Skip to content
View cufelix's full-sized avatar

Highlights

  • Pro

Block or report cufelix

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
cufelix/README.md

Felix Cumarav

I ship production apps that businesses run on,
and AI agents and models that operate real software.

Prague  ·  ČAIO 2026 finalist  ·  open to contract work

 Pripoj.to     LAI     Kestrel     VoltPlán     Virlya     felix.cumarav@gmail.com 


What I build

Project What it is Built with
🚐 Pripoj.to trailer rental with keyless pickup through smart locks React Native · Next.js · Firebase · Stripe · Igloohome
🍱 Meal-box ordering orders, menus, delivery zones, payments and invoicing for a food-delivery company web shop · admin · CRM · payments · bank import
🎮 Multiplayer game real-time iOS / Android game for a client Expo · Rust engine · WebSockets · Redis
🐧 LAI AI agent that drives the whole Linux desktop through the accessibility tree Python · AT-SPI · X11 · MCP
🦅 Kestrel desktop agent with memory and its own screen, built on opencode TypeScript · Bun · LAI
⚡ VoltPlán forecasts EV-charging demand for every zone in Prague LightGBM · scikit-learn · Streamlit
🪄 Virlya ten agents turn one brief into a full social-media campaign multi-agent · image generation · Telegram

Production

Agents are half of it. The other half is software real businesses run on: payments, auth, scheduling, invoices, hardware, store releases.

Pripoj.to  trailer rental · full product
Rent a trailer from your phone and pick it up with nobody there. React Native app with phone-number sign-in, a live map of trailers and availability-checked booking; Stripe with 3-D Secure; Firebase Cloud Functions that turn a paid booking into a time-limited Igloohome lock PIN, extend rentals and clean up expired codes; a Next.js admin with the fleet's real-time state, pricing and stats.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#161b22','primaryTextColor':'#e6edf3','primaryBorderColor':'#e0af68','lineColor':'#e0af68'}}}%%
flowchart LR
    U[app<br/>map · booking] --> A{availability<br/>check}
    A --> S[Stripe<br/>3-D Secure]
    S -- webhook --> F[Cloud Functions<br/>auto-extend · PIN cleanup]
    F --> L[Igloohome PIN<br/>keyless pickup]
    F --> M[admin<br/>live fleet · pricing]
Loading

Meal-box ordering system  client · in development
Replaces a meal-box delivery company's web shop and spreadsheets with one system: weekly menus built from a dish database with allergens, an order cut-off every Thursday 23:59 for Mon–Fri delivery, delivery zones drawn on a map with manual approval at the edges, online payments, bank-statement import that matches payments to invoices automatically, accounting export, and a CRM over all of it. Specified down to the domain model, API, security, migration and running costs before the first line of code.

Multiplayer mobile game  client · in development
Real-time iOS / Android game with a Rust rules engine, WebSockets, matchmaking and bots; load-tested at 300 concurrent players.

Also: Forksy, a nutrition tracker, and PhAuth, phone-number sign-in, both React Native / Expo.


Desktop agents · LAI + Kestrel

Desktop agents mostly fail on grounding: a model looking at a screenshot guesses coordinates and guesses wrong. LAI reads the AT-SPI accessibility tree, the desktop's DOM, fuses it with four other sources of truth and invokes widgets through their own accessible actions. Pixels are the fallback, not the plan.

$ lai do "open the text editor, write a haiku about X11, save it to ~/haiku.txt"

  ▸ app_open      {"name": "Text Editor"}
+   ✓ window up after 0.6s
  ▸ ui_snapshot
+   ✓ 57 accessible elements
  ▸ ui_type       {"ref": 12, "text": "Pixels in a grid…"}
+   ✓ set via a11y_set_text
  ▸ ui_click      {"name": "Save"}
+   ✓ invoked via a11y_action, not a pixel click
  ▸ file_read     {"path": "~/haiku.txt"}
+   ✓ effect verified on disk

@@ completed: 8 steps in 34s @@
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#161b22','primaryTextColor':'#e6edf3','primaryBorderColor':'#7aa2f7','lineColor':'#7aa2f7','clusterBkg':'transparent','clusterBorder':'#30363d'}}}%%
flowchart LR
    subgraph perceive [perceive]
        A[AT-SPI tree<br/>role · name · state · bounds]
        W[window tree]
        P[process tree]
        S[screen capture]
        O[OCR fallback]
    end
    A & W & P & S & O --> F{{grounded<br/>state}}
    F --> ACT[act<br/>a11y action first,<br/>pixels last]
    ACT --> V[verify<br/>re-read state]
    V -- effect seen --> F
    V -. "same failure ×3<br/>or no-op success ×6" .-> R[refuse & replan]
    R --> F
Loading

Kestrel puts LAI's hands under sst/opencode's agent loop and adds what a plugin can't: memory of the machine it lives on, its own X server so it never takes your mouse, and loop discipline. Same tools over MCP took opencode 18 calls; Kestrel took 7. The tools were identical. The whole gap was the loop.

Python · TypeScript · Bun · X11 / AT-SPI · MCP · ~47k lines in LAI


Forecasting · VoltPlán

2030 EV-charging demand for every grid zone in Prague, a station-type recommendation per zone, and a V2G layer that resolves grid overloads by moving charge windows instead of building hardware.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#161b22','primaryTextColor':'#e6edf3','primaryBorderColor':'#9ece6a','lineColor':'#9ece6a'}}}%%
flowchart LR
    D[(70+ features<br/>population · housing<br/>transit · grid)] --> L[leakage guard<br/>drop target-derived cols]
    L --> M[LightGBM<br/>P10 · P50 · P90 heads]
    M --> H[517-zone holdout<br/>MAE 4.7 · P@50 0.84]
    M --> C[station type<br/>AC small · AC mid · DC hub]
    M --> G[V2G load shifting<br/>delay charge windows]
Loading

ČAIO 2026 AI Startup track · 2,378 training zones · trained on CPU (Lunar Lake, no CUDA) with sklearnex · Streamlit demo


Multi-agent · Virlya  live product

Ten specialised agents turn one brief into a multi-platform campaign. A human signs off on the plan before anything is generated, and approves or rejects finished posts from Telegram.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#161b22','primaryTextColor':'#e6edf3','primaryBorderColor':'#bb9af7','lineColor':'#bb9af7'}}}%%
flowchart LR
    B[brief] --> R[web research] --> S[strategy] --> H{human<br/>approves plan}
    H --> C[on-brand copy] & I[image generation]
    C & I --> P[posts<br/>IG · FB · X · LinkedIn · TikTok]
    P --> T{Telegram<br/>approve / reject}
Loading

Also

Tools for working with agents
claude-session-dots: a panel dot per Claude Code session that turns red when one is waiting on you.
learn-claude-code: an AI tutor where answer keys are committed before the question is shown, so the model can't grade itself generously.
claude-widget: 5-hour and weekly usage limits in the Cinnamon panel.


How I work

1  beat a dumb baseline before believing a smart model
2  fix grounding before tuning prompts; most agent failures are perception failures
3  verify the effect, not the call; a click "succeeds" the moment the event is sent
4  build on a strong base and spend the effort where the gap actually is

ML  Python · LightGBM · scikit-learn · polars · DuckDB · Streamlit
Agents  tool use · MCP · RAG · vector databases · multi-agent pipelines · evals
Systems  TypeScript · Rust · Node · Bun · PostgreSQL · Redis · Docker · Caddy · Linux (X11, AT-SPI)
Product  React Native / Expo · Next.js · Firebase · Stripe · Spring Boot

Popular repositories Loading

  1. grokbot-cli-mcp grokbot-cli-mcp Public

    Forked from superagent-ai/grok-cli

    Grok coding agent for the terminal (built on pi) + MCP server for Claude Code: X/web search, vision, image/video, agent delegation. npm i -g grokbot-cli-mcp

    TypeScript 3 1

  2. Arduino Arduino Public

    Arduino/ESP32 sketches, incl. ai_drone_esp32 — a 65mm whoop drone flown with just ESP32 + ESP32-CAM, no flight controller or IMU

    C++

  3. newjava newjava Public

    Java game engine + raycasting engine, built from scratch

    Java

  4. olympiada olympiada Public

    pro pana kohuta a jeho komisi odevzdavam reseni

  5. smart-meta-browser smart-meta-browser Public

    attempt to create smart-meta-browser

  6. NeoForge-web NeoForge-web Public

    TypeScript