Platforms for building LLM applications: retrieval-augmented generation, agent memory, model routing and orchestration.
Active Pro listings from this category appear first. Your sort applies within Pro and Free results.
AgentaLLM App Platforms & RAGAgenta is an open-source workspace for building AI agents by chatting, sharing them with a team, running them on schedules or app events, and tracing every run. MIT core, self-hosted with Docker or Kubernetes, or Agenta Cloud.Open sourceSelf-hostedFreemium
BifrostLLM App Platforms & RAGBifrost is an Apache-2.0 AI gateway written in Go. It unifies 20+ providers behind one OpenAI-compatible API with fallbacks, virtual keys, semantic caching, logging and an MCP gateway, run through NPX or Docker.Open sourceSelf-hosted
BotpressLLM App Platforms & RAGBotpress is a cloud platform for building AI chat agents in a visual Studio or in TypeScript, then deploying them to web, WhatsApp, Slack, Teams and more. Its GitHub repository holds the open-source Hub integrations, SDK, CLI and API clients.Open sourceWeb platformFreemium
CogneeLLM App Platforms & RAGCognee is a free, open-source AI memory platform that turns documents, code and conversations into a knowledge graph with vector retrieval for agents.Open sourceSelf-hosted
Crawl4AIBrowser Automation & ScrapingCrawl4AI is an Apache-2.0 Python crawler built on Playwright that outputs Markdown, JSON, screenshots and PDFs for RAG and agents. Run it as a library, a Docker server with REST and MCP, or use the hosted Crawl4AI Cloud API.Open sourceSelf-hostedFreemium
DifyLLM App Platforms & RAGDify by LangGenius combines a visual workflow builder, knowledge pipelines, sandboxed agents, model management and app APIs. It runs as Dify Cloud or self-hosted with Docker Compose under a modified Apache 2.0 license.Open sourceSelf-hostedFreemium
FirecrawlBrowser Automation & ScrapingFirecrawl turns URLs, search results and documents into Markdown, HTML, screenshots or schema-based JSON. Use the hosted API with SDKs, CLI and MCP, or self-host the AGPL-3.0 core with Docker Compose and a reduced feature set.Open sourceSelf-hostedFreemium
FlowiseLLM App Platforms & RAGFlowise is an open-source visual builder for agent systems and chatbots that is being sunset: the repository is archived and core support has ended.Open sourceSelf-hosted
Free Claude CodeAI Coding Assistants & Agent ToolingFree Claude Code (FCC) is an AGPL-3.0 local server with an Admin UI that connects 12 coding harnesses, desktop apps and IDE extensions to 61 free, paid, subscription and local model providers, with fallbacks, rate limits and Discord or Telegram bots.Open sourceSelf-hosted
HexabotLLM App Platforms & RAGHexabot v3 is a self-hosted AI workflow automation platform by Hexastack. It runs conversational, manual and scheduled workflows with AI agent actions, memory, RAG, MCP servers and channel extensions, under the source-available FCL-1.0-ALv2 license.CommercialSelf-hostedFreemium
KhojAI Assistants & ChatOpen-source personal AI server under AGPL-3.0: semantic search and chat over PDF, Markdown, org-mode, Word and Notion content, with agents, research mode, automations and Obsidian, Emacs and web clients. Khoj Cloud closed in April 2026, so it is self-hosted.Open sourceSelf-hosted
LangflowLLM App Platforms & RAGLangflow is an MIT-licensed platform for composing AI agents and retrieval workflows from Python components on a visual canvas. Flows run in the Playground, through a REST API or as MCP tools, from Desktop, Docker or a pip install.Open sourceSelf-hosted
LiteLLMLLM App Platforms & RAGSelf-hosted AI gateway and Python SDK from BerriAI. It translates OpenAI-format requests for 100+ model providers and adds virtual keys, budgets, spend tracking, routing with fallbacks, guardrails, an MCP gateway and an Admin UI.Open sourceSelf-hostedFreemium
LLM GatewayLLM App Platforms & RAGAGPL-3.0 API gateway for LLMs: one OpenAI-compatible endpoint for many providers, with routing, failover, key management, usage and cost analytics, caching and guardrails. Use the managed cloud or self-host with Docker.Open sourceSelf-hostedFreemium
LobeHubAgent FrameworksLobeHub is a TypeScript agent workspace with tasks, memory, pages and MCP tools. Agents answer in Slack, Discord or Telegram, can drive Claude Code or Codex on your devices, and run in LobeHub Cloud, desktop apps or a Docker Compose stack.Open sourceSelf-hostedFreemium
Mem0LLM App Platforms & RAGMem0 extracts facts from conversations with an LLM, stores them per user, agent or run, and returns the relevant ones through hybrid search. It ships Python and Node SDKs, a Docker server with dashboard, a CLI, an MCP server and a hosted Platform.Open sourceSelf-hostedFreemium
NVIDIA NeMo SwitchyardLLM App Platforms & RAGNVIDIA NeMo Switchyard is an Apache 2.0 library that routes each AI agent request to an efficient or a more capable model to balance success, cost and latency.Open sourceSelf-hosted
OmnaraAgent FrameworksOmnara is an Apache 2.0 platform for running AI agents as a service: a Go control plane with a REST API, TypeScript SDK and CLI, durable state in Postgres, approvals, MCP tools and machines from sandboxes or your own hosts. Self-host it or use Omnara Cloud.Open sourceSelf-hostedFreemium
OmnigraphDatabasesOmnigraph is a Rust graph database from Modern Relay that stores graphs as Lance files on local disk or S3-compatible storage. It adds typed .pg schemas, branches with three-way merge, vector and full-text search, Cedar policy and MCP access.Open sourceSelf-hosted
Open NotebookAI Assistants & ChatOpen Notebook is an MIT-licensed research workspace you run with Docker: collect PDFs, web pages, audio and video into notebooks, chat with cited answers, search by keyword or meaning and generate podcasts, using any of 24 cloud or local AI providers.Open sourceSelf-hosted
ParlantAgent FrameworksApache 2.0 Python framework and engine by Emcie for support and sales chat agents. It matches written policies per turn, reviews tool calls and replies, and ships a React chat widget, human handoff, session API and an optional paid Dashboard.Open sourceSelf-hostedFreemium
PipesHubLLM App Platforms & RAGPipesHub connects Slack, Google Drive, Jira, GitHub, Microsoft 365 and other systems, indexes them with their permissions and answers with citations, for people in the web app and for agents through MCP, APIs and SDKs. Apache-2.0, self-hosted or PipesHub Cloud.Open sourceSelf-hostedFreemium
PixelRAGLLM App Platforms & RAGPixelRAG is the Apache-2.0 codebase for the Berkeley research paper on screenshot-based RAG. It renders documents to image tiles, embeds them with a fine-tuned Qwen3-VL-Embedding model, builds FAISS or Qdrant indexes and serves a search API.Open sourceSelf-hostedExplore collections with tools relevant to this category, grouped by deployment, source model or workload.
4 matching tools from this category
27 matching tools from this category
27 matching tools from this category
LLM app platforms supply the plumbing between a language model and a working application. Listings here build retrieval-augmented generation pipelines that fetch relevant documents before the model answers, store long-term memory as knowledge graphs, route each request to a cheaper or more capable model through one gateway, compress context to save tokens and offer visual builders for chat and agent workflows. Agent frameworks are code libraries for agent logic, and an MCP server exposes tools and data to an AI client through the Model Context Protocol, so both sit elsewhere.
What belongs in this category: A product belongs here when it helps developers assemble, ground, route or optimise LLM-powered applications through retrieval, memory, model gateways or workflow builders, rather than being an end-user chat assistant or a single agent.
iThub lists 28 tools in LLM App Platforms & RAG. 26 of 28 are open source, 27 of 28 can be self-hosted, 28 of 28 have a free, freemium or open-source pricing model and 27 of 28 offer an API.
Use the resources that match your decision stage. Profile data and linked sources were refreshed through November 11, 2026.
