Skip to content

RAG & Retrieval

40 entries

Tools and patterns for retrieval-augmented generation, vector search, embeddings, and knowledge retrieval pipelines.

Agent Harness Pattern

trial
pattern

Architectural pattern where all non-model code surrounding an LLM (planning, tools, sub-agents, context management) is p...

Agent Memory as Infrastructure

assess
pattern

Treats AI agent memory as first-class infrastructure with lifecycle hooks, layered storage, async writes, and active mai...

Agent Skills Specification

adopt
open-source

An open standard for packaging reusable procedural knowledge as markdown files that AI coding agents can discover, load,...

AGENTS.md

trial
open-source

An open cross-platform specification for a repository-root Markdown file that provides AI coding agents with project con...

Agno

assess
open-source

Open-source Python framework, stateless FastAPI runtime (AgentOS), and control-plane UI for building and operating multi...

AnythingLLM

assess
open-source

A self-hosted AI chat application with workspace-isolated RAG, a zero-config desktop app, and multi-provider LLM support...

BMAD Method

assess
open-source

A framework for structuring AI-assisted development using six specialized agent personas and versioned documentation art...

ChromaDB

trial
open-source

Open-source AI-native vector database designed for prototyping and RAG applications, with a 2025 Rust-core rewrite addin...

Claude Northstar

assess
open-source

MIT-licensed CLAUDE.md harness that bootstraps any git repo for autonomous goal-oriented agent operation, replacing sequ...

Cloudflare Workers AI

assess
vendor

Serverless GPU inference platform running 50+ open-weight models on Cloudflare's global network, with pay-per-token pric...

Cognee

assess
open-source

Open-source Apache-2.0 knowledge engine for AI agent memory that combines vector search and graph databases to ingest 30...

DeepEval

trial
open-source

Open-source Apache-2.0 LLM evaluation framework by Confident AI with 50+ metrics spanning RAG, agents, multi-turn conver...

Dify

assess
open-source

An open-source platform for building LLM-powered applications via a visual drag-and-drop workflow builder with built-in...

Flowise

assess
open-source

A lightweight visual builder for constructing AI chatbots and RAG pipelines using drag-and-drop LangChain components, de...

GitNexus

assess
open-source

Open-source code intelligence engine that indexes repositories into a precomputed knowledge graph and exposes 16 MCP too...

Haystack (deepset)

trial
open-source

Open-source Python AI orchestration framework by deepset for building production-ready LLM applications, RAG pipelines,...

Hippo Memory

assess
open-source

Zero-dependency TypeScript CLI and npm package implementing biologically-inspired AI agent memory with exponential decay...

InfiniFlow

assess
vendor

Shanghai-based AI infrastructure company behind RAGFlow (78.5k+ star open-source RAG engine) and Infinity, an AI-native...

Langflow

assess
open-source

A visual IDE for building AI agents and RAG applications with native LangGraph integration for stateful multi-agent work...

Langfuse

trial
open-source

Open-source LLM engineering platform (MIT-licensed, 21k+ GitHub stars) covering observability traces, evaluation, prompt...

LlamaIndex

trial
open-source

Open-source MIT-licensed data framework for building RAG and document agent applications on top of LLMs, with 38k+ GitHu...

MemPalace

assess
open-source

Local-first open-source AI memory system using a hierarchical palace metaphor (Wings/Rooms/Halls) over ChromaDB vector s...

Milvus

trial
open-source

Apache-2.0 distributed vector database for billion-scale similarity search, built for cloud-native Kubernetes deployment...

Open WebUI

trial
open-source

A self-hosted, provider-agnostic web interface for LLMs with built-in RAG, MCP support, RBAC, and Ollama integration for...

OpenSpec

assess
open-source

A CLI framework that adds a specification layer to AI-assisted development with structured proposals, specs, and task br...

OpenViking

assess
open-source

A context database by ByteDance that organizes AI agent memory via a virtual filesystem with tiered content loading to r...

Perplexity AI

assess
vendor

AI-native answer engine and agentic browser company pivoting from AI-assisted search to autonomous multi-step task execu...

RAG Pipeline

assess
pattern

Retrieval-Augmented Generation pattern that grounds LLM responses in retrieved documents to reduce hallucination and ena...

RAGAS

trial
open-source

Open-source Apache-2.0 evaluation framework for RAG pipelines and LLM applications by ExplodingGradients (YC W24), provi...

RAGFlow

assess
open-source

Open-source Apache-2.0 RAG engine by InfiniFlow specializing in deep document understanding (OCR, layout analysis, table...

Retrieval-Augmented Generation (RAG)

adopt
pattern

An LLM inference pattern that injects relevant documents retrieved from an external corpus into the model's context at q...

Spec-Driven Development

trial
open-source

Development pattern where structured specification documents are written before code and serve as the primary input for...

Supabase

trial
vendor

Open-source Firebase alternative providing managed PostgreSQL, authentication, storage, and serverless Edge Functions as...

Thunderbolt

assess
open-source

Open-source, self-hosted enterprise AI client by MZLA Technologies (Mozilla) offering multi-platform native apps, multi-...

TruLens

assess
open-source

Open-source MIT-licensed LLM evaluation and tracing framework by TruEra, now maintained by Snowflake, combining OpenTele...

VectorDBBench

assess
open-source

Open-source benchmarking tool for vector databases, covering 30+ databases with CLI and visual interface; maintained by...

Volcano Engine

assess
vendor

ByteDance's enterprise cloud platform offering AI services, the Doubao LLM family, VikingDB vector database, and agent t...

Weaviate

assess
vendor

Vector database supporting hybrid vector-keyword search, automatic vectorization, and multi-tenancy for AI-native applic...

Weaviate Engram

assess
vendor

Memory and context layer for AI agents built on Weaviate, organizing persistent semantic memory by topic across sessions...

Zilliz Cloud

trial
vendor

Fully managed vector database service built on Milvus, operated by Zilliz with enterprise-grade SLA (99.95%), SOC 2 Type...

Related Reviews

Related Topics