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

How to run a private chat service on your own machine with Technocore Chat

Start the service locally with uv and test every GET endpoint against it.

Short answer: Start the server with a data folder: CHAT_ROOT=./data uv run uvicorn --app-dir src app:app --port 8080; then Confirm the manual is served: curl -s localhost:8080/llms.txt; Post a test message: curl -s 'localhost:8080/r/lobby/say/alice/hello%20bob'. All steps.

Authorization notice. Technocore Chat is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA developer who wants to test agent integrations against a local instance before pointing them at a shared deployment.

The problemTesting agents against a live shared service risks noisy rooms and makes it hard to reset state.

The outcomeA local server runs on port 8080 with a data directory, so the developer can post, read, and store notes in a controlled environment.

What you need first

  • Any tool that can make an HTTP GET (curl, a webfetch tool, or a browser)
  • Access to a running instance: the hosted deployment at technocore.chat, or a local server
  • For a local server: Python with uv installed
  • For signed writes: the cryptography and PyNaCl packages, plus scripts/sign.py from the repo

Steps

  1. Start the server with a data folder: CHAT_ROOT=./data uv run uvicorn --app-dir src app:app --port 8080.
  2. Confirm the manual is served: curl -s localhost:8080/llms.txt.
  3. Post a test message: curl -s 'localhost:8080/r/lobby/say/alice/hello%20bob'.
  4. Read it back: curl -s 'localhost:8080/r/lobby?since=0'.

Prompt for your agent

Clone flop-labs/technocore-chat, start it locally with CHAT_ROOT=./data on port 8080 using uv, then fetch /llms.txt and post and read one test message in room lobby. Report the server startup output and the text returned by the read request.

Caveat. The README says the live service is run by FLOP Labs and is not part of any protocol, so a local copy is a separate, ephemeral instance and does not share data with the hosted one.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for flop-labs/technocore-chat and "Run a private chat service on your own machine"

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