undrgrnd-labs/hunch
App
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 8 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A proxy server that answers yes/no, choice and score questions about text or records on CPUs in milliseconds. It uses EmbeddingGemma 2 embeddings and a small student classifier trained on a slower teacher model's answers, and hands questions back to the teacher when it is not…
Who it's for
Developers running high-volume agent trace, log or comment analysis who want to reduce calls to an LLM or decision model judge
How to use it
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up undrgrnd-labs/hunch in my project. Follow its README: https://github.com/undrgrnd-labs/hunch. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #81, on 29 Oct 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
22,066 GitHub repos watched and ranked every hour. Figures as of 29 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/undrgrnd-labs/hunch?ref=badge)Similar repos
- AlibabaResearch/abench
A Python benchmark that replays recorded agent trajectories (DeepSWE v1.1, LMCache) or a locally generated workload in closed loop against an OpenAI-compatible inference server such as SGLang or vLLM.
- facebookresearch/swe-sweep
A benchmark that measures how many bugs language models and agents can find and fix in large real repositories. Agents receive no hints about bug type or location. Tasks run on Harbor and are scored b
- alleyxd/AnyDecide
A Python library and HTTP service that turns a local language model into a decision API. Typed questions (choice, score, yes/no) are answered in one batched forward pass by reading next-token probabil
- siglake/siglake
Open-source log and trace analytics that collects OpenTelemetry data, stores it as Parquet in Apache Iceberg tables on object storage, and allows querying with SQL. Built in Rust on DataFusion, with s
- StartLuxLabs/StartLux-Decision
Inference engine and HTTP server for a family of open decision models from 0.8B to 27B parameters. Given a state (text, JSON or images) and typed questions, the models return a calibrated probability
- smhanov/agentloop
A Go library that implements the LLM tool-calling loop: it sends prompts to a model, executes requested tool calls, feeds results back, and repeats until a final answer. It adds budgets, hooks, skills