HarnessRouter Community Edition
Open-source unified interface for agent harnesses
In plain words
HarnessRouter Community Edition is an open-source unified interface that lets developers integrate multiple AI agent harnesses—including Codex, Claude Code, and Hermes—into their products through a single API. Deployed on users' own infrastructure via Docker, it handles sessions, streaming, file management, and failure recovery while keeping model keys and data under user control. The community edition includes a gateway, runner, and console, requiring no external databases or cloud services, and allows switching between different agent harnesses without rebuilding backend code.
written from the facts on this page · September 2026
From the sources
Plug-and-play managed agent harnesses in your product: Codex, Claude Code and Hermes through one API on your infrastructure, now open sourced under Apache 2.0. Switch harnesses without rebuilding your backend. Sessions, streaming, files, artifacts, cancellation, failure recovery, all handled. Model provider keys, state, and deliveries under your control. Gateway, Runner, Console in one Docker container. Ready-to-use starter kit apps as inspiration of possibilities.
Plug Codex, Claude Code, and Hermes into your product through one Agent API on your own infrastructure. Explore Community Edition, UHP, and the Starter Kit.
The best agent harnesses as your infrastructure, one conversation away. Plug eight agent harnesses, Codex and Claude Code to OpenCode, Qwen Code, and Cline, into your product through one Agent API, on your own infrastructure. Apache 2.0 · One Docker container · Your keys, state, and files Gateway, Runner, and Console start together. No managed database, external vault, or cloud account required. The API, Console, SQLite state, and workspace files stay on the infrastructure you control. Integrate once, select the harness for each task, and switch without rebuilding your product backend. HarnessRouter handles the backend lifecycle around each harness, not only the initial model request. UHP…from harnessrouter.ai
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 · 16d 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, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com