Tools/LibreChat-AI/LibreChat

LibreChat

Enhanced ChatGPT clone with multiple AI providers

46.2k ★+392/wkgrowthTypeScriptMIT License →trending

View on GitHub →Compare in AI Chat Clients →Homepage →

Replaces:ChatGPT

See how it compares →

The Lens

By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.

Updated Oct 2026

LibreChat is a self-hosted ChatGPT replacement: one chat window for Claude, GPT, Google, Bedrock, Ollama and any OpenAI-compatible API, with agents, MCP tools, artifacts and search built in. It's MIT licensed with no paid tier, and ClickHouse bought it in November 2025, so a company now funds the work.

Setup is Docker Compose, but it's a real stack: the app, an admin panel, MongoDB, Meilisearch, Postgres with pgvector and a RAG API. Running code needs a separate service you deploy yourself. Releases ship constantly, and the README says to check the changelog for breaking changes before upgrading.

You bring your own API keys, so the bill is model spend plus a server. Login covers OAuth, SAML, LDAP and two-factor. Solo: free, worth it if you want every model behind one login. Small teams: free, one deployment with shared agents. Larger teams: free, but budget engineer time for patching.

The catch is security. LibreChat has published nearly 30 advisories since mid-2025, three rated critical in 2026, including one where any registered user could run shell commands as root inside the container. All are patched. This server holds everyone's API keys, so stay current and keep it off the open internet.

Free vs Self-Hosted vs Paid

fully free

Free: Everything in the repo, MIT licensed: multi-provider chat, agents with MCP tools and skills, artifacts, web search, message search, OAuth/SAML/LDAP login with two-factor, and a browser-based admin panel for users, groups and roles. No paid edition and no gated features.

Self-hosted: The only way to run it. The default Docker Compose file starts the app, the admin panel, MongoDB, Meilisearch, Postgres with pgvector and the RAG API. Code execution needs ClickHouse's separate code-interpreter service (Apache 2.0, Docker Compose or Helm). One-click templates exist on Railway, Zeabur and Sealos, billed by those hosts. Your running costs are the server plus whatever model APIs you connect; local models through Ollama remove the API bill if you have the hardware.

Paid: No paid LibreChat tier. ClickHouse, which owns the project, offers ClickHouse Agents (Beta) inside ClickHouse Cloud as a hosted agent product "built on the same foundation", with no public price. The real cost is the model APIs and the engineer time to keep a multi-service stack patched.

Free with nothing gated. You pay for the server and your model API usage, and the hidden cost is keeping a multi-container stack on the latest security patches.

What to do by team size

Solo: free; worth it if you want every model behind one login
Small team: free; one deployment with shared agents and per-user logins
Medium team: free; put SSO in front and use the admin panel's roles and groups
Large team: free, but assign someone to track security advisories and upgrades

Self-hosting ops:moderate

Get tools like this every Wednesday

One featured tool, three on the radar. No fluff.

Similar Tools

deer-flow95similar

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.