FBddcz/embodied-jev

EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs

AI agentsPython

4.6 Early signal Magnitude out of 10. Star growth looks organic. Data as of September 20, 2026.

About the project

A browser-based workbench that runs three MuJoCo Franka Panda manipulation tasks (pick-and-place, stacking, obstacle-carrying) and lets rule baselines or models like MiniCPM5-2B, TypeSafe Jev, Claude and OpenAI-compatible APIs drive the robot step by step, showing every decision, camera view and trajectory.

Useful for

Compare two or three models on the same manipulation task, seed and action budget with aligned replay.
Test an OpenAI-compatible or Claude API connection by running a single-step decision before a full experiment.
Try the simulation with zero setup using the built-in rule baseline before downloading model weights.

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

76 stars so far today, about 94 expected by the end of the day.
The repository is 0 days old and already has 87 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 87
Stars in a day: 94
Forks: 1
Issues and pull requests: 1
Watchers: 0
Language: Python
License: MIT
Created: September 20, 2026
Last push: September 20, 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 20, 2026Top new repositories this week: #200

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/FBddcz/embodied-jev.svg?lang=en)](https://gitnova.dev/en/r/FBddcz/embodied-jev)

Similar projects

9.0
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

BreakoutAI agentsPython+2,347 stars in a day
8.8
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

BreakoutAI agentsPython+1,883 stars in a day
8.2
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.

BreakoutAI agentsHTML+483 stars in a day
7.4
typesafe-ai/skills
Agent skills for building with TypeSafe's System One API: typed decisions and probabilities for LLM agents. Installs as a Claude Code plugin or via skills.sh.

Early signalAI agents+334 stars in a day
7.3
rmalde/minecraft-agent
An AI agent that plays Minecraft Java 1.16.5: the Astra GPT planner sets objectives, JEV picks actions, and Mineflayer executes them via the normal player protocol. Includes run recording and verification.

Early signalAI agentsJavaScript+262 stars in a day
7.0
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…

PeakingAI agentsTypeScript+665 stars in a day