide agent tools
-
deepthought
Functional wrapper around Llama.cpp with Rust Dynamic datatypes and Vector store support for creating RAG applications
-
snippet-agent
Codebase parsing tool. It aggregates code (i.e. RAG) as an input to LLMs
-
context-mcp
MCP server for context storage, text-based retrieval, and temporal tracking with optional persistence
-
langchain-ai-rust
Build LLM applications in Rust with type safety: chains, agents, RAG, LangGraph, embeddings, vector stores, and 20+ document loaders. A LangChain port supporting OpenAI, Claude, Gemini…
-
avocado-cli
CLI tool for AvocadoDB - deterministic context compilation for AI agents
-
reasonkit
The Reasoning Engine — Complete ReasonKit Suite | Auditable Reasoning for Production AI
-
foxstash-core
High-performance local RAG library - SIMD-accelerated vector search, HNSW indexing
-
ares-server
A.R.E.S - Agentic Retrieval Enhanced Server: A production-grade agentic chatbot server with multi-provider LLM support, tool calling, RAG, and MCP integration
-
swiftide-query
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
kiru
Fast text chunking for Rust
-
rag-module
Enterprise RAG module with chat context storage, vector search, session management, and model downloading. Rust implementation with Node.js compatibility.
-
ragit-server
poc server implementation of ragit
-
rusty-page-indexer
A high-performance, reasoning-based RAG indexer in Rust following the PageIndex pattern
-
infernum-server
HTTP API server for local LLM inference
-
phago
Self-evolving knowledge substrates through biological computing primitives
-
tavily
A tiny tool for calling Tavily's REST API in the simplest way!
-
swiftide-integrations
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
rsrvr
Store all your LLM Interactions
-
polarisdb
embedded vector database for local AI and RAG workloads
-
rwkv-agent-kit
high-performance memory system for AI applications with advanced RAG capabilities, vector-graph hybrid storage, and adaptive learning. Built with Rust for scalability and efficiency.
-
swiftide-docker-service
A docker executor for swiftide agent tools
-
swiftide-agents
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
ix-cli
Ixchel CLI
-
phago-agents
Reference agent implementations using Phago biological primitives
-
gatekpr-vector
Qdrant vector database integration for semantic search and RAG
-
phago-rag
Biological RAG — query interface on self-organizing Hebbian knowledge graph
-
avocado-core
Core engine for AvocadoDB - deterministic context compilation for AI agents
-
avocado-server
HTTP server for AvocadoDB - deterministic context compilation for AI agents
-
swiftide-langfuse
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
ragit
git-like rag pipeline
-
rmcp-memex
RAG/memory MCP server with LanceDB vector storage
-
graphrag-core
Core portable library for GraphRAG - works on native and WASM
-
gatekpr-opencode
OpenCode CLI integration for RAG-powered validation enrichment
-
embedvec
Fast, lightweight, in-process vector database with HNSW indexing, metadata filtering, E8 quantization, and PyO3 bindings
-
memvid-ask-model
LLM inference module for Memvid Q&A with local and cloud model support
-
adk-rag
Retrieval-Augmented Generation for Rust Agent Development Kit (ADK-Rust) agents
-
bridge-embex-infrastructure
Infrastructure layer for Embex (observability, retry, config, adapter factory)
-
project-rag
RAG-based codebase indexing and semantic search - dual purpose library and MCP server
-
codanna
Code Intelligence for Large Language Models
-
rs-agent
Lattice AI Agent Framework for Rust - Build production AI agents with clean abstractions
-
memkb
A local AI in memory RAG for markdown files in a folder exposed as MCP
-
vecmindb
High-performance vector database with multiple index algorithms (HNSW, IVF, etc.) and NSGA-II auto-tuning
-
rag-toolchain
native library designed to empower developers with seamless access to common Gen AI workflows
-
llama-core
The core library of LlamaEdge
-
yvdb
Small educational in-memory vector database with REST API, append-only durability, brute-force search, and adaptive heartbeat feat for RAG hallucination mitigation
-
rrag
High-performance Rust framework for Retrieval-Augmented Generation with pluggable components, async-first design, and comprehensive observability
-
ghost-lib
Ghost Librarian — ultra-lightweight local-LLM RAG engine with Context Distillation
-
seekdb-rs
Rust SDK for SeekDB
-
lumen-rag
A modular, database-agnostic RAG framework for Rust supporting MongoDB, Qdrant, and SAP HANA Cloud
-
capsa
A compact, lightweight library for embedding-based document storage and retrieval
-
tarzi
Rust-native lite search for AI applications
-
vecstore
The perfect vector database - 100/100 score, embeddable, high-performance, production-ready with RAG toolkit
-
miyabi-potpie
Potpie AI integration for Miyabi - Neo4j knowledge graph and RAG engine
-
trueno-rag-cli
CLI for Trueno-RAG pipeline
-
phago-viz
Browser-based real-time visualization for Phago colonies
-
stolas
Knowledge and RAG engine - The Prince reveals hidden knowledge
-
phago-llm
LLM integration for Phago semantic intelligence
-
velesdb-wasm
VelesDB for WebAssembly - Vector search in the browser
-
phago-embeddings
Embedding backends for Phago semantic intelligence
-
hallucination-detection
Extremely fast Hallucination Detection for RAG using BERT NER, noun, and number analysis
-
slabs
Text chunking for RAG: fixed, sentence, recursive, and semantic strategies
-
foxloom
Hybrid memory layer with mem0-style semantics on top of foxstash-core
-
zqa
A QA and search program for your Zotero library
-
toon-cli
Command-line tool for TOON-LD format conversion
-
zqa-rag
A retrieval-augmented generation (RAG) crate, used by
zqa -
serdes-ai-embeddings
Embedding models and vector operations for serdes-ai
-
rexis
Agentic AI Framework for Rust with memory-first agents, RAG, and graph orchestration
-
mini_langchain_core
A low-cost, cross-language LangChain implementation
-
gh-docs-download
Efficient CLI tool for downloading documentation from GitHub repositories using git sparse checkout. Perfect for RAG applications and documentation collection.
-
xlsxzero
Pure-Rust Excel parser and Markdown converter for RAG systems
-
helix-metrics
Metrics for HelixDB
-
ix-core
Ixchel core library: registries, validation, sync orchestration, and context building
-
ai00-mem
high-performance memory system for AI applications with advanced RAG capabilities, vector-graph hybrid storage, and adaptive learning. Built with Rust for scalability and efficiency.
-
swiftide-macros
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
oxirs-chat
RAG chat API with LLM integration and natural language to SPARQL translation
-
wg-ragsmith
Semantic chunking and RAG utilities for document processing and retrieval-augmented generation
-
contrag-core
ContRAG - Advanced RAG library for ICP canisters with on-chain storage
-
ragit-pdl
pdl parser for ragit
-
phago-runtime
Colony management, scheduling, and runtime for Phago biological computing
-
ragit-cli
cli argument parser for ragit
-
oxirs-graphrag
GraphRAG: Hybrid Vector + Graph Retrieval-Augmented Generation for OxiRS
-
tavily2
A tiny tool for calling Tavily's REST API in the simplest way!
-
shopify-approver-vector
Qdrant vector database integration for semantic search and RAG
-
ragit-ignore
ignore-parser for ragit
-
kjarni
Cross-platform ML inference engine. Embeddings, classification, reranking, and RAG search
-
kjarni-rag
Kjarni RAG - Retrieval-augmented generation for the Kjarni inference engine
-
spark-bert
Hybrid vector search using an inverted index and BERT embeddings
-
axiom-ai-core
Core abstractions and traits for Axiom
-
ragit-api
api utilities for ragit
-
anchor-chain
A statically typed async framework for building LLM-based applications
-
rrag-graph
Graph-based agent orchestration system built on RRAG framework
-
rexis-rag
Rexis RAG - High-performance Retrieval-Augmented Generation framework with memory-first agents, vector search, and LLM integration
-
archiver
RAG implementation with langchain-rust
-
qrawl
Composable web crawling tools for Rust
-
ragzilla
providing tools for RAG (Retrieval-Augmented Generation) pipelines
-
vector-nexus
Abstraction layer for multiple vector databases with schema generation and RAG support
-
mantr-sdk
Official Rust SDK for Mantr - Deterministic Semantic Memory
-
ragtime
Easy Retrieval Augmented Generation
-
swiftide-core
Fast, streaming indexing, query, and agentic LLM applications in Rust
-
polarisdb-core
Core library for PolarisDB - an embedded vector database for local AI
-
reasonkit-core
The Reasoning Engine — Auditable Reasoning for Production AI | Rust-Native | Turn Prompts into Protocols
-
fa-leiden-cd
Leiden algorithm for community detection in large networks
-
snippet-agent-syntax-queries
Tree-sitter based queries and utilities for snippet-agent (syntax queries)
-
mini-rag
100% Rust implementation of a vector storage database with on disk persistency
-
lumosai-vector-core
Core abstractions and traits for Lumosai vector storage system
-
ragx
AI RAG
-
phago-core
Core traits and types for Phago biological computing primitives
-
helix-macros
Proc macros for HelixDB
-
morgana-rust
A general purpose RAG agent
-
rustpotion
Blazingly fast word embeddings with Tokenlearn
-
cortex-sources
Ready-made source implementations for various data inputs in the Cortex ecosystem
-
pankosmia_rag_chat
A RAG chatbot library, leveraging RTEN, for pankosmia desktop applications
-
epsilla
SDK
-
blazegraph-io-core
Core library for semantic document graph processing - coming soon
-
ragkit
Developer platform to build RAG applications
-
molina
Rust/Python Synthetic Integration for an agentic-LLM approach to build a research agents for local knowledge representation
Try searching with DuckDuckGo.