OpenJet
Hi HN, I am building a Terminal User Interface (like Claude Code) for self-hosted AI agents on Jetsons. Works in air-gapped environments. Unlike other solutions, this is optimised for unified memory machines, as to avoid OOM errors. The agent can do stuff like edit, read, create files - manage and interpret data locally. Currently, it gets ~17 tok/s on Jetson Orin Nano 8GB using Qwen3-4B-Instruct-4bit In the future, adding TensorRT .engine support which will boost inference further. I am trying to get the memory footprint down, so if anyone has knowledge on kv cache optimisation, that…
OpenJet launched on March 5, 2026 with 4 votes, #2,516 of 23,380 launches that month and more than 75% of that year's launches.
What it does
Agentic Terminal User Interface for NVIDIA Jetson devices for local LLMs without any internet connection. Think Claude Code for edge compute. Fully local operation. No cloud transport, no API keys, no latency. All inference and logs stay on-device. It works with unified memory systems where memory management is crucial
Run Qwen and other local LLMs as private coding agents on your own hardware. OpenJet configures the runtime, repo tools, and Python SDK—no API key.
OpenJet profiles your hardware, configures Qwen or another open model, and gives you a terminal coding agent plus a Python SDK — without sending your code or prompts to a hosted API. $ pip install open-jet Copy ~/openjet Pause ♡ Runs locally. Stays local. Yours by default. + OpenJet’s job is the part nobody wants to do: profiling the hardware, picking a model that fits it, and configuring the local runtime. What you point at that runtime is up to you. Install it, run setup, and open the agent. It reads and searches files, applies edits, resumes sessions, and asks before it runs anything that changes state. Same harness, no terminal. Open an inference session and call it — the model runs on…from openjet.dev
In the maker’s words, at launch
Hi HN, I am building a Terminal User Interface (like Claude Code) for self-hosted AI agents on Jetsons. Works in air-gapped environments. Unlike other solutions, this is optimised for unified memory machines, as to avoid OOM errors. The agent can do stuff like edit, read, create files - manage and interpret data…
Does a similar job
all alternatives →
ReplicasJun 2026 · replicas.dev · ▲239Hey HN! I'm Connor, creator of Replicas. I'm a heavy Codex/Claude Code user, and I wanted to hand off tasks to agents like I would to an engineer - kick something off before work, let it scaffold while I'm at lunch, even come back to a ready PR. The problem: existing alternatives use workspace VMs that are black boxes. I have no access to any of them - they can't run tests, read logs, or use tools like the Playwright MCP (which I use to verify agents actually fixed what they claim to fix). Replicas gives agents real cloud workspaces where they can: - Run your test suite and read the…
Context GatewayMar 2026 · github.com · ▲220We built an open-source proxy that sits between coding agents (Claude Code, OpenClaw, etc.) and the LLM, compressing tool outputs before they enter the context window. Demo: https://www.youtube.com/watch?v=-vFZ6MPrwjw#t=9s. Motivation: Agents are terrible at managing context. A single file read or grep can dump thousands of tokens into the window, most of it noise. This isn't just expensive — it actively degrades quality. Long-context benchmarks consistently show steep accuracy drops as context grows (OpenAI's GPT-5.4 eval goes from 97.2% at 32k to 36.6% at 1M…
Skill that lets Claude Code/Codex spin up VMs and GPUsFeb 2026 · cloudrouter.dev · ▲138I've been working on CloudRouter, a skill + CLI that gives coding agents like Claude Code and Codex the ability to start cloud VMs and GPUs. When an agent writes code, it usually needs to start a dev server, run tests, open a browser to verify its work. Today that all happens on your local machine. This works fine for a single task, but the agent is sharing your computer: your ports, RAM, screen. If you run multiple agents in parallel, it gets a bit chaotic. Docker helps with isolation, but it still uses your machine's resources, and doesn't give the agent a browser, a desktop, or a GPU to…
AetherJul 2026 · runaether.dev · ▲26Since coding agents like Claude Code and Codex came out, I've been pretty obsessed with them. It's hard not to when you're getting a 20x discount on inference. I've also been frustrated by them a lot. I hated walking around with my laptop lid open while connected to a hotspot on my phone, having to tediously accept commands so I don't lose my root directory, and running out of RAM when running multiple agents that were spinning up dev servers in different worktrees at once. A lot of people would say existing cloud agents are the solution to this, as none of the above problems apply to any…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
