DEDUPEDAI Job Search
An open-source framework built on Claude Code that runs a job search on your own machine: it evaluates postings, tailors CVs and cover letters, and preps interviews.
5 use cases: Tailor a CV and cover letter to one job posting; Rank a batch of scraped jobs into a shortlist; Prepare a stage-specific interview pack · GitHub
Solidcraft
SolidCraft is an open-source parametric 3D CAD application written in pure Rust, with desktop, browser, headless CLI and MCP server versions.
3 use cases: Have an AI agent model a part through SolidCraft MCP; Run a JSON script to export a bracket as STEP; Design an enclosure whose height updates from Parameters · GitHub
Fastbrowse
fastbrowse is a Python browser agent where a choice model picks each action from the controls on a page, and answers come back with verbatim quotes from that page.
4 use cases: Get a cited answer from a live web page; Log in from a Bitwarden vault and stop before submitting; Add items to a cart in a profile that stays signed in · GitHub
Awesome AI Agent Platforms
A curated, license-annotated list of open-source AI agent platforms, frameworks, workflow automation tools, browser agents, and coding agents.
4 use cases: Shortlist self-hosted AI coworkers for a team; Choose a workflow automation tool that includes AI steps; Pick a Python agent framework for a multi-agent prototype · GitHub
Nautilo
Nautilo is a self-hosted, open source (MIT) workspace where people and their AI Genies work together in shared Rooms across desktop, mobile, and web.
3 use cases: Run Nautilo locally on a Mac and make a first document; Deploy a shared Nautilo server for your team; Build and check Nautilo from source before a code change · GitHub
Dontbemichael
Don't Be Michael is a desktop app for Mac and Windows that runs a small office of AI team members for a business, each built on Claude Code and working from its own folder and memory.
4 use cases: Set up an AI office for your small business; Sort and answer your support inbox on a schedule; Approve each sales email before it leaves · GitHub
Auto Swarm Shadow Adapter
A Python adapter that lets AutoSwarm agentic DAG tasks pause for a human reviewer or a remote worker without blocking parallel branches, with state kept in SQLite.
4 use cases: Pause a legal review step for human sign-off; Serve a developer seat from a local GPU model; Fill a QA seat with a remote OpenAI key · GitHub
Long Horizon Harness
LongHorizon-Harness is a loop that runs existing AI agents such as Claude Code, Codex, and OpenCode on desktop apps and the terminal for long tasks, checking results and saving verified progress along the way.
3 use cases: Run a long desktop task from the browser; Delegate a terminal task to a chosen agent; Split planning, execution, and auditing across models · GitHub
Partmode
PartMode is an open-source, browser-based parametric 3D CAD application built on OpenCascade WebAssembly, with typed, permissioned agent access to the same document model.
4 use cases: Model a parametric part in a local PartMode browser; Let an approved MCP agent revise an open CAD project; Run unattended CAD edits on a durable headless project · GitHub
Headcount
Headcount is a set of AI agent skills organized as a company, with departments such as security, finance, and product that you install separately into Claude Code, ChatGPT, or Codex.
4 use cases: Review a design for threats before building it; Check whether a planned hire is affordable; Diagnose why a landing page is not converting · GitHub
Foxprofile
FoxProfile is a free, self-hosted manager for anti-detect browser profiles, each with its own fingerprint, cookies and proxy, that people and AI agents can run locally or on a VPS.
5 use cases: Keep several accounts in separate browser identities; Let an AI agent browse a logged-in profile; Run profiles on a VPS and view their screens remotely · GitHub
Open Bot
OpenBot is an open-source, self-hosted template for AI coworkers that each get their own browser, files and tools, with every action checked before it runs and logged after.
4 use cases: Run a private AI coworker on your own laptop; Gate a Bot's browser actions with deny rules; Bring your own AG-UI agent as a Bot · GitHub
Hermes Office
HermesOffice is a free, open-source AI Office suite for macOS, Windows, and Linux that opens and edits Word, Excel, PowerPoint, PDF, and Markdown files.
4 use cases: Convert a PDF into an editable Word file on your own machine; Rewrite sections of a Word document with AI, using your own key; Correct text in a PDF while keeping the original fonts · GitHub
Utopia
Utopia is an open-source, self-hosted enterprise knowledge base in Rust that stores facts with time awareness, so you can ask what was true at a given date and what the base knew then.
4 use cases: Find which contract terms applied on a given date; Show who held a role in a past quarter and what was known then; Connect a coding agent to a knowledge base over MCP · GitHub
Doma
DomA is an open-source AI web automation agent that runs inside Chrome or Edge as a browser extension, handling tasks like browsing, filling forms, clicking, and collecting information.
3 use cases: Fill repetitive web forms with DomA in your browser; Collect data from web pages using a browser agent; Build and modify DomA from its open-source source code · GitHub
Tel Agent
Tel-Agent is an open-source, self-hosted gateway that connects phone lines and messaging channels to AI agents, using your own provider keys.
4 use cases: Answer business phone calls with an AI agent on your PBX; Answer website chat and messaging apps from one assistant; Run a local AI phone and chat dashboard on Windows · GitHub
Text to Cad
text-to-cad is a plugin and skill set that lets AI agents generate 3D CAD models from text and run related manufacturing and drawing workflows locally.
4 use cases: Generate a 3D CAD model from a text description; Check a generated part for manufacturing problems; Create an engineering drawing from a CAD model · GitHub
Botdirectory AI
An open-source, community-maintained directory of ready-to-use agent prompts for Grok Bot, Rakazo, and other agents, with a public read API, JSON feeds, and a pull request workflow for adding bots.
4 use cases: Find a ready-made bot prompt and paste it into your agent; Mirror the whole bot directory into your own catalog; Scout new bot listings on a schedule without rereading the full feed · GitHub
Invisible Playwright MCP
A Playwright MCP server and web UI that lets an AI agent drive a stealth Firefox browser that the README says is invisible to anti-bots.
4 use cases: Compare flight fares across a date range from your assistant; Run a web browsing agent in a local chat window; Keep logins and cookies between agent browsing runs · GitHub
Big Arrow on the Screen
big-arrow-on-the-screen (bigarrow) is a macOS command-line tool and skill for Claude Code and Codex that draws arrows, boxes and text signs over any window without taking focus or capturing the screen.
4 use cases: Point a human at the Allow button an agent cannot press; Walk someone through an app one control at a time; Point at the right browser tab out of many · GitHub
Genoffice
GenOffice is a free, open-source desktop office suite for macOS, Windows and Linux that edits real .docx, .xlsx, .pptx and PDF files with a built-in AI agent, and ships a genoffice command line and agent skill.
5 use cases: Have AI revise a Word file and review every change; Let a coding agent build decks and workbooks locally; Find the office file that answers your question · GitHub
Awesome Fde Resources
A curated GitHub list of books, guides, case studies, tools, and opportunities for Forward Deployed Engineers working on production AI delivery.
4 use cases: Pick evaluation tools for a customer LLM app; Find a reference build for a customer workflow; Harden a customer-facing agent before launch · GitHub
Halofy
Halofy is an open source access and governance layer that gives AI agents across an organization one server-resolved identity, policy model, provenance trail, audit log, and signed erasure.
4 use cases: Run the offline governed context demo; Connect an AI agent to shared context over MCP; Review agent access and audit in the control room · GitHub
Open Jev Verdict 2 0
A 149.6M parameter non-autoregressive decision model that classifies typed enterprise decisions (Choice, Score, Noul) and returns calibrated confidence estimates.
3 use cases: Auto-approve confident decisions and escalate the rest; Test typed decisions in the browser with no backend; Measure how often answers flip when options are reordered · GitHub
Movo
MOVO is a self-hosted enterprise Agent platform built on DeepSeek Harness, with a user workspace, admin console, knowledge, research, content generation and governance.
5 use cases: Stand up a self-hosted Agent workspace for a team; Run multi-round research with cited sources; Turn research material into a report or slide deck · GitHub
Yowes
Yowes is a headless MCP server in Python that generates realistic teacher verification documents, such as ID cards, licenses, and letters, for 13 countries.
3 use cases: Generate synthetic teacher documents as test fixtures; Give an AI agent a country-aware document generator tool; Add a new country generator to the Yowes codebase · GitHub
Skills
A pair of Claude skills, eli5-succinct and summary, that produce a short plain-language explanation in chat or one self-contained HTML summary page.
3 use cases: Get a short plain-language explanation in chat; Turn a repo's current work into one HTML summary page; Make a summary page accessible for ADHD or dyslexia readers · GitHub
Doop
Doop is an open-source multiplayer design canvas where humans and AI agents design together live, with a built-in MCP server.
4 use cases: Design a page section live with Claude Code on a canvas; Self-host a private team design canvas with Docker; Queue design cards for the built-in Doop Agent · GitHub
Kition
Kition is a desktop workspace that combines Markdown documents, structured tables, an infinite Whiteboard, a tool-using AI agent, web research, and visual workflows.
5 use cases: Review agent edits to a Markdown document line by line; Turn receipt photos into searchable table records; Generate 16:9 and 9:16 thumbnail batches from a table · GitHub
Lotvulture
Lot Vulture is a source-available app that runs computer vision on existing IP or RTSP camera feeds to show live parking space occupancy.
4 use cases: Show live space-by-space occupancy from existing cameras; Push lot availability to road signs and Home Assistant; Audit past lot use with the scrubbing timeline · GitHub
Laya PHP
A PHP SDK for classifying text with Laya, a self-hosted multilingual decision engine that returns typed enums, ints and bools without an LLM API bill.
4 use cases: Route support tickets by department, urgency and churn risk; Block abusive or spam text in Laravel form submissions; Unit-test classification code without a running server · GitHub
AI Employees
Open source AI Employees: folders of scheduled routines, one per business role, that run on your own machine through the AI agent you already use.
4 use cases: Run a product launch with a GTM Engineer; Publish one SEO article every weekday; Triage the customer inbox with drafted replies · GitHub
Skill Recorder
Skill Recorder is a desktop app that records your on-screen work session and uses the GitHub Copilot CLI to turn it into an intent, ordered steps, and a reusable Skill or scheduled Automation.
4 use cases: Turn one recorded task into a reusable Skill; Schedule a recorded task as a recurring Automation; Capture a terminal workflow as a Skill with native tools · GitHub
Open Maus Bot
OpenMausBot is an open-source chat app where each bot is a local Claude, Codex or Grok agent with its own model, cloud computer and connected apps.
4 use cases: Install a complete bot team from one Markdown file; Share a configured bot team as one file; Let a bot work on your Mac with approval on each step · GitHub
Nuphus MCP
nuphus-mcp is a Rust stdio MCP server that lets AI agents see the screen, control windows, mouse and keyboard, and drive Chrome or Edge.
4 use cases: Automate a signed-in website with one saved browser profile; Drive an existing anti-detect browser window over CDP; Operate a native desktop app by its accessibility tree · GitHub
AI Charter
A public website and open registry for the Universal AI Charter, a set of plain-language AI governance principles, where companies can certify their AI models.
4 use cases: Certify a model and submit it to the public registry; Propose a new hazard placard category; Check a certification file before submitting it · GitHub
Any Jev
AnyJev is a Python library that turns an LLM into a decision model: you give it a state and a typed question, and it returns an answer with a probability over the options, read from the model's next-token distribution.
3 use cases: Route support tickets to one option with a probability; Route tickets on an open LLM with no training or labels; Share one decision endpoint with a capped reasoning budget · GitHub
Bops
Bops is a Mac app that runs a team of AI bots for business operations such as inbox, pipeline, invoices and reports, each working on its own cloud computer.
4 use cases: Hand inbox triage and reports to a bot team on Mac; Self-host the Bops server on your Mac with your keys; Send tasks to your bot by email, text or phone call · GitHub
Scout
Scout is an open-source TypeScript agent that uses a real browser to carry out a task described in plain words and returns the answer.
4 use cases: Pull a ranked list from a website with one task; Compare prices and stock across product pages; Fill in a web form and confirm what the site received · GitHub
Multi Agent CAD
MAC is a Python framework that turns natural-language design briefs into editable CAD parts and multi-part assemblies, exported as STEP, STL, and GLB files.
5 use cases: Generate an editable printable part from a text brief; Run a local browser UI to generate and download parts; Review generated CAD with QA reports and repair history · GitHub
Work Humanizer
work-humanizer is an Agent Skill that removes AI tone from work writing while keeping every fact, commitment and caveat at the same strength.
3 use cases: Remove AI tone from a work email without changing its commitments; Get a specific work draft built from your answers, not guesses; Turn your notes or transcript into a human-sounding work piece · GitHub
Pinloop CLI
A terminal job board CLI that lets coding agents search, pull, and judge worldwide white-collar job postings.
3 use cases: Judge job postings against your resume; Count matching postings before pulling them; Schedule automatic scans for new postings · GitHub
Browser Kitten
Paw Work is an unpacked Chrome extension that runs an AI agent in a side panel to act on your live, logged-in browser tab and produce sheet, document, or site HTML files.
3 use cases: Turn data on a logged-in page into an editable sheet; Draft a site HTML artifact from a live browser session; Run regression tests before changing the extension · GitHub
Laya
Laya is an open-source System 1 decision model that a Node.js or TypeScript program can run locally through ONNX Runtime to answer typed questions about a state with calibrated probabilities, without generating text.
4 use cases: Route support tickets to teams with probabilities; Auto-act on confident answers and queue the rest; Bake Laya weights into a container image at build time · GitHub
Py Idp
py-idp is an open-source Python library for intelligent document processing that uses LLM backends and Pydantic schemas to pull structured fields out of documents.
4 use cases: Extract invoice fields into a validated schema; Route low-confidence fields to a human reviewer; Measure extraction accuracy with the eval harness · GitHub
Meetcap
MeetCap is a Mac meeting assistant that records and transcribes meetings on your computer, writes live summaries and minutes, and lets an AI agent start recordings and search past meetings.
3 use cases: Find what was agreed in past meetings by asking your agent; Keep minutes local for meetings that cannot leave the room; Get live summaries and minutes from your background agent · GitHub
Humanizer Local Model
A 12B local model that rewrites AI-written drafts so they read like a person wrote them, keeping numbers, names, dates and quotes, and running on your own computer.
4 use cases: Rewrite an AI-drafted email offline before sending it; Rewrite a long Markdown or Word document in one command; Rewrite a report while keeping chosen quotes word for word · GitHub
Start Lux Decision
StartLux-Decision is an open inference engine and HTTP server for a family of decision models that return a calibrated probability for every option of typed questions.
3 use cases: Route support tickets to teams with typed decision questions; Test decision requests on the hosted 27B model without a GPU; Send decisions with no fitting option to a person · GitHub
Superpower
Superpower is a browser extension and Windows desktop app that lets AI web chats and a native workspace call local or remote MCP tools and return the results to the same conversation.
4 use cases: Summarize a web page inside your AI chat; Build research Projects from saved web and YouTube sources; Send a research set to a notes or file MCP tool · GitHub
Strands Decider
Strands Decider is a small, fast decision model that picks between options, answers yes or no, or rates text on a scale, with a confidence score on each answer.
4 use cases: Route support messages to the right team; Flag messages that convey urgency; Serve a scorer that other services can call · GitHub
Tab Tin
TabTin is an open source workspace where people and multiple AI agents share tasks, context, documents, and results.
4 use cases: Run Tab Tin from source on your own machine; Hand off an AI task with its context to a colleague; Turn agent results into shared online documents and sheets · GitHub
Type LLM
TypeLLM is a Python library that makes open autoregressive LLMs return type-safe answers (strings, numbers, booleans, enum choices, objects and arrays) by constraining generation with JSON Schema, either through the hosted TypeLLM API or a model you serve with SGLang.
4 use cases: Extract typed fields from receipts into structured data; Route support tickets to the right team with fixed choices; Pull every line item from a document into a typed list · GitHub
QM
QM is a self-hosted multiplayer agent harness that gives each person and each room in a company its own scoped agent, reachable through Slack and a web app.
4 use cases: Deploy a shared agent for your team in Slack and web; Track a project in a shared Slack channel; Triage your inbox on a schedule in your own voice · GitHub
Other categories · All use cases · Hot repos
Questions
What is the best AI repo for Work and operations in 2026?
Right now the top pick on Deduped is AI Job Search: An open-source framework built on Claude Code that runs a job search on your own machine: it evaluates postings, tailors CVs and cover letters, and preps interviews.
How are these Work and operations repos ranked?
By how hot they are on GitHub (stars gained and mentions in the AI sources we track), then by how many practical use cases we found. The list is rebuilt every day.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them free