Runkite: Self-hosted Agent Control Plane
Self-hosted agent control plane in one Go binary
What it does
Self-hosted Agent Protocol control plane in one Go binary. Pluggable runners (LangGraph, CrewAI, and more), embedded Admin, and plane-level governance you own.
Self-hosted control plane for agents: Agent Protocol clients, Runner Protocol workers, connectors, HITL, fencing, and audit — one Go binary.
When one script stops being enough: coordinators and workers still need one place for credentials, HITL, kill, and audit. Each process owns its env, HITL, and logs. Delegation is ad-hoc HTTP. Ops is SSH and grep. Clients speak Agent Protocol. Runners pull jobs. Connectors mint credentials from the assignment — not from forged headers. Docker-only cold path: compose, echo, HITL interrupt, resume. Full commands and Admin preview live in Docs. Grants, HITL, fencing, and reclaim ceilings live on the plane — not as afterthought middleware in every script. Agent Protocol on the front. Runner Protocol on the back. The plane owns lifecycle, policy, and proof. Pluggable state, transport, and vectors…from getrunkite.github.io
Does the same job
all alternatives →
HarnessRouterJul 2026 · harnessrouter.ai · ▲238Bring the world's best AI agents into your app, with one API
OpenCode SuperappJul 2026 · opencodesuper.app · ▲128The power of Codex with local, self-hosted models and voice
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, August 2026
the whole month →- TL
Life & fun · 10d 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 · 17d ago · simedw.com