Open-source tools for Knowledge & documents

Documents, notes, knowledge bases and persistent memory.

Start with the documents you already use. Compare supported file types, where indexing happens, and whether answers point you to the original passage.

93 projects

agent-cockpit chutingyean · AGPL-3.0
A local whiteboard and MCP server where AI coding/research agents log every claim and the exact code run that produced it, so if the underlying code changes, the claims…
agent-me jzjzzzzzzz · MIT
It turns your own notes, memories, projects and past decisions into an inspectable AI agent that keeps learning how you think and can answer questions with your context.
agent-memory tigerless-labs · MIT
Gives AI coding agents a shared long-term memory kept as plain Markdown, with local ranked retrieval and a background layer that tidies what has been learned, no API…
agent-vision-toolkit anionex · MIT
Gives text-only AI coding agents the ability to understand images by handling image Q&A, screenshot OCR, and UI recognition outside the model itself.
ai-agent-book bojieli · Apache-2.0
A free open-source book, translated into 15 languages including English, that teaches how AI agents actually work with 109 runnable experiments.
ai-engineering-course amitshekhariitbhu · Apache-2.0
A free, complete course that teaches AI engineering step by step, from machine learning basics through building and evaluating LLM-based agents.
ai-engineering-from-scratch rohitg00 · MIT
A free, open-source course that walks you through building modern AI systems from scratch, 511 lessons spanning LLMs, RAG, agents and transformers.
ai-engineering-hub patchy631 · MIT
A collection of in-depth, hands-on tutorials teaching how to build with LLMs, RAG pipelines, and real-world AI agent applications.
ai-engineering-lab zorost · MIT
Zorost Intelligence AI Lab open-sourced a free, self-paced 24-week AI engineering course that takes a beginner from Python to production LLM/RAG/agent systems, with 43…
ai-memory akitaonrails · MIT
A tool that gives AI coding assistants long-term memory and lets you switch between different AI agent vendors mid-project without losing context.
ai-system-design amitshekhariitbhu · Apache-2.0
A free, complete guide that teaches how to design real AI systems, step by step, from LLM inference and RAG to AI agents, guardrails, and cost optimization.
ailearningguide fazmin · MIT
A desktop app that teaches how modern AI works through 51 hands-on labs covering tokens, transformers, RAG, agents and fine-tuning, with plain-language lessons next to…
auto-ontology-mcp gogoymh · Apache-2.0
Share receipts, notes, papers or screenshots with your AI assistant and it extracts the facts into a searchable personal knowledge base (originals kept in your own…
book-to-skill virgiliojr94 · MIT
Turns any PDF or EPUB technical book into a structured AI agent skill (chapter files, glossary, cheatsheet) that Claude Code or Copilot can load on demand instead of…
briefd ismailperim · Apache-2.0
A self-hosted tool that packages your team documentation into small, relevant bundles and serves them to coding agents over MCP so they stop guessing at context.
bullflow jaikydota · MIT
An open-source, self-hostable AI agent that turns a company's internal documents into marketing content and auto-publishes it across 17 platforms (Instagram, LinkedIn,…
carrel fengzhenfei · MIT
Carrel is a self-hosted knowledge base for AI agents: it automatically parses, indexes and builds knowledge graphs from your documents (PDFs, Word, slides, code,…
claude-mem thedotmack · Apache-2.0
Gives any AI coding agent persistent memory across sessions: it captures what the agent did, compresses it with AI, and feeds the relevant parts back into future…
claude-obsidian agricidaniel · MIT
claude-obsidian turns Claude Code into a self-organizing AI second brain for Obsidian, automatically reading, linking, and filing anything dropped into it as connected…
claude-seo agricidaniel · MIT
A free, open-source SEO skill for Claude Code with 26 sub-skills and 19 sub-agents that audits a site for technical SEO, schema, E-E-A-T and also AI-search citability.
cloudflare-os cloudflare · Apache-2.0
An open-source AI operating system from Cloudflare that lets anyone at a company ask an agent to build and safely share small personal apps - like slide decks or…
code-graph-rag vitali87 · MIT
code-graph-rag builds a knowledge graph of a codebase so an AI assistant can query, understand, and edit it more accurately.
codebase-memory-mcp deusdata · MIT
An MCP server that indexes an entire codebase into a queryable knowledge graph in milliseconds, so AI coding agents can answer structural questions using ~120x fewer…
contextcraft khanhtq29vn · MIT
A tool that intelligently compresses a whole codebase down to fit an LLM context window, keeping the most relevant code first.
daidocs kerneta · Apache-2.0
Gives your AI assistant a memory that lives as plain .dai files on your own disk, so you can open, grep, and keep it instead of trusting a black-box memory feature.
deeptutor hkuds · Apache-2.0
DeepTutor is an open-source AI tutoring platform that turns your own books, notes, and courses into a personalized learning companion that remembers your progress over…
deskcommcrm melgarafael · MIT
A self-hosted, open-source CRM where AI agents handle WhatsApp sales conversations - qualifying leads and closing chats - as an open alternative to Kommo, Octadesk and…
digup arahim3 · MIT
A macOS menu-bar app that lets you search your entire Mac by meaning, not just filename, across photos, PDFs, recordings, videos and code, running fully on-device via a…
docflare-ai p10node · MIT
Docflare AI lets you drop one script tag into any documentation site to get an AI chatbot that answers questions with cited sources, running entirely on Cloudflares…
dsh-vision-toolkit anionex · MIT
dsh-vision-toolkit adds a real vision toolbox to text-only AI agents: paste an image for recognition, multi-image Q&A, screenshot-to-UI restoration, and pixel-level…
easyread edwardxlai · MIT
easyread is a local desktop app that translates English research papers into natural Chinese, keeps the original text side-by-side, and lets you chat with an AI about…
echomind nirbhay41120003 · MIT
A local-first assistant that transcribes your speech live and lets you ask a private RAG chatbot questions grounded in what you have actually said, entirely on your…
embedflow arnsri33 · AGPL-3.0
Lets teams switch to a better embedding model for their AI search or RAG system without taking anything offline while re-indexing.
frametell sitor-ai · AGPL-3.0
A local-first desktop app where an AI agent turns one sentence or a document into a narrated, illustrated explainer video you approve step by step.
garden-skills conardli · MIT
A ready-made library of skills that plug into AI coding agents to do things like generate images, build web pages, and turn sources into polished articles.
gitaviswa himanshumohanty-git24 · MIT
GitaVisva turns the Bhagavad Gita into an explorable 3D knowledge graph with 20 classical commentaries, and lets you ask it questions in plain English that it answers…
graphicle graphicle-ai · Apache-2.0
Maps your codebase into a local graph and remembers your project's docs and past agent sessions, so your coding agent gets cited file-and-line answers instead of…
graphify graphify-labs · Apache-2.0
Turns any codebase, plus its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph that AI coding agents like Claude Code, Cursor, Codex, and Gemini…
halofy halofyai · AGPL-3.0
An open-source governance layer that gives every AI agent in an organization one identity and policy model over shared context, with provenance, audit logs and…
headroom headroomlabs-ai · Apache-2.0
Headroom shrinks everything an AI agent reads (logs, files, RAG chunks, tool output) before sending it to the LLM, cutting token costs without changing the answers.
hello-agent-system heaven999b · MIT
A free, hands-on 17-lesson course that walks you through building a production AI agent system from scratch, covering tools, reliability, security, evals, and cost.
hindsight vectorize-io · MIT
Hindsight is an open-source agent memory system that helps AI agents learn from experience over time instead of just recalling past conversations.
inkdoc abdoslamb · MIT
A free desktop app that drops in any PDF, Word doc, webpage or image and converts it to clean Markdown locally, so it is ready to feed into an AI tool or notes system.
issue-rag zaxiu88888 · MIT
A support assistant that answers questions from a repo's GitHub issues using RAG, and instead of just claiming it works, publishes a hand-reviewed eval showing exactly…
jev-chat-jarvis jev-chat · MIT
An Android app that reads your on-screen chat via accessibility service, uses an LLM to judge intent and draft ranked reply options, and fills your chosen one into the…
jev-doc-search vectifyai · Apache-2.0
A technique for finding the exact page that answers a question in a 300-page report by having an LLM make a series of small multiple-choice decisions down a document…
jevcrawl rayenmlayeh · Apache-2.0
A small MCP server/CLI that crawls websites for AI agents and returns only the passage that actually answers the question, instead of whole pages.
jevmem avinash-jetwani · MIT
jevmem automatically saves the decisions, rules, and dead ends from your Claude Code sessions to a file in your repo, so the AI remembers them next time instead of…
kancelaria-lex ai4charitypl · MIT
An open-source AI tool for Polish lawyers that reads case files and answers questions with citations traced to the exact source sentence, engineered so it cannot invent…
keelflow perruer · Apache-2.0
A self-hosted visual builder for AI agents and LLM workflows, forked from the abandoned Flowise project with known vulnerabilities patched and all commercial-license…
kenfold jeonjw85 · MIT
A self-hosted memory server that lets Claude Code, Codex, OpenCode and ChatGPT share one memory over MCP, so a decision made in one agent is already known in the next.
kensaku yjid · MIT
A free, open-source file launcher that lets you instantly search inside documents, code, and screenshots, using OCR and semantic search, entirely on your own machine.
lemmalog jordyzomer · MIT
A Rust Datalog engine that gives LLM agents a verifiable, provenance-tracked memory, with an MCP server so tools like Claude Code can use it as a shared long-term brain.
lifeboat johnpsasser · MIT
Lifeboat runs a local AI model plus a 200 GB offline knowledge library entirely on one Mac, so you can ask practical questions like how to treat a wound or fix a…
llm-hallucination-detector syasj · MIT
Color-codes an AI chat answer token by token based on model confidence, and separately checks each factual claim against your own source documents, flagging guesses vs.…
llm-master youngyangyang04 · MIT
A free, structured roadmap of 150+ tutorials taking developers from their first LLM API call through building production-ready RAG pipelines and AI agents.
macro macro-inc · AGPL-3.0
An open-source all-in-one team workspace where AI agents and a shared memory layer tie together email, chat, docs, tasks, calls and CRM.
manga-generator stockedge · MIT
Hands a novel or short story to an AI coding agent and gets back a finished manga: script, AI-generated artwork, lettering and a PDF, with a real published example on…
markitdown microsoft · MIT
Converts PDFs, Word, PowerPoint, Excel, images and audio into clean Markdown so the text is ready to feed into an LLM.
memoket-kite memoket · Apache-2.0
An open-source memory engine for AI agents that keeps what it is told as traceable, cited facts instead of fuzzy vector matches, and answers questions with an auditable…
mirofish 666ghj · AGPL-3.0
An open-source swarm-intelligence engine that coordinates many LLM agents together to make predictions.
mnemos-mcp riley-coyote · Apache-2.0
Mnemos gives an AI coding agent a memory of its own: it writes and keeps notes about you and your work in its own words, then reads them back at the start of every new…
ms-cookbook modelscope · Apache-2.0
A free, open-source cookbook that walks developers from picking an open-source model through inference, fine-tuning, evaluation, RAG, and agents to shipping a real AI…
nuphus-mcp mrpulor-gh · MIT
Gives AI agents actual computer-use capability: they can see your screen and control windows, mouse, keyboard, and Chrome through a lightweight local server.
octop tencentcloud · MIT
Octop is a self-hosted AI assistant you run on your own infrastructure, built to support multiple users and multiple agents at once.
ods osmantic · Apache-2.0
Installs and connects everything needed to run AI locally so you get a private AI server without assembling the pieces by hand.
OG Converter dr-at0mic · GPL-3.0-or-later
Office workers can turn Word, Excel and PowerPoint files into PDFs, merge or split PDFs, and password-protect documents without uploading them to a website. Students…
okf-agent-memory okf-memory · MIT
Gives AI agents a lasting, version-controlled memory stored as plain Markdown files in your own repo, with fast local BM25 search and no vector database or embedding…
openhuman tinyhumansai · GPL-3.0
OpenHuman is an open-source personal AI assistant that builds a local, private memory of your life and work, then uses that memory to research, automate tasks, and…
openviking volcengine · AGPL-3.0
OpenViking gives AI agents a filesystem-style long-term memory, storing memories, docs, and skills under a viking:// protocol with tiered loading, and its own published…
opspilot-ai router0824 · MIT
Turns meeting notes, documents and project activity into structured decisions, tasks and risks using an LLM (OpenAI, Azure OpenAI or DeepSeek), with a human-approval…
pageindex vectifyai · MIT
An open-source document index that lets an LLM retrieve the right passages from long documents by reasoning over structure instead of vector similarity search, skipping…
pagesift yolow92 · Apache-2.0
A fast, memory-efficient tool that turns any website or document into clean text and structured data an AI system can actually use, as an alternative to existing…
papergraph-mcp lotchuazzz-crypto · MIT
An MCP server that extracts results and proof evidence from math papers so AI agents can plan reading order without guessing.
personal_external_brain chenkanglin198904 · MIT
A local-first tool that turns your notes, PDFs, web pages and audio/video into a private knowledge graph, and is designed to say I do not know rather than guess.
ppt-master hugohe3 · MIT
ppt-master uses AI to turn a document or topic into a real, editable PowerPoint deck, complete with charts, animations, and narrated speaker notes.
ragflow infiniflow · Apache-2.0
RAGFlow is an open-source RAG engine that combines retrieval with agent capabilities to give LLMs better context for answering questions over your own documents.
recollect mikek184 · Apache-2.0
A self-hosted, Rust-built memory and MCP coordination layer that gives coding agents persistent context across repos and sessions.
researchpilot renfei421 · MIT
An AI research agent that checks claims against real literature and keeps a persistent workspace of prior work, instead of just summarizing a paper once.
rhizome aliengiraffe · MIT
Rhizome lets your Claude Code, Codex, and OpenCode agent sessions discover each other and exchange messages over MCP, so parallel agents (or a colleague's agents) can…
ruflo ruvnet · MIT
An open-source tool that lets you coordinate teams of AI agents working together on a task, with memory and native integration into Claude Code and Codex.
semantica semantica-agi · MIT
A graph-based infrastructure layer that gives AI systems structured context and an audit trail for their reasoning.
shared-memory-vault songs-aaa · MIT
Turns a plain cloud-synced Markdown folder into a shared knowledge base every AI agent and every device can read and update consistently, with conflict handling and no…
skills google · Apache-2.0
Google's official pack of ready-made Agent Skills that AI coding agents can install in one command to instantly gain Cloud setup, RAG, and agent-deployment know-how…
sno-station sno-ai · Apache-2.0
A local, no-cloud platform that lets Claude Code and Codex agents share encrypted memory and message each other while working together on the same machine.
sourcelens msmahdinejad · MIT
SourceLens turns a folder of documents into a research workspace: ask questions and get cited answers, or have it generate a podcast, a PowerPoint, or a video from the…
sparky anisayari · MIT
A free, open-source private AI assistant for Windows that runs entirely offline: chat like ChatGPT, see images, generate pictures and videos with sound, search your own…
turbovec ryancodrai · MIT
A fast, compressed vector index (built on TurboQuant) for searching embeddings at scale, the kind of component that powers RAG and semantic-search systems.
typesafe-computer-use awlevin · MIT
A macOS tool that drives your computer toward a plain-English goal by reading the screen and picking the next click with a cheap classifier instead of a big AI model,…
univer dream-num · Apache-2.0
An open-source, all-in-one office runtime (spreadsheets, docs, slides, PDFs) designed to be the workspace AI agents actually operate inside.
voicemem xzf-thu · Apache-2.0
Gives voice assistants a persistent memory that tracks facts and emotional context across conversations, so the assistant gradually gets to know each user, at low…
whirl whirlchat · MIT
An open-source, self-hostable AI chat app that lets you talk to every major AI model in one place, with real memory across chats and documents you can keep editing.
xerj xerj-org · Apache-2.0
One command indexes your code, docs, logs and PDFs so AI agents can search and remember your data using far fewer tokens than grep, while staying Elasticsearch…