#rag

TekMyraNew

Context compression system for LLM pipelines that verifies no protected content is lost and refuses compression when safety cannot be guaranteed. Apache-2.0 open source by LaconIQ.

GitNexusNew

Runs entirely in your browser and turns any git repo into an interactive knowledge graph with a built-in AI agent for exploring the code.

EBM LensNew

An open-source agentic RAG system that searches 12 biomedical databases and produces a source-cited synthesis of the evidence.

Dify

An open-source platform for building AI chatbots and automated workflows by connecting blocks on a canvas, instead of writing code from scratch.

Haystack

An open-source toolkit for building AI systems that answer questions using your own documents — feeding an AI model your company's PDFs, wikis, or support tickets so it answers from real content instead of guessing.

Ontheia

A free, open-source, self-hosted AI agent platform built for organizations that can't send data to a third-party cloud — think law firms, clinics or banks — with role-based access, memory, and support for every major AI model.

WeKnora

An open-source, self-hosted platform from Tencent that turns a pile of company documents into a searchable knowledge base with AI Q&A — built to plug into a very wide range of AI models and vector databases.

turbovec

A free, open-source vector search library that finds similar items (for AI search, recommendations, RAG) faster and using far less memory than the previous standard, FAISS.

OpenKB

A free, open-source command-line tool that reads your documents (PDFs, Word files, spreadsheets...) and turns them into a linked wiki you can browse in Obsidian, using AI instead of manual note-taking.

Leni

An AI analyst for real estate and private-equity investment teams that reads messy deal documents and produces underwriting, valuation and reporting outputs with source citations you can actually check.

Lens AI

A knowledge layer that keeps every AI chatbot and assistant in your company answering from the same up-to-date source of truth.

Polygres

Turns a Postgres database into working memory for AI agents, with hybrid search across relational, graph, and vector queries in one call.

Heym

A workflow automation tool you host yourself, where you drag boxes onto a canvas to connect AI models, actions, and approval steps — instead of paying a monthly fee to a cloud automation platform.

MemoryPlugin

Cross-platform long-term memory system that maintains shared context across 21+ AI tools without requiring repetition.

Timbal AI

A toolkit for building AI "employees" that actually finish a job reliably — instead of a chatbot that just talks, Timbal helps a company wire up an AI agent that can look things up, take real actions in other systems, and behave consistently every time.

Mem0

Gives AI chatbots and agents a real memory — so they remember what you told them last week — instead of forgetting everything the moment a conversation ends, the way most AI apps do by default.

Zep

Builds a living map of everything a user has told an AI agent over time — and how those facts connect and change — so the agent can pull up exactly the right context in under 200 milliseconds instead of re-reading an entire chat history.

Firecrawl

Web scraping and crawling API that turns entire websites into clean, structured data ready for AI models to read.

turbopuffer

Vector + full-text search database built on object storage: cheap at scale, sub-10ms latency, used by Cursor, Notion and Linear.

Mastra

TypeScript framework for AI agents and workflows: typed tools, graph orchestration, memory, RAG and 90+ model providers.