---
title: "Show HN: Lynx – open-source fully-customizable AI workspace"
slug: "lynx-macht-aus-ai-agenten-ein-frei-konfigurierbares-arbeitscockpit"
date: 2026-11-12
category: community
tags: [anthropic, agents, open-source]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/lynx-macht-aus-ai-agenten-ein-frei-konfigurierbares-arbeitscockpit
---

# Show HN: Lynx – open-source fully-customizable AI workspace

**Published**: 2026-11-12 | **Category**: community | **Sources**: 1

---

## TL;DR

I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.

---

## Summary

I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx. Lynx lets you quickly build fully custom interfaces connected to your data sources (e.g. via MCP or API) and trigger agents running on your machine from them (e.g. with Claude Code or Codex). I built it as an experiment but have found myself doing 80-90% of my work from inside Lynx. I have my own Conductor-like workspace for coding, a Mail client, a workspace for my writing, and various others for dashboards and explorations.

---

## Why it matters

I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.

---

## Key Points

- I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.
- Lynx lets you quickly build fully custom interfaces connected to your data sources (e.
- via MCP or API) and trigger agents running on your machine from them (e.
- with Claude Code or Codex).
- I built it as an experiment but have found myself doing 80-90% of my work from inside Lynx.

---

## Nauti's Take

The best first test is a small, clearly bounded workflow, such as PR review or copy editing with a local agent triggered by a custom button. Check permissions, data flow, and failure handling first, because the productivity gain depends more on reliable integrations than on the visual interface.

---


## FAQ

**Q:** What is Show HN about?

**A:** I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.

**Q:** Why does it matter?

**A:** I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.

**Q:** What are the key takeaways?

**A:** I was finding that managing multiple agent threads with walls of text was getting tiring and inefficient for me and that I wanted a more visual way to interact with my agents, so I built Lynx.. Lynx lets you quickly build fully custom interfaces connected to your data sources (e.. via MCP or API) and trigger agents running on your machine from them (e.

---

## Related Topics

- [anthropic](https://news.ainauten.com/en/tag/anthropic)
- [agents](https://news.ainauten.com/en/tag/agents)
- [open-source](https://news.ainauten.com/en/tag/open-source)

---

## Sources

- [Show HN: Lynx – open-source fully-customizable AI workspace](https://github.com/yakkomajuri/lynx) - Hacker News AI

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-11-13*