Route Anything
A research framework studying model and policy routing across language, media generation, coding agents and robot manipulation, with quality and resource trade-offs.
- By
- Pengfei Zhou and collaborators
21 entities · 3 projects · 4 tools · 5 models · 9 news
A research framework studying model and policy routing across language, media generation, coding agents and robot manipulation, with quality and resource trade-offs.
An alpha Python pipeline that compiles organizational policy into reviewed rules, reproducible scenarios and decision-model training data.
A startup developing a behavioral world model for probabilistic predictions of individual actions, initially offered to financial brokerages.
Community Swift packages for interchangeable speech-recognition engines and typed classification decisions with probabilities.
Liquid AI's compact open-weight family for local text agents, vision, audio, multimodal interaction and structured decisions.
A pretrained relational foundation model for classification and regression across linked tables using historical labeled examples as inference context.
An MIT-licensed Python decision compiler that uses an LLM during compilation and a frozen local model for classification, scoring and routing at runtime.
A community llama.cpp port that serves local language and decision models from a jailbroken PS5's GPU.
IBM's modular 8B and 30B checkpoints combining Granite chat, Decision and Guardian activated LoRA adapters, and an English speech-to-text encoder in one serving endpoint.
An MCP server and CLI that uses a hosted decision model to rank crawl links and return relevant verbatim web passages to AI agents.
Google DeepMind and Singapore GovTech developed an on-device model intended to warn users about manipulative scam conversations without sending message text to the cloud.
An independent open-weight Qwen 3.5 fine-tune built to return typed decisions rather than chat responses.
A community-maintained Jev reproduction index corrected its same-skill scoring and added a public-versus-private comparison.
The Typed Decisions maintainers replaced a test-exposed model score with a clean re-score after a public challenge.
OpenAI's Decisions API is in public beta for text and image classification, with predicates, fixed choices and rubric scores at $0.10 per million input tokens.
McDonald's AI-assisted restaurant pricing recommendations, now challenged in a proposed antitrust class action that the company disputes.
Liquid AI released two downloadable decision models for text, images and audio, with edge-device speed and benchmark claims that still need independent testing.
AWS-affiliated Strands Labs released an open 2B-parameter decision model for choosing among supplied options in agent workflows.
Robinhood unveiled planned in-app AI trading agents that can research markets and place trades within a dedicated account.
Airbnb is introducing optional text and voice property search with dynamic filters and AI-generated listing comparisons.
TypeSafe AI's System One model for fast, typed, confidence-aware decisions.