jevbooks

← All projects

fly-x-jev

pasangimhana/fly-x-jev

Fruit fly connectome robot with Jev picking descending neuron actions.

Agent Decisions0.63Runner-up: Game & SimulationFail open, fail closed
Automated README summary

Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A browser demo of a small robot walking down a road, driven by wiring from the real MaleCNS v1.0 fruit fly connectome. It is for anyone interested in connectome-based control and TypeSafe's Jev model.

How it uses Jev

Jev receives the robot's senses, mushroom-body valence, visual pathway drive and descending drive, then answers one choice question among six actions (walk_forward, veer_left, veer_right, walk_backward, takeoff, feed). The returned action is applied in js/jev.js; when stalled over 1.5 s, the action is sampled from Jev's probabilities.

Primitives:choice

Technique worth stealing

Use Jev's choice probabilities as a stochastic policy when the robot is stuck, instead of always taking the top action.

Try it

Set TYPESAFE_API_KEY in .env, run python3 arena/server.py, open http://127.0.0.1:8777 and press Play.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.76
  • Shows a System One patternnot found in the excerpt0.27
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolunclear0.58
  • Top-10 learning shortlist signalnot found in the excerpt0.26
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.00 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.76Shows a System One pattern0.27Describes handling uncertainty0.03Reports measured numbers0.05Is a runnable tool0.58Top-10 learning shortlist signal0.26Is a replica of the model0.0500.51Solves a common problem (0–2)0.00 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.7500.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 29 Sept 2026.