StartLux Decision
Open decision models (0.8B to 27B) that return a calibrated probability for every option in a single pass, with an inference engine and HTTP server.
Updated
✨ Try AgentScout's free AI image generator →Good for: getting calibrated probabilities for every option of a choice, yes/no, or score question in one forward pass for agents, bots, and classifiers
Use cases
Pin StartLux Decision to the top of models & local runtimes for 30 days + get a dedicated X launch spotlight on @clampdown19 & @AgentScoutHQ for $49, or book the exclusive $99/wk sitewide & newsletter slot.
About StartLux Decision
StartLux Decision is listed in our models & local runtimes category and is aimed at builders. Open decision models (0.8B to 27B) that return a calibrated probability for every option in a single pass, with an inference engine and HTTP server. Pricing, as the maker states it: Open weights 0.8B-27B on Hugging Face; free hosted API. Maturity: Active. We last checked the official link on 2026-10-26.
StartLux Decision at a glance
- Category: Models & local runtimes
- Built for: Developers and teams building with AI agents
- Pricing: Open weights 0.8B-27B on Hugging Face; free hosted API (as the maker states it)
- GitHub: StartLuxLabs/StartLux-Decision · 1,579 stars (as of Oct 26, 2026)
- Official site: github.com/StartLuxLabs/StartLux-Decision
- Listed on AgentScout: Oct 26, 2026
StartLux Decision FAQ
What is StartLux Decision?
Open decision models (0.8B to 27B) that return a calibrated probability for every option in a single pass, with an inference engine and HTTP server.
How much does StartLux Decision cost?
StartLux Decision's pricing, as the maker states it: Open weights 0.8B-27B on Hugging Face; free hosted API. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find StartLux Decision's source code?
On GitHub at StartLuxLabs/StartLux-Decision, which had 1,579 stars as of Oct 26, 2026.
What are alternatives to StartLux Decision?
Similar tools include LocalAI, Gufo, Strands Decider, MiroThinker, pooled and Meta Muse Wonder.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
StartLux Decision ratings and reviews
Be the first to rate StartLux Decision: tap 1 to 5 stars below. A written review is optional.
StartLux Decision alternatives
Other models & local runtimes tools in our directory. See all models & local runtimes tools →
LocalAI
Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.
Gufo
Gufo is an open-source inference engine built for AMD Strix Halo machines that runs text, vision and speech models locally, with tuned kernels and published benchmarks for each supported model. It serves models through an API so local agents can use them, and image and video generation support is in progress.
Strands Decider
Strands Decider is a small, fast decision model from Strands Labs for agent workflows. Rather than asking a full LLM every time, an agent can use it to choose between options or score something on a scale in a fraction of the time, with calibrated confidence so the workflow knows when to fall back to a bigger model.
MiroThinker
Deep research agent and open models tuned for complex research and forecasting tasks.
pooled
Peer-to-peer LLM inference in the browser: pool your laptops, phones and other devices into a room to run large open models for chat and coding agents, with no GPU server.
Meta Muse Wonder
Meta's new models for personal and professional agent tasks, available via Meta Model API and Muse Code.
Related lists
🏆 See also: LocalAI alternatives · All best-of lists
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built StartLux Decision? Add this badge to your README or site. It links back to this page. About badges
