Memory & Retrieval Projects in AI & Machine Learning

AI & ML, distilled: frameworks, models, datasets and tools with practical guidance, evals and workflows to ship reliable, real-world intelligence.

172 repositories in this collection

Choose a direction

Explore by topic

Open a topic to see its stories, then follow the trail.

Repository stories

No published repository stories here yet.

Tracked projects to explore

Agent memory and retrieval: strategy, changing information, operational cost and latency.

These projects are selected from Geekist Stars or matched by GitHub topic tags. They are not necessarily reviewed or recommended by Geekist.

31 tracked projects
  • 1Panel-dev/MaxKBMatched GitHub topic

    🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

  • BoundaryML/bamlResearch selection

    The programming language for agents

  • buildingjoshbetter/TrueMemoryResearch selection

    The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude…

  • Cinnamon/kotaemonMatched GitHub topic

    An open-source RAG-based tool for chatting with your documents.

  • codexu/note-genMatched GitHub topic

    Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.

  • dair-ai/Prompt-Engineering-GuideMatched GitHub topic

    🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

  • FlowiseAI/FlowiseMatched GitHub topic

    Build AI Agents, Visually

  • infiniflow/ragflowResearch selection

    RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

  • ItzCrazyKns/VaneMatched GitHub topic

    Vane is an AI-powered answering engine.

  • julep-ai/julepMatched GitHub topic

    Julep — durable, composable AI agents. Flows that crash and resume, retry safely, and explain every step.

  • kevin-hs-sohn/hipocampusResearch selection

    Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.

  • khoj-ai/khojMatched GitHub topic

    Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or loca…

  • labring/FastGPTMatched GitHub topic

    FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and…

  • llmware-ai/llmwareMatched GitHub topic

    Unified framework for building enterprise RAG pipelines with small, specialized models

  • Mintplex-Labs/anything-llmMatched GitHub topic

    Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

  • MODSetter/SurfSenseMatched GitHub topic

    Air-gapped, privacy-focused, open-source NotebookLM alternative. AI agent that researches, transforms, and edits your documents. Join our Discord: https://disco…

  • NevaMind-AI/memUResearch selection

    Personal memory across agents

  • NirDiamant/agents-towards-productionMatched GitHub topic

    End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

  • open-webui/open-webuiMatched GitHub topic

    User-friendly AI Interface (Supports Ollama, OpenAI API, …)

  • palico-ai/palico-aiMatched GitHub topic

    Build, Improve Performance, and Productionize your AI Application

  • pingcap/autoflowMatched GitHub topic

    pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

  • ruvnet/rufloMatched GitHub topic

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive me…

  • ScrapeGraphAI/Scrapegraph-aiMatched GitHub topic

    Python scraper based on AI

  • screenpipe/screenpipeMatched GitHub topic

    YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agent…

  • supermemoryai/supermemoryResearch selection

    Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

  • technovangelist/llm_dataset_builderResearch selection
  • The-Vibe-Company/quivrMatched GitHub topic

    An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, model…

  • umbertogriffo/rag-chatbotMatched GitHub topic

    RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

  • unclecode/crawl4aiMatched GitHub topic

    Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this…

  • Unstructured-IO/unstructuredMatched GitHub topic

    Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats fo…

  • VectifyAI/PageIndexResearch selection

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

1 resource collection

Collections are grouped separately from individual projects.

Need setup help? Geekist Concierge can help for as little as $20

Get Geekist in your inbox

    Choose your newsletters. Confirm your email to subscribe.

    Choose your newsletters

    Read the privacy policy