62 apps RAG
Basjoo screenshot thumbnail

Basjoo

Support tickets that repeat the same twelve questions all week can answer themselves when Basjoo turns your website and documents into an embeddable AI support agent you host yourself. Knowledge bases are built independently of agents, fed by crawling a single page or an entire site, or by uploading PDF, Word, Excel, HTML, and text files that are parsed into searchable chunks. Visitors chat through a widget added with one script tag, in a floating bubble, inline frame, or iframe, and answers stream back with source citations so people can verify what the bot claimed. A curated question and answer index is matched before retrieval, which means correcting a wrong answer takes effect immediately without reindexing the whole collection, and a keyword fallback mode can answer matched questions with no model key at all. When a conversation needs a person, operators watching the live session wall can take over, reply with saved macros, release the chat back to the bot, or resolve it, with business hours deciding when the bot is off duty. Lead capture forms, an unanswered question queue that groups repeats into future answers, thumbs feedback rolled into analytics, and signed outbound webhooks for seven event types round out the operator side. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
RESTai screenshot thumbnail

RESTai

Every AI project you build in RESTai becomes an endpoint that any app can call over plain HTTP. RESTai gives you a browser dashboard where each project gets its own model, system prompt, tools, and chat playground. Build knowledge-base assistants over uploaded files and synced web pages, ReAct-style agents that call MCP servers, or drag-and-drop block projects that need no model at all. Connect Ollama, OpenAI, Anthropic, Gemini, vLLM, Azure, Bedrock, or any OpenAI-compatible endpoint, and let teams share the ones you approve. Daily charts follow tokens, cost, and latency per project, with rate limits, guardrails, prompt version history, and evaluation runs for quality tracking. Teams, roles, two-factor sign-in, white-label branding, and an audit trail cover administration. A one-line chat widget embeds a project on any website, and connectors reach Telegram, Slack, and WhatsApp. One install can serve several branded assistants and bill each team separately. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Deploy
Agent-Me screenshot thumbnail

Agent-Me

Build an AI twin that has to show its homework. Agent-Me answers questions from a folder of Markdown notes you control, and every reply arrives with the exact source excerpts behind it. Pick Standard Q&A for a direct grounded answer, Role-based multi-agent to watch a planner, researcher, critic, and writer hand work to each other, or Verified multi-agent to add a final check on citation paths and answer metadata. When the notes do not contain an answer, the critic blocks the draft and the app says so instead of inventing one. Press Compare workflows to run the baseline and verified pipelines on the same question and read the results side by side. Download a sanitized run record for any collaboration, then open it later in the browser to review the trace without re-running anything. The interface speaks nine languages, and the default mode never calls an outside model, so private notes stay on your server. Swap in your own documents and test supported, unsupported, and adversarial questions to see exactly where an assistant stays grounded. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
AKB screenshot thumbnail

AKB

Achieving 98.4% Recall@5 on LongMemEval-S without a reranker, AKB is the agent-native knowledge infrastructure giving Claude Code, Cursor, Windsurf, and any MCP-aware agent persistent organizational memory — a drop-in replacement for Confluence or Notion where AI agents read and write directly rather than scraping human-formatted pages. Documents are stored as Markdown with YAML frontmatter in Git bare repositories (full version history, branching, diff), while PostgreSQL 16 serves as source of truth for chunk text, metadata, and BM25 vocabulary, with dense embeddings handled by a pluggable vector store (pgvector default, Qdrant optional, or managed Seahorse). Agents interact through 20+ MCP tools — akb_put, akb_search, akb_browse, akb_relations, akb_sql, akb_edit, akb_history — performing hybrid dense plus BM25 search fused via Reciprocal Rank Fusion in one call. The URI graph (depends_on, related_to, implements relations) lets agents traverse knowledge connections without external graph databases. Multi-tenant vault isolation is enforced at the PostgreSQL ACL level with per-user roles and SET LOCAL ROLE for SQL sandboxing. Event fanout streams structured events to Redis Streams for external consumers (synthesis bots, digest agents, audit trails), and a hash-chained append-only audit log integrates with enterprise SIEMs. Ships with agent plugins for Claude Code and Codex (session capture, wiki ingest, lifecycle hooks), Kubernetes kustomize manifests, and Open Knowledge Format export. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSL 1.1 licensed (free under 100 seats, auto-converts to Apache 2.0 after four years).

Deploy
Lumen Learning Platform screenshot thumbnail

Lumen Learning Platform

Tell Lumen what you want to learn in one sentence and it interviews you, drafts a brief, and builds a private course with modules, lessons, and quizzes, showing progress as it goes. Every learner owns the whole loop: define a goal, build the course, study it, and share it only when you choose to. An AI tutor sits beside each lesson, streams answers grounded in that course, and attaches citations that jump to the lesson it drew from. A trace view shows every planner step, tool call, and retrieval score behind an answer, and a replay view steps through how a course was authored. Quizzes feed a spaced-repetition review queue, a mastery view tracks progress, and finishing a course issues a verifiable Open Badges credential. Browse a public catalog with subject, level, and tag filters, clone any listed course into your own draft, and press Ctrl+K to search courses or switch themes. Add your own OpenAI, Anthropic, Groq, or Mistral key, or run without a key and keep the rest of the app working. An admin area moderates shared courses, and an MCP server lets coding agents list courses and ask the tutor. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
loci screenshot thumbnail

loci

Point Claude Desktop, Cursor, Cline, or any other MCP host at one loci instance and every assistant searches the same notes, project docs, and saved memories. Hybrid retrieval fuses vector hits with BM25 using reciprocal rank fusion, so an exact identifier like user_id still surfaces, and every answer cites the file and section it came from, with optional claim-by-claim verification. Notes stay readable as Markdown, and the index updates incrementally from folders of text, HTML, org files, PDF, and Word documents or an Obsidian vault. Durable memories are saved with one command, structured task state is stored and fetched by exact key, and decision notes can declare what they supersede so a history command shows the chain and answers stop quoting retired policy. A memory health report shows which notes were cited, corrected, or never used. The web console has a dashboard, search with an evidence pane, memory editing, sources and file uploads, a query log, a note graph, and an activity log, in English or Chinese with light and dark themes. Role-based tokens separate viewers, editors, and admins. Embedding and chat calls go only to the providers you configure, and local endpoints like Ollama keep the whole workflow offline. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy
LLemonStack screenshot thumbnail

LLemonStack

One CLI command deploys a complete AI development environment: n8n, Flowise, Supabase, Ollama, Qdrant, LiteLLM, Langfuse, Open WebUI, LightRAG, Browser-Use, Firecrawl, Crawl4AI, and more, all pre-wired with networking, credentials, and database connections. LLemonStack eliminates the hours of Docker Compose configuration that typically precede any local AI agent project. The llmn CLI initializes isolated project environments with auto-generated secure credentials, starts services in dependency order (databases first, then middleware, then apps), and displays a dashboard showing every service URL and access token. n8n brings 400+ workflow integrations, Flowise provides visual agent building, Ollama runs local LLMs like Llama and Mistral, Qdrant stores vectors at high performance, Open WebUI offers ChatGPT-style model interaction, and LiteLLM proxies requests to any provider with cost tracking. Langfuse automatically logs traces for every LiteLLM query, providing full observability. Each project maintains isolated Postgres schemas preventing data collision across parallel stacks. Firecrawl and Crawl4AI extract web content into LLM-ready formats for RAG pipelines feeding LightRAG or Qdrant. Dozzle streams live container logs for debugging. Import/export tooling migrates workflows between projects with automatic credential reconfiguration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Deploy
PharosRAG screenshot thumbnail

PharosRAG

Your team's documents sit in folders nobody can search, and the answer to a simple question hides on page 40 of a PDF someone saved last year. Pharos ingests PDFs, scans, Word documents, presentations, and spreadsheets into a local knowledge base, then answers questions against that library with citations traced back to the exact page. Hybrid retrieval finds the passages that matter, and every answer carries its evidence so readers can verify the claim in the source. Access control decides visibility per person: an API key resolves to an identity with a tenant and group memberships, retrieval filters hard to only the documents that identity may see, and a document with no permissions attached stays invisible to everyone. Two doors lead into the same library. The HTTP API runs a closed question-answering pipeline that retrieves, grounds, and answers in one call, and coding agents connect through MCP to decide for themselves when to retrieve, how to rewrite a query, and when a question needs multiple hops. A resident daemon keeps the search index and models warm, so every session shares one backend instead of reloading heavy resources. The deployment scales from one machine to replicated application tiers behind a load balancer. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Deploy