The best open-source RAG tools in 2026
The best open-source RAG tools right now are Qdrant, pgvector and Docling, out of 55 we have reviewed. Each is ranked by our rating, with its price, our verdict and who it suits.
By ReviewRamble editors · Updated Nov 18, 2026 · How we review
How we ranked: by our rating out of 5, from reviews built on each product's own pricing, documentation and policies plus independent benchmarks where they exist, each checked on the date shown in the review. We take no affiliate commission.
- 1
Filtered vector search done properly makes Qdrant the open-source database to beat for production RAG, as long as someone locks down a server that ships open.
Best for: Teams running production RAG or search that need fast filtered vector queries.
Price: Free and open source under the Apache 2.0 licence. Qdrant Cloud has a free 1 GB cluster, then usage-based billing; Premium, Hybrid and Private Cloud are priced by sales.
Read our Qdrant review4.7/5 - 2
For most teams already on Postgres, a dedicated vector database is extra infrastructure that pgvector makes unnecessary.
Best for: Teams already on Postgres building RAG or semantic search over a few million vectors.
Price: Free and open source under the PostgreSQL License. The only cost is the Postgres instance you already run, or a larger one.
Read our pgvector review4.6/5 - 3
Docling is the open-source parser that gets tables right, and the one whose security releases you cannot afford to skip.
Best for: Teams building self-hosted RAG over PDFs and Office documents with complex tables.
Price: Free and open source under the MIT license.
Read our Docling review4.5/5 - 4
Hindsight is the most capable open-source agent memory server you can run today, with nothing held back from the MIT licence, though its benchmark lead rests on numbers its own paper's co-authors reproduced.
Best for: Teams that want graph, temporal and vector memory in one self-hostable server without an open-core feature split.
Price: Self-hosted server free under MIT. Hindsight Cloud is usage-billed with $5 of free credit: retain $10 per million tokens, recall $0.75 per million tokens, reflect $0.05 per call, storage $0.25 per million tokens a month after the first 30 days. Enterprise (BYOC, on-premises, SSO) by quote.
Read our Hindsight review4.4/5 - 5
Built for billions of vectors and priced in operational effort; below a few hundred million, it is more database than most teams need.
Best for: Platform teams running vector search at hundreds of millions to billions of vectors.
Price: Free and open source under Apache 2.0. Zilliz Cloud is the managed service: free tier (5 GB, five collections), Dedicated from $63, $16 or $5 per million 768-dimension vectors a month (performance, capacity or tiered), Enterprise from $197 a month, Business Critical by quote.
Read our Milvus review4.4/5 - 6
The Python scraper to reach for when a site fights back, provided you are comfortable with what its anti-bot features are for.
Best for: Python developers and data teams scraping sites that change often or block simple clients, including for agent and RAG pipelines.
Price: Free under the BSD-3-Clause licence. Proxies, CAPTCHA services and hosting are your own cost.
Read our Scrapling review4.4/5 - 7
For agents whose facts change over time, Graphiti is the open-source memory layer to beat, provided you will run a graph database and pay for LLM extraction on every write.
Best for: Teams building long-running agents that must remember changing facts about users, accounts or the world.
Price: Free and open source under Apache 2.0. You supply the graph database and pay for LLM and embedding calls during ingestion.
Read our Graphiti review4.3/5 - 8
Still a deep toolkit for document-heavy RAG, but its maker now says plainly that the framework is no longer its priority.
Best for: Python developers building RAG or document agents over large, varied data sources.
Price: Framework free under MIT. LlamaParse (paid cloud): Free with 10k credits, Starter $50/month (40k credits), Pro $500/month (400k credits), Enterprise custom; 1,000 credits = $1.25.
Read our LlamaIndex review4.3/5 - 9
Marker turns hard PDFs into usable Markdown better than any other open pipeline its makers measured, though the weights licence puts a revenue ceiling on that freedom.
Best for: RAG and data teams converting large volumes of complex or scanned PDFs on their own hardware.
Price: Code free under Apache 2.0; weights free below $5M revenue and funding, commercial licence above. Hosted Datalab API: Convert $4 per 1,000 pages (fast or balanced); Team plan $400/month.
Read our Marker review4.3/5 - 10
MinerU pairs one of the most accurate open document models with a busy, well-documented toolkit, though its licence is no longer plain open source and its APIs keep moving.
Best for: RAG and data teams parsing large, mixed collections of PDFs and Office files on their own hardware, who can accept an attribution clause.
Price: Free under the MinerU Open Source License (Apache 2.0 with added terms); a separate commercial licence is required above 100 million monthly active users or $20 million monthly revenue.
Read our MinerU review4.3/5 - 11
Repomix packs a small repo into one prompt better than anything else, and becomes the wrong tool the moment the repo outgrows the context window.
Best for: Developers who want to hand a small or medium repo to a chat model in one file.
Price: Free and open source (MIT). The web version at repomix.com is free; there is no paid tier.
Read our Repomix review4.3/5 - 12
Still the strongest open crawler for LLM pipelines, but its Docker server's 2026 security record rules out exposing it without hardening.
Best for: Python teams that want a self-hosted crawler for RAG or agents without per-page costs.
Price: Library and Docker server free (Apache 2.0 plus an attribution clause). Crawl4AI Cloud: 1,000 free credits a month; Starter $10 a month for 10,000 credits.
Read our Crawl4AI review4.2/5 - 13
A hosted web layer for agents that earns its fee; the open-source edition is a starting point, not a substitute.
Best for: Developers who want a managed API to turn websites into LLM-ready data.
Price: AGPL-3.0 open source. Cloud: Free 1,000 credits/month; Hobby $19, Standard $99, Growth $399, Scale $749 a month; Enterprise custom.
Read our Firecrawl review4.2/5 - 14
A framework for people who want to read their RAG system rather than trust it, at the price of writing more of the wiring themselves.
Best for: Engineering teams building maintainable production RAG and agent pipelines in Python.
Price: Free and open source under the Apache 2.0 licence. deepset Studio is free for one user; the Haystack Enterprise Platform is custom-priced.
Read our Haystack review4.2/5 - 15
OpenWiki is the first agent-written docs tool that knows which of its own sentences have gone stale, and that is what makes generated documentation worth keeping.
Best for: Teams whose coding agents keep rediscovering the same codebase and who want a wiki that updates itself in pull requests rather than drifting.
Price: Free and open source (MIT). You pay your model provider directly.
Read our OpenWiki review4.2/5 - 16
pdf-inspector should be the first stop in any PDF pipeline, because the cheapest OCR call is the one you never make.
Best for: Engineers building RAG or agent pipelines over mostly digital PDFs who want local, fast extraction and a cheap scan-or-text decision.
Price: Free under the MIT licence.
Read our pdf-inspector review4.2/5 - 17
PyLate is the practical way to train and serve ColBERT-style retrievers in Python today, provided you accept that multi-vector search costs more storage and a smaller community than ordinary embeddings.
Best for: Search and RAG engineers who want to train or deploy ColBERT-style retrievers in Python without adopting research code.
Price: Free and open source (MIT). You pay only for the GPUs used to train and encode, and for the disk the token-level index occupies.
Read our PyLate review4.2/5 - 18
Hybrid keyword-and-vector search is still Weaviate's best argument, but its newest operational features now sit behind a licence key.
Best for: Teams building search or RAG where exact keywords and semantic similarity both matter.
Price: Core is BSD-3-Clause; some enterprise features need a paid licence key. Weaviate Cloud: Free (100,000 objects), Flex pay-as-you-go with a $45/month minimum, Premium from $400/month on a prepaid contract.
Read our Weaviate review4.2/5 - 19
Quick to embed and cheap to host for read-heavy RAG, though nothing has been tagged since May 2026.
Best for: Developers prototyping RAG or running small to mid-size vector search.
Price: Free and open source under Apache 2.0. Chroma Cloud: Starter $0 plus usage with $5 credits; Team $250/month plus usage; Enterprise custom. Writes $2.50/GiB, storage $0.33/GiB-month.
Read our Chroma review4.1/5 - 20
Honcho is the memory layer to choose when you want an agent to understand a person rather than look facts up, and its AGPL licence is the first thing your lawyers will ask about.
Best for: Teams building tutors, companions or support agents that must understand individual users over many sessions.
Price: Server free under AGPL-3.0. Managed service: $2.00 per million tokens ingested (context reads unlimited, dreaming included); chat queries from $0.001 (minimal) to $0.50 (max) each, $0.01 by default. $5 in credits for new accounts and $5 a month once a card is added; Enterprise by quote.
Read our Honcho review4.1/5 - 21
The default graph store when your RAG or agent memory genuinely needs relationships, but the free edition stops at one server and most RAG does not need a graph at all.
Best for: Teams whose RAG or agent-memory questions depend on relationships between entities, and who need a proven graph store.
Price: Community Edition free under GPLv3. Enterprise by quote. AuraDB: Free tier; Professional $0.09/GB/hour (1 GB minimum); Business Critical $0.20/GB/hour (2 GB minimum).
Read our Neo4j review4.1/5 - 22
Open Ontologies brings Terraform-style plans and checkable proofs to ontology changes, and it is unusually honest about where its guarantees stop.
Best for: Knowledge-graph teams who change a production OWL or RDF ontology regularly and must show a reviewer or auditor what each change entailed.
Price: Free and open source (MIT). Tesseract Semantics sells a hosted platform and enterprise support at unpublished prices, and offers a no-cost one-month evaluation to its next ten enterprise teams.
Read our Open Ontologies review4.1/5 - 23
Xberg opens almost any file from almost any language you write in, and that reach comes with a large surface to secure.
Best for: Teams outside Python that need one embeddable parser for a wide mix of file types, with OCR they can swap.
Price: Free under the MIT licence. Xberg Pro and Enterprise (managed or self-hosted backends) are sold through a design-partner programme; prices are disclosed only on application.
Read our Xberg (formerly Kreuzberg) review4.1/5 - 24
Fast enough on plain CPUs to change the economics of bulk OCR, provided your documents are clean print and your company fits under the licence's $20M line.
Best for: Startups and research teams that need to OCR large volumes of clean printed documents cheaply on CPUs.
Price: Code Apache-2.0; weights free under a modified OpenRAIL-M for research, personal use and companies under $20M funding or revenue; commercial licence from Datalab otherwise.
Read our Indra OCR review4.0/5 - 25
When your embeddings live next to images, video or training data, LanceDB removes the separate database entirely, though busy multi-user search is not what the free library is built for.
Best for: Teams working with multimodal or training data who want vector search without running a server.
Price: Free and open source under Apache 2.0. LanceDB Enterprise is sold on annual commitments; AWS Marketplace lists a $60,000 12-month commitment, with private offers by quote.
Read our LanceDB review4.0/5 - 26
Maxun is the scraper to hand a non-programmer, because a recorded robot keeps running without an LLM bill, though the anti-bot muscle hard sites need lives in the paid cloud.
Best for: Operations and research teams that need recurring tables from the same websites and would rather record clicks than write scraping code.
Price: Free to self-host under AGPLv3. Maxun Cloud: 7-day trial without a card (5 pages or 50 rows, 2 robots); Starter $19/month for 5,000 credits; Growth $99/month for 100,000 credits; Premium priced on request. Subscriptions are not refunded.
Read our Maxun review4.0/5 - 27
Mem0 is still the quickest way to give an agent a memory, but the open-source SDK is increasingly the trial version of a platform that keeps graph memory and the best benchmark scores for itself.
Best for: Developers adding cross-session user memory to chatbots and agents.
Price: Open-source SDK free under Apache 2.0. Platform: Free (10,000 adds and 1,000 retrievals a month for the first 30 days with model calls included, then 50,000 adds and 10,000 retrievals with your own LLM key, usage-billed beyond that up to a cap you set); Custom plans by quote. The earlier $19 Starter and $249 Pro plans are no longer listed.
Read our Mem0 review4.0/5 - 28
A finished document-to-answer product you can run on one server, whose security record says it belongs behind a VPN rather than on the open internet.
Best for: Teams that want a self-hosted document Q&A and knowledge assistant without building a pipeline.
Price: Free and open source under the Apache 2.0 licence. InfiniFlow also sells RAGFlow Cloud: Free (500 credits a month, no API key), Starter $29/month and Pro $129/month (each shown against a higher $59 and $259), and Enterprise on request with BYOC and on-premises deployment.
Read our RAGFlow review4.0/5 - 29
Airbyte has the widest open catalogue for pulling business data into a RAG index, but its AI destinations lag its ELT core and self-hosting it means owning its security patches.
Best for: Data teams feeding a RAG system from many SaaS apps and databases who want incremental syncs they can self-host.
Price: Self-hosted Core is free (MIT and ELv2). Cloud Standard from $20/month with 5 credits; Plus from $189/month for 40 credits up to $4,999 for 2,000; Pro and Enterprise Flex custom.
Read our Airbyte review3.9/5 - 30
The sensible way to try graph RAG, cheaper to maintain than Microsoft GraphRAG, but most teams should prove they need a graph before adding one.
Best for: Teams whose evaluations show multi-hop questions failing with hybrid search and who want a graph on Postgres.
Price: Free and open source under the MIT license. Indexing and queries use your own LLM and embedding credits.
Read our LightRAG review3.9/5 - 31
A serious, self-hosted answer to agents that write valid SQL with the wrong business meaning, provided you can run its whole stack and spend the time certifying what it drafts.
Best for: Data platform teams who want agents to answer from certified business definitions on their own infrastructure and can run a multi-service stack.
Price: Free under Apache-2.0. You pay for model inference (NVIDIA's hosted API catalog by default, or your own NIM or OpenAI-compatible endpoints) and for hosting Postgres and three services.
Read our NVIDIA Auto Ontology review3.9/5 - 32
OpenViking makes agent memory something you can open and read, but its AGPL licence, Volcengine-first defaults and frequent breaking changes ask more of a team than Mem0 or Graphiti do.
Best for: Teams that want agent memory and document retrieval they can audit file by file, and can live with AGPL and a fast-moving server.
Price: Open source under AGPL-3.0, with no activation key. You pay for the embedding and vision-language model calls. Volcengine's hosted OpenViking Service has Personal and Enterprise plans, first 50 files free; prices are not in the README. Self-Managed edition by licence key, priced on request.
Read our OpenViking review3.9/5 - 33
WeKnora packs RAG, an agent and a self-writing wiki into one self-hosted app with real access controls, but its 2026 security record and its tilt towards Chinese workplace tools mean it belongs on an internal network, chosen deliberately.
Best for: Engineering teams at companies on Feishu, WeCom or Confluence that want a self-hosted, permissioned knowledge base with an agent on top.
Price: Free and open source (MIT, with third-party components under their own licences); you pay for servers and model APIs. Hosted options on WeChat Dialog Open Platform and Tencent Cloud Lighthouse; pricing for those is not published in the project's docs.
Read our WeKnora review3.9/5 - 34
code2prompt is the packer for people who care about the prompt template, held back by a release trail that no longer lines up.
Best for: Terminal users who want templated prompts or git-diff prompts built from their code.
Price: Free and open source (MIT).
Read our code2prompt review3.8/5 - 35
Cognee builds a shared knowledge graph from almost any source, but its defaults need an owner before they meet production.
Best for: Teams building several agents that need a shared knowledge graph assembled from many sources.
Price: Open source under Apache 2.0. Cognee Cloud: free up to 1M tokens and one workspace, then $1 per 1M tokens plus $5 per extra workspace a month; Enterprise is a quoted BYOC engagement.
Read our Cognee review3.8/5 - 36
MarkItDown gets Office files into a model faster than anything else open source, and flattens the PDFs that retrieval most needs kept intact.
Best for: Developers who need to feed Office documents and clean digital PDFs to a model quickly and cheaply.
Price: Free and open source under the MIT licence. Optional Azure conversion services are billed by Microsoft.
Read our MarkItDown review3.8/5 - 37
Memorilla is a clever answer to long-term memory, beating retrieval methods with a fraction of the tokens, but for now it is research code that needs an 80 GB GPU.
Best for: Researchers and ML engineers exploring long-term memory for assistants and agents who have large GPUs to experiment with.
Price: Free and open source (Apache 2.0).
Read our Memorilla review3.8/5 - 38
Ocrs is the OCR engine to embed when you want a clean Rust build and English text, and the wrong one the moment a page arrives in Chinese.
Best for: Rust and WebAssembly developers who need lightweight English-language OCR inside their own application.
Price: Free under Apache-2.0; models are free to download from Hugging Face.
Read our Ocrs review3.8/5 - 39
Still the widest net for odd file formats, but its makers now publish the numbers showing why you would pay them instead.
Best for: Teams building ETL pipelines that ingest many document formats for RAG.
Price: Library free under Apache 2.0. Hosted platform: 10,000 free pages, then $0.015 a page; Business plan with VPC or dedicated deployment priced on request.
Read our Unstructured review3.8/5 - 40
A careful, fast-moving client for one paid API; the code is MIT, but the thing you are actually buying is Valyu's credit meter.
Best for: TypeScript teams that have already decided Valyu's data sources suit their agent and want the official, maintained client.
Price: SDK free under MIT. The Valyu API is metered in credits: pay-as-you-go 1,600 credits per $10; plans $29, $99 and $499 a month; new accounts get $10 free credits ($20 with a company email).
Read our Valyu TypeScript SDK (valyu-js) review3.8/5 - 41
A tidy chunking library mid-rewrite: v1.7 works today, but most of what makes it distinctive is scheduled for removal in v2.
Best for: Teams that need a light recursive or code chunking step and can accept a v2 migration soon.
Price: Free and open source under the MIT licence.
Read our Chonkie review3.7/5 - 42
A careful, honest design for asking what the law said on a date, held back for now by thin coverage outside a handful of countries and open bugs that can return a wrong answer without warning.
Best for: Legal-tech developers and comparative-law researchers who want point-in-time statute text for the few countries with full corpora, and will check anything that matters against the official gazette.
Price: Free. The tooling is CC0; each country's law text is under that repository's own terms (public domain, Licence Ouverte 2.0, OGL v3.0 or BOE reuse conditions). Lexifina's separate legal workspace costs $0, $20 or $200 a month, with Enterprise priced on request.
Read our Git for Global Law review3.7/5 - 43
grepai trims an agent's code-reading bill without sending code anywhere, though its own benchmark puts the saving nearer a quarter than the 97% headline.
Best for: Developers who want their coding agent to search a repo by meaning, locally, instead of reading whole files.
Price: Free and open source (MIT). Runs locally with Ollama or LM Studio; OpenAI embeddings are billed by OpenAI.
Read our grepai review3.7/5 - 44
Mnemosyne is the most self-contained agent memory around, one SQLite file and no services, but its benchmark record is thin and partly withdrawn, so its quality claims still need your own test.
Best for: Individual developers and Hermes Agent users who want persistent memory on their own machine without running a database.
Price: Free and open source under the MIT licence. No hosted service or paid tier; costs are your own machine plus any remote embedding or LLM endpoint you choose.
Read our Mnemosyne review3.7/5 - 45
Obscura is a promising way to cut the memory bill of scraping at scale, but it is a six-month-old engine with an anonymous owner and a stealth pitch, so it belongs behind your own tests, not in front of them.
Best for: Scraping and agent teams paying for many Chrome instances who can test their target sites against a non-Chromium engine first.
Price: Free under Apache-2.0. Obscura Cloud (hosted, with proxies) is waitlist-only and unpriced.
Read our Obscura review3.7/5 - 46
ocr-rs is the practical way to get PaddleOCR's Chinese and Japanese coverage into a Rust binary, provided one maintainer and a C++ runtime do not worry you.
Best for: Rust developers who need non-Latin OCR, especially Chinese and Japanese, inside a native application.
Price: Free under Apache-2.0; PaddleOCR models are Apache-2.0 from Baidu.
Read our ocr-rs (formerly rust-paddle-ocr) review3.7/5 - 47
A neat way to ask fuzzy questions of a table in SQL, as long as you accept a full scan, a superuser install and rows leaving the database.
Best for: Analysts and developers on self-managed Postgres who want to classify or filter thousands of rows by meaning without building an embedding pipeline.
Price: Free (PostgreSQL Licence). Each row judged is billed by TypeSafe's Jev API unless you point it at a local compatible server.
Read our pg-jev review3.7/5 - 48
deepseek-ocr.rs puts a modern OCR model behind an OpenAI endpoint on a Mac with no Python, but it is a one-person project that went quiet in February.
Best for: Developers on Apple Silicon or CPU-only machines who want a local OCR model behind an OpenAI-style API without a Python stack.
Price: Free under Apache-2.0; model weights follow their upstream licences.
Read our deepseek-ocr.rs review3.6/5 - 49
Memvid is a tidy way to ship searchable memory as one file an agent can carry offline, but it is a document index rather than a memory layer that understands changing facts, and its benchmark lead rests on rivals' 2025 figures.
Best for: Developers building offline or edge agents that need a searchable, portable knowledge file rather than a model of a changing user.
Price: Free under Apache 2.0. The library caps a file at 50 MB by default (the Free tier in the source); larger capacities of 2 GB and 10 GB are unlocked by signed tickets from memvid.com. Cloud plan prices are not published.
Read our Memvid review3.6/5 - 50
Good at pulling a few typed fields from messy pages, but it ships your scraped content to its makers by default and pays a model call for every page.
Best for: Developers extracting typed fields from a modest number of varied web pages.
Price: Library free under MIT; you pay for LLM tokens. Hosted API: 500 one-off free credits, then $20, $100 or $500 a month; Enterprise custom.
Read our ScrapeGraphAI review3.6/5 - 51
A capable local search engine for agents, wrapped in instructions that tell your agent to file reports about you without asking.
Best for: Developers whose agents work on large private or unfamiliar codebases and who will set XERJ_DISABLE_FEEDBACK before first use.
Price: Free and open source (Apache 2.0). Optional reranking calls TypeSafe's paid Jev service with your own key.
Read our XERJ review3.6/5 - 52
franken_ocr is a serious piece of engineering that gets Unlimited-OCR onto a laptop CPU, wrapped in a licence and a governance model most companies will not sign up to.
Best for: Individual developers and small teams who need Unlimited-OCR quality on CPU-only machines and are comfortable with a single-author project and its licence.
Price: Free under the MIT licence with an OpenAI/Anthropic exclusion rider; model weights carry their upstream licences (Unlimited-OCR is MIT).
Read our franken_ocr review3.5/5 - 53
Still the reference design for whole-corpus questions, but Microsoft has stopped developing it and the indexing bill is as large as ever.
Best for: Teams with a fixed, high-value document set where cross-document questions justify a costly one-off index.
Price: Free and open source under the MIT licence. Indexing runs on your own OpenAI or Azure OpenAI credits, which the README warns can be expensive.
Read our GraphRAG review3.5/5 - 54
A fast, agent-friendly way to self-host web search, held back by unresolved questions over whether its upstream providers allow this use.
Best for: Developers who want a local web search tool for their own agents and are willing to check each enabled provider's terms.
Price: Free under the AGPL-3.0-or-later licence. Optional authenticated search providers bill you directly.
Read our RustXNG review3.5/5 - 55
A smart paper about using a website's own structure for RAG, released as serving code that cannot yet index your site.
Best for: Researchers and university web teams studying structure-aware retrieval over HTML sites, rather than teams that need a production RAG system.
Price: Free and open source under Apache 2.0; the bundled benchmark is research use only. Queries and indexing use your own LLM, embedding and reranker API credits (SiliconFlow by default).
Read our PolyUQuest review3.0/5
Sources
The main official source behind each ranked review; every review lists its full set.
- Qdrant: qdrant/qdrant on GitHub
- pgvector: pgvector/pgvector on GitHub (README)
- Docling: docling-project/docling on GitHub
- Hindsight: vectorize-io/hindsight on GitHub
- Milvus: milvus-io/milvus on GitHub
- Scrapling: D4Vinci/Scrapling on GitHub
- Graphiti: getzep/graphiti on GitHub
- LlamaIndex: run-llama/llama_index on GitHub
- Marker: datalab-to/marker on GitHub (README)
- MinerU: opendatalab/MinerU on GitHub (README)
- Repomix: Repomix on GitHub
- Crawl4AI: unclecode/crawl4ai on GitHub
- Firecrawl: firecrawl/firecrawl on GitHub
- Haystack: deepset-ai/haystack on GitHub
- OpenWiki: langchain-ai/openwiki on GitHub
- pdf-inspector: firecrawl/pdf-inspector on GitHub
- PyLate: lightonai/pylate on GitHub
- Weaviate: weaviate/weaviate on GitHub
- Chroma: chroma-core/chroma on GitHub
- Honcho: plastic-labs/honcho on GitHub
- Neo4j: neo4j/neo4j on GitHub
- Open Ontologies: fabio-rovai/open-ontologies README
- Xberg (formerly Kreuzberg): xberg-io/xberg on GitHub
- Indra OCR: datalab-to/indra on GitHub
- LanceDB: lancedb/lancedb on GitHub
- Maxun: getmaxun/maxun on GitHub
- Mem0: mem0ai/mem0 on GitHub
- RAGFlow: infiniflow/ragflow on GitHub
- Airbyte: airbytehq/airbyte on GitHub
- LightRAG: HKUDS/LightRAG on GitHub
- NVIDIA Auto Ontology: NVIDIA/auto-ontology on GitHub
- OpenViking: volcengine/OpenViking on GitHub
- WeKnora: Tencent/WeKnora on GitHub
- code2prompt: code2prompt on GitHub
- Cognee: topoteretes/cognee on GitHub
- MarkItDown: microsoft/markitdown on GitHub
- Memorilla: snap-stanford/memorilla on GitHub
- Ocrs: robertknight/ocrs on GitHub
- Unstructured: Unstructured-IO/unstructured on GitHub
- Valyu TypeScript SDK (valyu-js): valyuAI/valyu-js on GitHub
- Chonkie: feyninc/chonkie on GitHub
- Git for Global Law: lexifina/global-law README
- grepai: grepai on GitHub
- Mnemosyne: mnemosyne-oss/mnemosyne on GitHub
- Obscura: h4ckf0r0day/obscura on GitHub (README)
- ocr-rs (formerly rust-paddle-ocr): zibo-chen/ocr-rs on GitHub
- pg-jev: realZachi/pg-jev on GitHub
- deepseek-ocr.rs: TimmyOVO/deepseek-ocr.rs on GitHub
- Memvid: memvid/memvid on GitHub
- ScrapeGraphAI: ScrapeGraphAI/Scrapegraph-ai on GitHub
- XERJ: xerj-org/xerj on GitHub
- franken_ocr: Dicklesworthstone/franken_ocr on GitHub
- GraphRAG: microsoft/graphrag on GitHub
- RustXNG: sahenjp/RustXNG on GitHub
- PolyUQuest: 13-pieces-teen/PolyUQuest on GitHub
More guides
- Best open-source tools to run LLMs locally
- Best open-source AI agent frameworks
- Best open-source LLM fine-tuning tools
- Best open-source AI chat apps
- Best open-source AI coding agents
- Best open-source image and video AI tools
- Best open-source LLM evaluation tools
- Best open-source LLM gateways and observability tools
- Best Claude Code plugins and agent skills
- Best open-source tools for coding agents
- Best free courses for learning AI