DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to put one OpenAI-compatible endpoint in front of every model with Fastllm Proxy

Run the proxy with Docker so apps call one address while it routes to local and cloud backends.

Short answer: Run git clone https://github.com/azrtydxb/Fastllm-proxy && cd Fastllm-proxy; then start with docker compose up -d; set an admin password with the set-password command from the README. All steps.

Credentials. The proxy stores provider keys centrally, so protect the management UI and change the example password.

Who it is forA platform engineer tired of every team wiring up provider keys separately.

The problemEach app talking to providers directly means scattered keys and no central control.

The outcomeOne endpoint on port 4000 and a management UI on 4001.

What you need first

  • Docker and Docker Compose
  • At least one inference backend or provider key

Steps

  1. Run git clone https://github.com/azrtydxb/Fastllm-proxy && cd Fastllm-proxy
  2. Start with docker compose up -d
  3. Set an admin password with the set-password command from the README
  4. Point clients at port 4000 and open the UI on 4001

Prompt for your agent

Deploy azrtydxb/Fastllm-proxy with `docker compose up -d`, add <backend>, and send one chat request through port 4000. Confirm it appears in the management UI.

Caveat. It reads LiteLLM-format config files unchanged, so an existing LiteLLM setup can be pointed at it.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for azrtydxb/Fastllm-proxy and "Put one OpenAI-compatible endpoint in front of every model"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer