Try describing what you need:

LibreChat logo

LibreChat

★ 46.9k

A self-hosted alternative to Chatgpt

MIT LicenseOpen Source — No Paywall6 Containers — 6 containers — moderate hosting footprintCompose · SourceNeeds MongoDB1 documented maintainer

About

LibreChat is a self-hosted AI conversation platform for users and teams who want a centralized interface for working with many AI providers. It presents a ChatGPT-inspired experience while adding...

Community Ratings

No ratings yet

Features

  • AI model selection
  • custom endpoints
  • code interpreter
  • agents and tools integration
  • web search
  • generative UI artifacts
  • image generation and editing
  • presets and context management
  • multimodal file interactions
  • admin panel

Details

Last Updated
Nov 10, 2026
Created
Feb 12, 2023
Install Methods
docker-composesource
Requirements
RedisS3 with CloudFront (optional for media links and downloads)
Authentication
oauthldaplocal
Backup & Export
native-export
Runtime / Stack
NodejsDocker
Privacy & Independence
Cloud: Optional
User Model
Multi-User
Deployment

Deployment: Docker Compose ✓6 Containers — moderate hosting footprintRuns as 6 containers

Run LibreChat yourself

Pick how much you want to manage.

2 more ways to host

Some links earn us a commission. netcup pays us one and is our preferred VPS host.

Is this your project? Sponsor a listing

Run LibreChat with Docker Compose

Compose file from the LibreChat project repository.

6 services · database: mongo · infra: mongo, meilisearch, pgvector · 3 unclassified (librechat-dev, librechat-admin-panel, librechat-rag-api-dev-lite)

no resource limits declared

needs persistent storage (8 volumes)

docker-compose.yml · @ cf9a426 · scanned Nov 3, 2026

# Do not edit this file directly. Use a ‘docker-compose.override.yaml’ file if you can.
# Refer to `docker-compose.override.yaml.example’ for some sample configurations.

services:
  api:
    container_name: LibreChat
    ports:
      - "${PORT}:${PORT}"
    depends_on:
      - mongodb
      - rag_api
    image: registry.librechat.ai/danny-avila/librechat-dev:latest
    restart: always
    user: "${UID}:${GID}"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    environment:
      - HOST=0.0.0.0
      - MONGO_URI=mongodb://mongodb:27017/LibreChat
      - MEILI_HOST=http://meilisearch:7700
      - RAG_PORT=${RAG_PORT:-8000}
      - RAG_API_URL=http://rag_api:${RAG_PORT:-8000}
      - PROXY=${PROXY:-}
      - HTTP_PROXY=${HTTP_PROXY:-}
      - HTTPS_PROXY=${HTTPS_PROXY:-}
      - NO_PROXY=${NO_PROXY:-localhost,127.0.0.1,::1},${no_proxy:-},mongodb,chat-mongodb,meilisearch,chat-meilisearch,rag_api,vectordb,host.docker.internal
      - http_proxy=${http_proxy:-}
      - https_proxy=${https_proxy:-}
      - no_proxy=${no_proxy:-localhost,127.0.0.1,::1},${NO_PROXY:-},mongodb,chat-mongodb,meilisearch,chat-meilisearch,rag_api,vectordb,host.docker.internal
    volumes:
      - type: bind
        source: ./.env
        target: /app/.env
      - ./images:/app/client/public/images
      - ./uploads:/app/uploads
      - ./logs:/app/logs
      - ./skill:/app/skill
  admin-panel:
    container_name: admin-panel
    image: registry.librechat.ai/clickhouse/librechat-admin-panel:latest
    ports:
      - "${ADMIN_PANEL_PORT:-3000}:3000"
    depends_on:
      - api
    restart: always
    environment:
      - PORT=3000
      # Plain expansion (not :?) so `docker compose down`/`pull` still run when this is unset.
      # The panel itself refuses to start without it; set ADMIN_PANEL_SESSION_SECRET in .env.
      - SESSION_SECRET=${ADMIN_PANEL_SESSION_SECRET}
      - API_SERVER_URL=http://api:${PORT:-3080}
      - VITE_API_BASE_URL=${DOMAIN_CLIENT:-http://localhost:3080}
      - SESSION_COOKIE_SECURE=${ADMIN_PANEL_SESSION_COOKIE_SECURE:-false}
  mongodb:
    container_name: chat-mongodb
    image: mongo:8.0.20
    restart: always
    user: "${UID}:${GID}"
    volumes:
      - ./data-node:/data/db
    command: mongod --noauth
  meilisearch:
    container_name: chat-meilisearch
    image: getmeili/meilisearch:v1.35.1
    restart: always
    user: "${UID}:${GID}"
    environment:
      - MEILI_HOST=http://meilisearch:7700
      - MEILI_NO_ANALYTICS=true
      - MEILI_MASTER_KEY=${MEILI_MASTER_KEY}
    volumes:
      - ./meili_data_v1.35.1:/meili_data
  vectordb:
    container_name: vectordb
    image: pgvector/pgvector:0.8.0-pg15-trixie
    environment:
      POSTGRES_DB: mydatabase
      POSTGRES_USER: myuser
      POSTGRES_PASSWORD: mypassword
    restart: always
    volumes:
      - pgdata2:/var/lib/postgresql/data
  rag_api:
    container_name: rag_api
    image: registry.librechat.ai/danny-avila/librechat-rag-api-dev-lite:latest
    environment:
      - DB_HOST=vectordb
      - RAG_PORT=${RAG_PORT:-8000}
    restart: always
    depends_on:
      - vectordb
    env_file:
      - .env

volumes:
  pgdata2:

This file may be out of date. Check the LibreChat documentation for current setup steps.

Track your self-hosted stack

Bookmark software to try, rate tools you've used, and keep your collection in one place.

Metadata extracted from README on Aug 9, 2026

Alternatives to LibreChat

LibreChat logo

LibreChat

46.9k
LibreChat is a self-hosted AI chat platform that unifies major AI providers in a ChatGPT-like interface.
Artificial IntelligenceAI InterfacesPermissive License+4
5 Containers
Details
NextChatAI logo

NextChatAI

88.9k
NextChat is a light, fast AI assistant web app and desktop client with support for multiple AI models and local browser storage.
Artificial IntelligenceAI InterfacesPermissive License+1
2 ContainersOpen Core
Details
AnythingLLM logo

AnythingLLM

68.1k
An all-in-one AI application for chatting with documents, building AI agents, and running local or cloud LLM workflows.
Artificial IntelligenceAutomation ToolsSelf Hosting Solutions+7
Single Container
Details
Open-WebUI logo

Open-WebUI

158.2k
Open WebUI is a self-hosted AI platform for chatting with LLMs, managing RAG, and building custom model workflows, designed to run entirely offline.
Artificial IntelligenceAI InterfacesLocal LLMs+7
2 ContainersOpen CoreFOSS with Issues
Details
Dify.ai logo

Dify.ai

160.8k
An open-source platform for building, testing, and operating LLM-powered applications with workflows, RAG, agents, and observability.
Low Code DevelopmentArtificial IntelligenceFOSS with Issues+6
36 ContainersOpen CoreFOSS with Issues
Details
HuggingFace Chat UI logo

HuggingFace Chat UI

11.0k
A SvelteKit chat interface for OpenAI-compatible LLM APIs, powering HuggingChat.
Artificial IntelligenceAI InterfacesSelf Hosting Solutions+1
Details
Chatbox logo

Chatbox

42.3k
Chatbox is a desktop AI copilot and chat client for ChatGPT, Claude, and other LLM providers on Windows, macOS, and Linux.
Artificial IntelligenceAI InterfacesLocal LLMs
Details
LobeHub logo

LobeHub

84.6k
LobeHub is a self-hostable platform for organizing, creating, and collaborating with AI agents as a team.
Artificial IntelligenceGenerative AISelf Hosting Solutions+4
10 Containers
Details

Related Software

LocalAI logo

LocalAI

50.3k
LocalAI is an open-source AI engine for running LLMs and other model types locally on a wide range of hardware, with drop-in API compatibility for several popular AI APIs.
Generative AIPermissive LicenseArtificial Intelligence+4
Single Container
Details
Ollama logo

Ollama

186.5k
Ollama is a tool for running open models locally and exposing them through a REST API for apps, agents, and integrations.
Artificial IntelligenceLocal LLMsGenerative AI+3
Details
LLM Harbor logo

LLM Harbor

3.3k
Harbor is a CLI and companion app for spinning up and managing a local LLM stack with pre-wired services like Open WebUI, Ollama, llama.cpp, SearXNG, Speaches, and ComfyUI.
Artificial IntelligenceLocal LLMsAI Tooling+5
Details
private-gpt logo

private-gpt

57.6k
PrivateGPT is an open-source API layer that turns local models into production AI applications.
Artificial IntelligenceAI RAG SystemsPermissive License+2
Details
big-AGI logo

big-AGI

7.2k
Big-AGI is a multi-model AI workspace for experts, focused on chat, model comparison, and local-first self-hosting.
Artificial IntelligenceAI InterfacesAI Media Generation+2
Open Core
Details
Onyx Community Edition logo

Onyx Community Edition

33.3k
Onyx is a self-hostable open source AI chat platform that works with any LLM and supports advanced search, agents, RAG, and connectors.
Generative AIPermissive LicenseArtificial Intelligence+5
Open Core
Details
Aider logo

Aider

50.0k
AI pair programming tool for working with large language models directly in the terminal.
Artificial IntelligenceAI Coding AssistantPermissive License+1
Details
SillyTavern logo

SillyTavern

35.5k
SillyTavern is a locally installed interface for interacting with text generation LLMs, image generation engines, and TTS voice models.
Artificial IntelligenceAI InterfacesCopyleft License+3
Single Container
Details
GPT4All logo

GPT4All

77.4k
GPT4All runs large language models privately on everyday desktops and laptops, and provides a Python client around llama.cpp implementations.
Artificial IntelligenceLocal LLMsAI Interfaces+2
Details
hermes-agent logo

hermes-agent

262.1k
Hermes Agent is a self-improving AI agent with a built-in learning loop, terminal UI, and messaging gateway for chatting and automating work across platforms.
Artificial IntelligenceAI AgentsAI Coding Assistant+2
2 Containers
Details
LiteLLM logo

LiteLLM

63.0k
LiteLLM is an open source AI gateway and Python SDK for calling 100+ LLM providers through a unified OpenAI-compatible interface.
API ManagementProxy ServersArtificial Intelligence+2
3 ContainersOpen Core
Details
AutoGPT logo

AutoGPT

188.0k
AutoGPT is a platform for creating, deploying, and managing continuous AI agents that automate complex workflows.
Artificial IntelligenceAutomation ToolsPermissive License+2
13 ContainersOpen Core
Details