RAG · Search

This repo open-sources a full Chinese textbook on AI agent engineering—complete with Markdown source, compiled PDF, and runnable Python demos for every chapter.

A Dart SDK that lets Flutter apps upload video and search inside it by meaning, speech, or imagery—without imposing any UI.

wigolo gives AI coding agents a local, keyless web research layer that runs entirely on your machine and bills nothing per query.

It learns how you think by watching your Mac, then hands an evidence-linked model of you to your coding agents via MCP.

Moss exists because calling out to a remote vector database adds 200–500 ms of latency—enough to kill a real-time conversation—so it runs embedding and search inside your process instead.

Heym exists because serious AI automation shouldn't require a sales call to access observability, evals, or multi-agent orchestration.

Vector search shouldn't force you to choose between PostgreSQL and DuckDB.

A self-hosted framework for building real-time voice-first AI agents that persist memory, delegate long tasks to background sub-agents, and optionally show up as lip-synced digital humans.

It exists because RAG shouldn't be the only way to turn a file dump into usable knowledge.

Turns URLs into clean markdown and JSON so AI agents don't have to parse HTML soup.

Macro exists because context dies when your email, chat, docs, and tasks live in separate apps, so it links them into one queryable workspace with shared AI memory.

turbovec exists so you can index embeddings immediately—no training, no tuning, no rebuilds—and search them faster than FAISS in a fraction of the RAM.

Dream Server exists because most people would rather pay OpenAI than spend a weekend hand-wiring Docker configs for local LLMs, RAG, and image generation.

DEEIX Chat exists because most open-source AI frontends stop at the fun stuff and leave you to invent user management, billing, and audit logs.

It gives Claude Code and Codex CLI hybrid semantic search and AST-based call graphs across seven languages.

Second Brain is a self-hosted semantic memory layer that lets every AI tool you use—Claude, ChatGPT, Cursor, or any MCP client—recall the same persistent context without you repeating yourself.

It exists because builders wanted a Claude Cowork-style agent that keeps work context local, encrypted, and auditable instead of shipping memory to someone else’s server.

A CLI generator that spits out complete FastAPI + Next.js AI apps with agents, RAG, auth, and billing wired in.

AI4Paper is a commercial Zotero plugin that stuffs the entire research pipeline—search, translation, reading, and survey writing—into your reference manager, backed by a claimed 240-million-paper knowledge base.

Omnigraph exists to let fleets of agents collaborate on a shared knowledge graph using git-style branches and merges, keeping the data on S3-compatible object storage.