Show HN: Zuckerman – minimalist personal AI agent that self-edits its own code
by ddaniel10 on 2/1/2026, 1:50:15 PM
https://github.com/zuckermanai/zuckerman
Comments
by: aaaalone
I will not download or use something which constantly reminds me of this weird dude suckerberg who did a lot of damage to society with facebook
2/1/2026, 5:05:50 PM
by: asim
I started working on something similar but for family stuff. I stopped before hitting self editing because, well I was a little bit afraid of becoming over reliant on a tool like this or becoming more obsessed with building it than actually solving a real problem in my life. AI is tricky. Sometimes we think we need something when in fact life might be better off simpler.<p>The code for anyone interested. Wrote it with exe.dev's coding agent which is a wrapper on Claude Opus 4.5<p><a href="https://github.com/asim/aslam" rel="nofollow">https://github.com/asim/aslam</a>
2/1/2026, 5:41:22 PM
by: 4b11b4
DIY agent harnesses are the new "note taking"/"knowledge management"/"productivity tool"
2/1/2026, 3:41:23 PM
by: ddaniel10
Hi HN,<p>I'm building Zuckerman: a personal AI agent that starts ultra-minimal and can improve itself in real time by editing its own files (code + configuration). Agents can also share useful discoveries and improvements with each other.<p>Repo: <a href="https://github.com/zuckermanai/zuckerman" rel="nofollow">https://github.com/zuckermanai/zuckerman</a><p>The motivation is to build something dead-simple and approachable, in contrast to projects like OpenClaw, which is extremely powerful but has grown complex: heavier setup, a large codebase, skill ecosystems, and ongoing security discussions.<p>Zuckerman flips that:<p>1. Starts with almost nothing (core essentials only).<p>2. Behavior/tools/prompts live in plain text files.<p>3. The agent can rewrite its own configuration and code.<p>4. Changes hot-reload instantly (save -> reload).<p>5. Agents can share improvements with others.<p>6. Multi-channel support (Discord/Slack/Telegram/web/voice, etc).<p>Security note: self-edit access is obviously high-risk by design, but basic controls are built in (policy sandboxing, auth, secret management).<p>Tech stack: TypeScript, Electron desktop app + WebSocket gateway, pnpm + Vite/Turbo.<p>Quickstart is literally:<p><pre><code> pnpm install && pnpm run dev </code></pre> It's very early/WIP, but the self-editing loop already works in basic scenarios and is surprisingly addictive to play with.<p>Would love feedback from folks who have built agent systems or thought about safe self-modification.
2/1/2026, 1:50:15 PM
by: falloutx
Terrible name, kind of a mid idea when you think about it (Self improving AI is literally what everyone's first thought is when building an AI), but still I like it.
2/1/2026, 5:23:11 PM
by: amelius
Sounds cool, but it also sounds like you need to spend big $$ on API calls to make this work.
2/1/2026, 3:42:15 PM
by: pillbitsHQ
[dead]
2/1/2026, 5:59:35 PM
by: pillbitsHQ
[dead]
2/1/2026, 2:49:20 PM