Horizons – OSS agent execution engine
I'm Josh, founder of Synth. We've been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We've also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI's Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0. It integrates with our sdk for evaluation and optimization but…
In plain words
Horizons is an open-source engine for executing coding agents at scale. Built by the team at Synth, it handles agent optimization, evaluation, and deployment through a unified stack that manages memory, live context, and agent actions. The platform supports multiple code execution models and integrates with Synth's evaluation and optimization SDK while offering self-hosted options. It's designed for developers building agent-based products who want to focus on proprietary data and algorithms rather than infrastructure.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I'm Josh, founder of Synth. We've been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We've also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI's Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0. It integrates with our sdk for evaluation and optimization but also comes batteries-included with self-hosted implementations. We think Horizons will make building agent-based products a lot easier and help builders focus on their proprietary data, context, and algorithms Some notes: - you can configure claude code, codex, opencode to run in the engine. on-demand or on a cron - we're striving to make it simple to integrate with existing backends via a 2-way event driven interface, but I'm 99.9% sure it'll change as there are a ton of unknown unknowns - support for mcp, and we are building with authentication (rbac) in mind, although it's a long-journey - all self-host able via docker A very simplistic way to think about it - an OSS take on Frontier, or maybe OpenClaw for prod
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
