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

How to use Work Wit AI Agent: what you can do with it

WorkWit is a self-hosted, MIT-licensed AI Agent platform for office work, with built-in contract review and resume screening, deployed with one Docker Compose command.

Trended earlier

View repo on GitHub

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

What do you want to do?

4 use cases

  • Deploy a self-hosted office AI agent on your own server

    Run WorkWit on a Linux server with Docker Compose and connect it to your own model endpoints.

    View prompt
    In the WorkWit-AI-Agent repo at <repo-path>, set up .env with the four model endpoints at <model-base-url> and <model-key>, then start the stack with docker compose up -d --build. Expected output: the backend container running and the web app reachable on port 4001. Verify that docker compose logs shows no startup errors and that the admin password has been changed.

  • Score resumes against a job profile in minutes

    Upload a resume and a job profile to get key candidate fields, a match score, and a recommendation.

    View prompt
    Using the WorkWit-AI-Agent repo deployed at <app-url>, run Resume Screening on <resume-file> against the job profile <job-profile-file>. Expected output: key candidate fields, a match score, and a recommendation. Verify that the score is explained by fields that appear in the resume text.

  • Get contract risk points from your side's stance

    Upload a contract as txt, docx, or pdf and get risk points and revision suggestions for Party A or Party B.

    View prompt
    Using the WorkWit-AI-Agent repo at <app-url>, run Contract Review on <contract-file> with the stance set to <Party A or Party B>. Expected output: structured risk points and revision suggestions. Verify that each risk points to a clause that actually appears in the uploaded contract.

  • Add an MCP server's tools to the WorkWit agent

    Point WorkWit at an MCP server through data/mcp.json so its tools join the agent's catalog.

    View prompt
    In the WorkWit-AI-Agent repo at <repo-path>, add an MCP connector for <mcp-server-name> in data/mcp.json using the <transport> transport, then rebuild the stack. Expected output: the external tools listed in the Tool Library. Verify that a test agent task calls one of those tools and returns a result, and that data/mcp.json is not committed to git.

Quick start with Work Wit AI Agent

  1. Check you have what it needs: A Linux server (Ubuntu 22.04 recommended) with Docker and the docker compose plugin; Four OpenAI-compatible model endpoints with addresses and keys for chat, vision, embed, and rerank roles; Git access to the repo.
  2. Open crane-in-clear-sky/WorkWit-AI-Agent on GitHub and read the README and license.
  3. Clone the repo: git clone https://github.com/crane-in-clear-sky/WorkWit-AI-Agent ~/workwit, then run cd ~/workwit (inferred, check the README)
  4. Install Docker if needed: curl -fsSL https://get.docker.com | sudo sh, then sudo usermod -aG docker $USER
  5. Copy the template: cp .env.example .env, then set the four MODEL_*_BASE and MODEL_*_KEY pairs to your real addresses and keys
  6. Start the stack: docker compose up -d --build, then check docker compose logs -f backend for errors

These steps come from our top use case, Deploy a self-hosted office AI agent on your own server, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for crane-in-clear-sky/WorkWit-AI-Agent

Add Deduped to Claude Code once

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

Cursor, ChatGPT, others

Work Wit AI Agent alternatives · Best AI repos for Work and operations

About this repo

Requirements

  • A Linux server (Ubuntu 22.04 recommended) with Docker and the docker compose plugin
  • Four OpenAI-compatible model endpoints with addresses and keys for chat, vision, embed, and rerank roles
  • Git access to the repo

Add this badge to your README

Maintain Work Wit AI Agent? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/crane-in-clear-sky/WorkWit-AI-Agent.svg)](https://dedupedai.com/use-cases/crane-in-clear-sky-workwit-ai-agent/?utm_source=github&utm_medium=badge&utm_campaign=crane-in-clear-sky-WorkWit-AI-Agent)

HTML 

<a href="https://dedupedai.com/use-cases/crane-in-clear-sky-workwit-ai-agent/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=crane-in-clear-sky-WorkWit-AI-Agent"><img src="https://dedupedai.com/badge/crane-in-clear-sky/WorkWit-AI-Agent.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Work Wit AI Agent

What is Work Wit AI Agent?

WorkWit is a self-hosted, MIT-licensed AI Agent platform for office work, with built-in contract review and resume screening, deployed with one Docker Compose command. It is an open-source project on GitHub: https://github.com/crane-in-clear-sky/WorkWit-AI-Agent.

Who is Work Wit AI Agent for?

IT admins and team leads who want an on-premises AI office assistant for contracts, resumes, and agent tasks, using their own model endpoints.

What can I do with Work Wit AI Agent?

4 use cases so far, for example: Deploy a self-hosted office AI agent on your own server; Score resumes against a job profile in minutes; Get contract risk points from your side's stance. Each has steps and a copy-paste agent prompt.

What do I need to run Work Wit AI Agent?

A Linux server (Ubuntu 22.04 recommended) with Docker and the docker compose plugin; Four OpenAI-compatible model endpoints with addresses and keys for chat, vision, embed, and rerank roles; Git access to the repo.

What are alternatives to Work Wit AI Agent?

Other hot AI repos in Work and operations: Sprawling Agents, GPT 6 Astra Skill, Apowerb, Punctual, Subpool.

Is Work Wit AI Agent safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.