User repository on GitHub
1,000 individuals. One intelligence. A WebGL swarm whose strategy is decided live by TypeSafe Jev. By KI Boost Mittelstand.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Demos & Experiments
THE SWARM
A WebGL visualization of 1,000 light-point boids whose swarm strategy is decided in real time by TypeSafe Jev: PixiJS v8 rendering, TypeScript strict and Vite 8, built by KI Boost Mittelstand.
- Stars
- 0
- Language
- TypeScript
- License
- APACHE-2.0
- Reading time
- 2 min
- Published by
- Community
- Author
- machine1986
- Last verified
- Oct 2026
Works forJev for Realtime control
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- Browser
- Capabilities
- Open source
Highlights
- A living swarm of 1,000 light points whose strategy is decided in real time by TypeSafe Jev, rendered with PixiJS v8 WebGL.
- TypeScript in strict mode on Vite 8, with a Node 22.18 or newer badge and a claim of 60 FPS with 1,000 particles.
- A project by KI Boost Mittelstand, Apache-2.0 licensed, with a demo gif titled for a chaos event, a Jev decision and a singularity finale.
- Topics include ai, boids, pixijs, swarm, visualization and webgl; 0 stars, created and pushed 2026-10-15.
Watch out
README reviewed 2026-10-17; it is written mostly in German and the captured excerpt stops after the introduction, so the Jev integration, decision cadence, performance details and setup instructions are not visible in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A WebGL visualization of a swarm of 1,000 light points whose strategy is decided live by TypeSafe Jev, built in strict TypeScript with PixiJS v8 by KI Boost Mittelstand.
The README says the swarm's strategy is decided in real time by TypeSafe Jev. The captured excerpt stops before the integration details, so the questions asked and their cadence are not documented.
The repository's demo gif is captioned for a chaos event, a Jev decision and a singularity finale, suggesting the visualization is staged around moments where Jev changes the swarm's behavior.
TypeScript in strict mode, PixiJS v8 for WebGL rendering and Vite 8 as the build tool, with Node 22.18 or newer required; the README advertises 60 FPS with 1,000 particles.
KI Boost Mittelstand, a consultancy that the README links; the project carries an Apache 2.0 license badge and GitHub metadata in the digest shows 0 stars and 0 forks.
The captured README does not include local setup steps or API key requirements; the digest records the stack, the badges, the demo gif and the attribution, but not install or configuration instructions.
The excerpt is mostly German and stops after the introduction, so the Jev calls, performance tuning, controls, license text and setup details are unavailable in the digest. The repo was created and pushed 2026-10-15.
More Jev resources like this
A TypeScript WebGL lab that explains a JEV-style decision architecture layer by layer, from user intent and context through a decision core with scoring, policy and confidence to execution and output.
Jev Demos & Experiments#community#github#typescript
Community
pandeeswaran-08/jevTypeScript
pandeeswaran-08/jevTypeScriptThe Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
trycua/cuaRustBrowser-only Laya demo suite: four Vite apps — a Traditional Chinese decision playground, Gomoku, Big Two and a 3D maze — run the Laya ONNX model on-device through Transformers.js, downloading fp16 weights from Hugging Face on first use.
Jev Demos & Experiments#community#catalog-import#madewithjev
Community
killkli/open-jev-layaPython
killkli/open-jev-layaPythonA browser visual IDE for composing Jev API requests: build a state plus Choice, Score, Noul and Box questions with image assets, preview and validate the request JSON, send it, and read the answers as visual cards instead of raw JSON.
Jev Demos & Experiments#community#github#typescript
Community
MoeclubM/PlayJevTypeScript
MoeclubM/PlayJevTypeScriptA Bun workspace pairing a typed decision API over System One providers with a React arcade where decision models play games and every call is stored and ranked. The sample code calls Jev through OpenRouter with boolean, choice and score questions.
Jev Demos & Experiments#community#github#typescript
Community
desplega-ai/system-oneTypeScript
desplega-ai/system-oneTypeScriptA small, deliberately bounded browser loop joining ego-lite control with Jev decisions: each step Jev picks an operation and a target from the current ego snapshot, and the executor discards the ref after acting.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
phd-peter/ego-jevTypeScript
phd-peter/ego-jevTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.