Show HN: Ragleap-RAG – RAG engine that documents what it doesn't do yet RagLeap has released RagLeap Core, an MIT-licensed, open-source RAG engine that powers its self-hosted AI business manager, allowing users to run a document-grounded chat system on their own infrastructure with their own keys. The engine provides persistent memory across channels, a dashboard for non-technical owners, and built-in voice AI, with no vendor lock-in. The project is honest about its early stage, with a roadmap reflecting the real state of the code. The open-source AI business manager. One AI, five channels, one memory. RagLeap Core is the open-source engine behind RagLeap — a self-hosted RAG retrieval-augmented generation chat system that answers questions from your own documents, on your own server, with no vendor lock-in. Quickstart quickstart · Docs https://docs.ragleap.com · Website https://ragleap.com · Hosted Version https://ragleap.com Not to be confused with— that's a separate, paid, license-gated self-hosted product Free tier with a license key, up to Enterprise . install.ragleap.com ragleap-core this repo is MIT-licensed, completely free, and never requires a license key. If you cloned this repo, you're in the right place for a genuinely free, open-source RAG engine. Most open-source RAG projects give you a toolkit — you still have to build the app, wire up a UI, add memory, and connect every channel yourself. RagLeap Core gives you a working chat engine out of the box, and the full RagLeap platform turns it into an AI that actually operates a business. | Without RagLeap | With RagLeap | |---|---| | ❌ A different bot for your website, WhatsApp, and Telegram — none of them share memory | ✅ One AI across every channel, with memory that persists between them | | ❌ Your RAG chatbot forgets everything the moment a session ends | ✅ Persistent memory — facts and preferences carry across sessions and channels | | ❌ You're a developer, so you can wire up LangChain — but your team can't manage it | ✅ A real dashboard for non-technical owners: settings, analytics, team, billing | | ❌ Answering customer questions and running the business are two separate systems | ✅ Manager AI — an executive assistant that can see analytics, send emails, and manage settings by conversation | | ❌ Adding a phone line means integrating Twilio, STT, and TTS yourself | ✅ Voice AI is built in — real inbound calls, answered and routed automatically | | ❌ Automating a workflow means writing custom code per integration | ✅ n8n workflow automation triggered directly from any conversation | This repo isn't a general-purpose RAG framework you assemble into something — it's the real, working engine that already powers a production AI business platform see What's in the hosted version whats-in-the-hosted-version-ragleapcom below . The code here is honest about being early, but it's extracted from something that already works in the real world, not built as a demo. Open-source AI agent projects like OpenClaw took off for a specific reason: people wanted an assistant that runs on their own infrastructure , with their own keys , answering from the chat apps they already use — not a black box hosted by someone else. That same principle is what RagLeap Core is built on for business AI specifically. Your keys, your infrastructure, your data. RagLeap Core never asks for a system API key. You bring your own Gemini key, you run your own PostgreSQL database, your documents never leave your server unless you choose the hosted version. Chat is the interface, not a separate dashboard you have to learn. The same way OpenClaw meets people on WhatsApp, Telegram, and Slack, RagLeap's full platform meets business owners on the channels they already use — WhatsApp, Telegram, Discord, and real phone calls — not a new app they have to check. A real, working system — not an abstract framework. This isn't a toolkit like LangChain where you assemble your own app from primitives. RagLeap Core is the actual chunking → embedding → retrieval → generation pipeline extracted from a production system that already answers real customer questions, at a company that already runs on it. Built in public, honestly. This repo says clearly what's done and what isn't. No inflated claims, no vaporware Quickstart commands that don't work yet — the Roadmap reflects the real state of the code, updated as it progresses. RagLeap Core is a document-grounded chat engine. Upload your documents, ask questions, get cited answers — self-hosted, on your own infrastructure, with your own API key. WhatsApp, Telegram, and Discord bots are included in this repo too — single-tenant, .env-configured channel adapters that answer from the same document knowledge base. It is the foundation of RagLeap https://ragleap.com , a hosted AI business manager that adds Voice calling, multi-tenancy, a persistent memory system, and an executive-assistant layer on top of this same core engine. If RagLeap hosted is the business, RagLeap Core is the engine room. - ✅ You want a self-hosted RAG chatbot with full control over your data - ✅ You want to understand exactly how document retrieval and citation works, not use a black box - ✅ You're comfortable running your own server and your own AI provider key - ✅ You want to contribute to or extend an open document-QA engine - ✅ You'd rather see the code than trust a vendor's word on data privacy | It's not... | It is... | |---|---| | A hosted product | Self-hosted software you run yourself | | Multi-tenant, with persistent cross-session memory | Single-tenant — one bot, one document set, per deployment | | A multi-tenant platform | WhatsApp/Telegram/Discord/Voice channel adapters included, single-tenant — multi-tenant routing lives in the hosted version | | A no-code SaaS dashboard | A codebase you deploy and configure | | Feature-complete with the hosted version | The foundational subset — see | 📄 Document ingestion | Upload PDFs, text, and common document formats | 🔍 RAG retrieval | Vector search over your documents via pgvector | 💬 Chat with citations | Answers reference the source document, not a black box | 🔌 Bring your own AI key | OpenAI, Gemini, Anthropic, or any OpenAI-compatible endpoint | 🌐 Web chat widget | Embed a chat widget on any website | 🐳 Docker-based setup | One-command local deployment | 🕸️ Knowledge Graph Neo4j | Entity extraction and graph-boosted retrieval alongside vector search | 🌍 Language detection | Auto-detects document and query language, applied across every channel | 🔗 Integrations | Connect MySQL, PostgreSQL, MongoDB, REST APIs, Salesforce, HubSpot, Shopify, Google Sheets, Stripe | 🔀 Hybrid search | Combines dense vector and sparse full-text retrieval via Reciprocal Rank Fusion | ⚡ Streaming responses | Answers stream token-by-token instead of waiting for the full response | 🔁 Provider fallback | Automatically retries with a backup LLM provider if the primary fails | 💰 Token usage reporting | Real per-call token counts from the provider, plus context-size budget trimming | RagLeap Core is the foundation layer of the full RagLeap platform. Here's how it fits into the bigger picture: +-------------------------------------------------------------+ | RagLeap Hosted Platform | | | | locked Manager AI — private executive assistant | | locked AI Employees — role-based persistent memory | | locked n8n Workflow Automation | | locked Persistent Memory cross-channel, cross-session | | locked Multi-tenant Billing, Teams & Permissions | | locked Audit History / Compliance logging | | locked Embed Widget Control Center white-label | | locked Managed hosting, backups, SLA, support | | | | built on top of | +-------------------------------------------------------------+ | +-------------------------------------------------------------+ | RagLeap Core this repo, open | | | | +----------------+ | | | Web Chat UI | | | +-------+--------+ | | | | | +-------v--------+ | | | Chat API | | | +-------+--------+ | | | | | +---------------------+---------------------+ | | | | | | | | +-----v----+ +---v-----+ +--v------+ +-v-------+ | | | WhatsApp | |Telegram | | Discord | | Voice | | | +----------+ +---------+ +---------+ +---------+ | | | | | | | | +---------------------+---------------------+ | | | | | +---------------------+---------------------+ | | | | | | | +-----v-----+ +------v------+ +------v------+ | | | Document | | RAG | | AI Provider | | | | Ingest | | Retrieve | | Adapter | | | +-----+-----+ +------+------+ +------+------+ | | | | | | | +---------------------+---------------------+ | | | | | +-----------v-----------+ | | | PostgreSQL + pgvector | | | +-----------+-----------+ | | | | | +-----------v-----------+ | | | Neo4j Knowledge | | | | Graph | | | +------------------------+ | +-------------------------------------------------------------+ locked = commercial/hosted-only feature, not included in this repository. See below for the full breakdown. ragleap-core/ ├── core/ RAG engine — chunking, embedding, retrieval, generation │ ├── chunker.py │ ├── embedding.py Gemini embeddings gemini-embedding-001, 3072-dim │ ├── retrieval.py pgvector cosine search │ ├── generation.py 19-provider BYOK generation Gemini, OpenAI, Anthropic, etc. │ ├── ingest.py chunk - embed - store pipeline │ ├── parsers.py PDF/DOCX/TXT text extraction │ └── api.py FastAPI app — /health, /upload, /chat, /webhook/ ├── channels/ Messaging + voice channel adapters │ ├── whatsapp/ Twilio + Gupshup │ ├── telegram/ │ ├── discord/ │ └── voice/ Twilio Media Streams, WebSocket server ├── db/ │ └── schema.sql documents + chunks tables, pgvector index ├── examples/ Runnable example scripts ├── .github/workflows/ CI: compile check, Docker build, smoke tests ├── docker-compose.yml app + db + voice services └── Dockerfile RagLeap Core covers document upload, retrieval, and web chat. The hosted platform builds a full AI business manager on top of it: | Area | What it adds | |---|---| Manager AI | A private executive assistant for the owner — sees documents, analytics, team permissions, and database connections; can send emails, generate reports, and manage settings by conversation, reachable via Web, WhatsApp, Telegram, or phone call | AI Employees | Specialized AI roles seeded per workspace, each with its own permanent memory, so support and sales conversations draw on different context automatically | Voice AI | Real inbound phone calls via Twilio — speech-to-text, RAG-grounded response, text-to-speech, with owner vs. customer call routing | Multi-channel bots multi-tenant | WhatsApp Twilio or Gupshup , Telegram, and Discord — single-tenant versions are in this repo; the hosted version adds multi-tenancy, per-workspace routing, and shared config across channels | Persistent Memory | Facts and preferences that persist across sessions and channels, not just within a single conversation | Advanced AI Settings | Model selection Gemini/OpenAI/Claude , temperature tuning, bring-your-own-key per provider, and automatic failover across a fallback key pool | Team Chat | Internal team messaging board per workspace, separate from customer-facing AI chat | n8n Workflows | Trigger no-code automations directly from a conversation, across every channel | 222+ Languages | This repo includes language detection langdetect, ~55 languages across all channels; the hosted platform extends this to 222+ languages with per-user persisted preferences | Integrations & Database Connectors | This repo includes 9 raw connectors MySQL, PostgreSQL, MongoDB, REST API, Salesforce, HubSpot, Shopify, Google Sheets, Stripe with on-demand sync; the hosted platform adds AI-suggested automations per channel and developer-level custom automation workflows on top | Analytics Dashboard | Per-provider usage breakdown OpenAI, Gemini, Claude , query volume, token costs, and daily trends | Team & Billing | Multi-tenant workspaces, team member permissions, subscription plans, usage-based billing | Audit History | Full log of configuration changes — who changed what, and when | Embed Control Center | White-label widget builder — Bubble, Fixed Panel, or Full Page embeds for any website | Data Visibility Controls | Per-document and per-database Public/Private settings — control exactly what customer-facing bots see vs. what's reserved for Manager AI only | Observability & Hallucination Detection | Built-in monitoring layer that audits AI responses for accuracy and flags potential hallucinations | Cloud or Self-Hosted deployment | Run the full platform as managed cloud subscription or self-hosted on your own server one-time license | Managed hosting | Backups, uptime SLA, and support — zero infrastructure to maintain | This is the standard open-core model — the same approach used by projects like n8n, Supabase, and Cal.com: the engine is free and open, the managed/extended product is commercial. ✅ Status: core pipeline verified working.Ingest - embed - retrieve - generate runs end-to-end via Docker Compose, including a clean fresh-clone test. See the Roadmap for what's next PDF/DOCX support, alternative BYOK providers . Fastest way to try it — one command checks Docker, clones the repo, and sets up .env for you: curl -fsSL https://raw.githubusercontent.com/antonyrag/ragleap-core/main/install.sh | bash Windows users: run this in Git Bash, not Command Prompt or PowerShell. The script will pause after cloning and ask you to add your Gemini API key to .env — get a free one at aistudio.google.com/apikey https://aistudio.google.com/apikey , then re-run the same command. Or, the manual way — better if you want to read the code before running anything: git clone https://github.com/antonyrag/ragleap-core.git cd ragleap-core cp .env.example .env add your Gemini API key to .env docker compose up --build -d Requirements: Docker, Docker Compose, an API key from OpenAI, Google Gemini, or Anthropic. Try it in 30 seconds — with the stack running, see examples/ /antonyrag/ragleap-core/blob/main/examples for two verified, runnable scripts: examples/01 ingest and query.py — upload a document and ask a question via the API examples/02 test channel directly.py — test the WhatsApp/Telegram/Discord answering logic without real bot credentials RagLeap Core is bring-your-own-key only there is no system-provided key for any provider. Set LLM PROVIDER in .env to choose which one to use for the generation chat step. Embeddings currently always use Gemini gemini-embedding-001 , regardless of LLM PROVIDER . LLM PROVIDER value | Required env vars | Notes | |---|---|---| gemini default | GEMINI API KEY | Get a key at aistudio.google.com/apikey | anthropic | ANTHROPIC API KEY , ANTHROPIC MODEL optional | Get a key at console.anthropic.com | openai | OPENAI API KEY , OPENAI MODEL | | mistral | MISTRAL API KEY , MISTRAL MODEL | | groq | GROQ API KEY , GROQ MODEL | Free tier available | together | TOGETHER API KEY , TOGETHER MODEL | | openrouter | OPENROUTER API KEY , OPENROUTER MODEL | | ollama | OLLAMA MODEL no API key needed | Self-hosted; requires Ollama running locally | deepseek | DEEPSEEK API KEY , DEEPSEEK MODEL | | xai | XAI API KEY , XAI MODEL | | cohere | COHERE API KEY , COHERE MODEL | | perplexity | PERPLEXITY API KEY , PERPLEXITY MODEL | | qwen | QWEN API KEY , QWEN MODEL | | moonshot | MOONSHOT API KEY , MOONSHOT MODEL | | zhipu | ZHIPU API KEY , ZHIPU MODEL | | yi | YI API KEY , YI MODEL | | baidu | BAIDU API KEY , BAIDU MODEL | | minimax | MINIMAX API KEY , MINIMAX MODEL | | custom | CUSTOM API KEY , CUSTOM MODEL , CUSTOM BASE URL | Any OpenAI-compatible endpoint | Example, switching to Groq in .env : LLM PROVIDER=groq GROQ API KEY=your-groq-key GROQ MODEL=llama-3.3-70b-versatile RagLeap Core includes a real-time voice channel: Twilio Media Streams connects via WebSocket, your speech is transcribed with OpenAI Whisper, answered by the core RAG pipeline, and spoken back with OpenAI TTS. The voice-activity detection and echo-suppression logic is carried over from a production system tuned against real call traffic. Runs as a separate service on port 8765 see docker-compose.yml , since Twilio's real-time audio protocol needs a raw WebSocket server, not an HTTP route. Setup: - Set OPENAI API KEY in .env used for both Whisper STT and TTS in v1 - Optionally set VOICE BOT NAME , VOICE GREETING , VOICE TTS VOICE - Point a Twilio phone number's