Toto
Context rich tasks sent to the best model.
What it does
toto routes every task to the best model. toto intelligently routes your tasks to the best model for what you need from the vendors you already pay for (OAI, Anth, Goog). speed, cost, skill - you choose what you route for. today, you choose the model you use when you do your work. almost everyone chooses the expensive, 'best': opus 4.7, gpt 5.5. that mistake is costing your business a LOT of money in metered, wasted token spend. models are spiky creatures that change fast - toto keeps up.
Does a similar job
all alternatives →
- RYRoute your prompts to the best LLM2024 · unify.ai · ▲298
Hey HN, we've just finished building a dynamic router for LLMs, which takes each prompt and sends it to the most appropriate model and provider. We'd love to know what you think! Here is a quick(ish) screen-recroding explaining how it works: https://youtu.be/ZpY6SIkBosE Best results when training a custom router on your own prompt data: https://youtu.be/9JYqNbIEac0 The router balances user preferences for quality, speed and cost. The end result is higher quality and faster LLM responses at lower cost. The quality for each candidate LLM is predicted ahead of time…
Smart model routing directly in Claude, Codex and CursorJun 2026 · github.com · ▲216We built a model router that plugs into coding agents (e.g. Claude Code, Codex, Cursor, etc.) and intelligently sends requests to the best model to serve them. Here's a quick demo of running it locally: https://www.youtube.com/watch?v=isKhAyivtfM. At Weave, we write most of our code with AI, and it's been getting more expensive. This came to a head when Opus 4.7 was released and, thanks to its tokenizer changes, our costs shot up. We knew we didn't need Opus for everything but we didn't want to lose out on the intelligence for the cases where you really need it. So we decided…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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 · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com