logan-markewich/jeff
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
About the project
A self-hosted drop-in replacement for TypeSafe's jev System One API, powered by the GLiFormer model (400M) and compatible with the official typesafe-sdk. It classifies text locally into choices, ordered scores, and yes-probabilities.
Useful for
- Deploy a local text classification service without external API keys
- Swap out paid jev in an existing app by setting TYPESAFE_BASE_URL
- Score ticket tone and urgency through the /v1/systemone HTTP endpoint
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 57 stars so far today, about 73 expected by the end of the day.
- The repository is 0 days old and already has 82 stars.
- Top new repositories this week: #166.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 82
- Stars in a day
- 73
- Forks
- 4
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 19, 2026
- Last push
- September 19, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 19, 2026Top new repositories this week: #166
Similar projects
-
7.7
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.
-
7.4
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).
-
6.7
githubnext/localjev
A local TypeScript/Bun HTTP service implementing a Jev-compatible POST /v1/systemone API on top of an OpenAI-compatible Chat Completions endpoint (DiffusionGemma via oMLX). It acts as a bridge for typed decisions…
-
6.7
higgsfield-ai/higgsfield
Fault-tolerant GPU orchestration and ML framework for distributed training of models with billions to trillions of parameters, including LLMs. Manages node access, experiment queueing, and GitHub Actions integration.
-
6.3
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
6.3
jaredpalmer/kev
kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.