# Why We Built Sahkarmi: The Open-Source AI Coworker That Never Acts Without Your Approval > Source: > Published: 2026-10-27 10:33:13+00:00 **By Dhrubojyoti Gangopadhyay (Founder, Sahkarmi)** *Website: [sahkarmi.site](https://sahkarmi.site) | GitHub: [github.com/ganguydhrubo/sahakarmi](https://github.com/ganguydhrubo/sahakarmi) | License: Apache-2.0* Over the past two years, the promise of autonomous AI agents has captured the imagination of every software engineer and startup founder. We were told agents would write our code, debug production incidents, handle customer support, and deploy our cloud infrastructure while we sleep. Yet in practice, most developers still hesitate to hand full control over to autonomous scripts. Why? `rm -rf`, drop a database table during a migration attempt, or overwrite critical configuration files. We asked ourselves: **What if autonomous AI agents didn't replace human judgement, but instead operated like trusted colleagues with built-in human verification gates?** That is why we built **Sahkarmi (सहकर्मी)** — the Hindi word for *coworker*. Sahkarmi is an **open-source desktop team workspace** where autonomous AI coworkers run locally on your own machine. Unlike traditional scripts or chat windows, Sahkarmi's agents are equipped with specialized tools — a sandboxed local terminal, filesystem access, an embedded Chromium browser, and persistent long-term memory — while strictly obeying a single foundational principle: **Zero Unapproved Impact**: An agent can plan, inspect files, draft code, and browse documentation autonomously; but the moment it attempts a sensitive action — such as executing a shell command, writing a file, submitting a web form, or executing a transaction — it pauses and presents a clear, interactive **Human-in-the-Loop Approval Card**. ``` [ Sahkarmi Human Verification Card ] -------------------------------------------------- Task: Deploy backend schema migration Agent: Dev_Backend_Coworker Proposed Command: python manage.py migrate --database=prod Working Dir: /home/user/project [ APPROVE ] [ REJECT ] [ REVISE ] -------------------------------------------------- ``` You maintain complete oversight. You can approve with a single keystroke, reject with corrective feedback, or take over directly. Sahkarmi never locks you into a proprietary LLM API. You can switch models per task: Sahkarmi is free and open-source under the **Apache-2.0** license. **Platform support, honestly stated:** Sahkarmi ships a **Windows 10/11 (x64)** desktop build today. macOS and Linux are planned but are *not* released yet — installer scripts exist in the repository but are not used for releases. Grab the latest signed release directly: `SHA256SUMS-windows.txt` so you can verify the download before running it. ``` git clone https://github.com/ganguydhrubo/sahakarmi.git cd sahakarmi bun install bun run dev ``` WinGet and Scoop manifests are submitted and currently awaiting review by their respective communities. Once those land, installation will also be a one-liner. Until then, please use the direct download above. We believe the future of software development belongs to collaborative human-AI teams, where humans provide intent and strategic oversight while autonomous coworkers handle the execution grind. If you try it, I would genuinely like to hear where the approvals model gets in your way — that feedback is what shapes the roadmap.