PostHog/jeeves
Jeeves – Reasoning improves Jev-like decision models
About the project
Jeeves is a reasoning model built on Qwen3.5-9B (LoRA + pointer head), trained with SFT and CISPO, that thinks before answering and returns calibrated probabilities for yes/no, multiple-choice and rating questions via a Jev-compatible API.
Useful for
- Serve a local classification endpoint that answers in Jev's request format
- Swap Jev for a higher-accuracy model on out-of-domain tasks
- Inspect model confidence via probabilities and ECE on your own data
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 83 stars so far today, about 119 expected by the end of the day.
- The repository is 0 days old and already has 71 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Jeeves. Reasoning improves Jev-like decision models” — 68 points, 2 h ago.
- About 109 forks a day — people are taking the code.
- Recent forks include notable developers: @jonnydubowsky (299 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 71
- Today
- 83 · ≈ 119 by evening
- Forks
- 7
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 29, 2026
- Last push
- September 29, 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.
Hacker News discussions
- Jeeves. Reasoning improves Jev-like decision models68 points, September 29, 2026
Spotted in
- September 29, 2026Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/PostHog/jeeves)Similar by description
-
3.9
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.
-
0.8
kshetrajna12/reflex
An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.
-
4.4
InternLM/Intern-Decision
A multimodal decision model built on Qwen3.5 that turns a state, optional images, and typed questions (choice, score, yes/no) into decisions with probabilities. Ships with training, two inference backends, temperature…
-
2.5
mode-io/vllm-jev
A vLLM-based server for Jev decision models: given a question and candidate answers, it returns a label and probability for each candidate. Runs on Linux with NVIDIA GPUs and on Apple Silicon via MLX/MPS.
-
0.6
allebee/jevk5
An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens.…
-
0.2
Heman10x-NGU/openJev-verdict-2.0
An open non-autoregressive decision model built on ModernBERT (149.6M) that emits typed decisions (Choice, Score) with calibrated probabilities in ~20-25 ms. On the typed-decisions benchmark it reaches 77.10% accuracy…