Desktop app to run Python agents over TCP with live server geolocation
I built an open-source desktop app for running and monitoring Python agents that talk over TCP. It works on macOS, Linux, and Windows. The basic idea is simple: if a repo has an `agent.py` entrypoint, the app can import it from GitHub, install `requirements.txt` if needed, connect it to a TCP server, and show what it is doing in one UI. Current features: * import agent repos from GitHub, including private repos * run agents through `agent.py` * optional `requirements.txt` support * optional `id.json` for agent metadata * connect agents to TCP servers * inspect message flow in one place *…
What it does
In the maker’s words, at launch
I built an open-source desktop app for running and monitoring Python agents that talk over TCP. It works on macOS, Linux, and Windows. The basic idea is simple: if a repo has an `agent.py` entrypoint, the app can import it from GitHub, install `requirements.txt` if needed, connect it to a TCP server, and show what it is doing in one UI. Current features: * import agent repos from GitHub, including private repos * run agents through `agent.py` * optional `requirements.txt` support * optional `id.json` for agent metadata * connect agents to TCP servers * inspect message flow in one place * map/network view showing where connected servers are I originally built this because managing multiple agents by hand across terminals and scripts gets messy fast. This is not an agent framework. It is more of an operational layer for Python repos that already follow a simple entrypoint and communicate over TCP. Repo: https://github.com/Summoner-Network/summoner-desktop Demo: https://youtu.be/yvD712Uj3vI Interested in feedback on whether this workflow makes sense, and what might be missing for real multi-agent setups.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
