AnythingLLM
All-in-one local RAG and agentsOpen-source desktop and self-hosted app for document RAG, AI agents and multi-LLM chat, with broad local and cloud provider support and MCP.
- Maker
- Mintplex Labs
- Founded
- 2023
- Pricing
- Free tier
- Last checked
- October 2026
Verdict
Open-source desktop and self-hosted app for document RAG, AI agents and multi-LLM chat, with broad local and cloud provider support and MCP.
Score breakdown
vs LM Studio, the category leaderIndividuals and small teams who want a local-first app for document RAG and agents without writing code or locking into a cloud vendor.
Key features
- RAG over PDFs, DOCX, CSV, codebases and more
- No-code agent builder with web browsing, scraping, SQL and file skills
- Support for 30+ LLM providers, local (Ollama, LM Studio, LocalAI) and cloud
- Multiple vector-database backends, local and cloud
- Model Context Protocol (MCP) support on desktop and Docker, with Intelligent Tool Selection
- Visual Agent Flows (drag-and-drop workflow builder) and Community Hub marketplace
- Workspaces with per-workspace model, embedding and prompt settings
- Multi-user instances with role-based permissions
- Embeddable chat widget and scheduled recurring agent tasks
- Magic Features (v1.15.0): on-device, cross-app dictation (Magic Echo), text actions (Magic Beacon) and autocomplete (Magic Tab) that run locally in any app
Strengths
- +Free, open-source (MIT) desktop app with no account or telemetry required
- +Very broad compatibility — 30+ local and cloud LLM providers and many vector databases
- +No-code agent builder plus visual Agent Flows, MCP support, and Intelligent Tool Selection
- +Flexible deployment: desktop app, self-hosted Docker, or hosted cloud; Community Hub for sharing prompts, skills and flows
Weaknesses
- −Cloud-hosted tiers (Basic $50/mo, Pro $99/mo) are pricey relative to running it yourself
- −The desktop app is a resource-heavy Electron application
- −Self-hosted Docker setup can be involved despite the 'no-code' positioning
- −RAG output quality depends heavily on the underlying model you choose
Overview
Overview
AnythingLLM, built by YCombinator-backed Mintplex Labs and first released in 2023, is an open-source (MIT) “all-in-one” AI app centered on document RAG and agents. It runs as a native desktop app or a self-hosted Docker container, requires no code, and connects to more than 30 LLM providers — local options like Ollama, LM Studio and LocalAI, plus the major clouds — alongside a wide range of vector databases. Its workspace model keeps separate chat contexts, each with its own model, embeddings and prompt settings, and it supports the Model Context Protocol for connecting external tools.
Beyond retrieval, AnythingLLM includes a no-code agent builder with built-in skills (web browsing, scraping, SQL, file operations), visual Agent Flows, and scheduled agent tasks. The project is active — roughly 62.7k GitHub stars and frequent releases (v1.15.0, the latest, shipped in mid-2026) — and recent additions include dynamic model routing, Intelligent Tool Selection (only relevant tools/MCPs are injected into the prompt), a beta Community Hub for sharing system prompts, skills and flows, and the v1.15.0 “Magic Features” that bring on-device dictation, text actions and autocomplete to any app. The managed cloud now spans Basic ($50/mo), Pro ($99/mo) and Enterprise. The desktop app is a fairly heavy Electron build, hosted cloud tiers are comparatively expensive, and as always the quality of RAG answers depends on the model you point it at. For a local-first knowledge assistant, though, it’s one of the most complete options.
Key Benefits
- Local-first knowledge base: Turn your documents into a private, queryable assistant with no cloud requirement.
- Bring any model: Broad provider support means you’re never locked into one vendor.
- Agents without code: Build tool-using agents and schedule recurring tasks from a GUI.
- Deploy your way: Desktop, Docker or managed cloud, all from the same project.
Use Cases
- Chat with your documents — Index company or personal files for grounded, cited answers.
- Private research assistant — Combine local models with RAG for sensitive material.
- No-code agents — Automate web research, scraping or database queries with built-in skills.
- Team knowledge hub — Self-host a multi-user instance with per-workspace settings.
Pricing
Checked October 2026 · USD- Full open-source app (MIT)
- Local RAG, agents and MCP with bring-your-own models
- No account or telemetry required
- Private hosted instance with custom subdomain
- Up to ~5 users and ~100 documents
- Bring-your-own LLM API key
- RAG and agents out-of-the-box at larger scale
- Larger document collections and team collaboration
- 72-hour support SLA
- On-prem or dedicated deployment
- Custom SLA and domain
- White-glove installation