vgrichina

Image Analysis with Bounding Boxes

Get precise bounding boxes for image elements using Gemini 3 Flash. Complements Claude's vision which can see but can't provide exact coordinates.

API Call

# Convert image to base64
IMAGE_BASE64=$(base64 -i image.png)

vgrichina

Using Gemini CLI for Large Codebase Analysis

When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.

File and Directory Inclusion Syntax

Use the @ syntax to include files and directories in your Gemini prompts. The paths should be relative to WHERE you run the gemini command:

vgrichina

Pug Language Support for ast-grep

This guide shows how to use ast-grep with Pug template files using custom language support.

Setup

1. Built the Pug Parser: We've compiled the tree-sitter-pug parser as a dynamic library (pug.so)

2. Configuration: Created sgconfig.yml with:

vgrichina

AI Code Agent

A lightweight, Node.js-based AI agent for code generation and project management, similar to Aider. It integrates with Git, supports a CLI with autocompletion, a rich web UI with visual commands, and fully configurable LLM prompts stored in separate .txt files. Every code change is automatically committed with the prompt included, with support for managing context, undoing changes, running tests, and copying context to the clipboard.

Features

• CLI Interface: Interactive terminal with @ file autocompletion, / commands, ! or /run for shell commands, and ? for questions.
• Web UI: Browser-based interface with visual buttons for all slash commands, input fields, diffs, commit history, and context management.
• Git Integration: Automatically commits code changes with prompts included; supports /undo for reverting.
• LLM-Powered: Uses an LLM (e.g., xAI's Grok API) to generate code and answers, with dynamic file context via /add and /drop.
• Test & Fix: Run

vgrichina

Vibe Compiler (vibec)

A self-compiling tool to process vibe-coded projects using prompt stacks and LLM generation.

Overview

vibec transforms stacks of prompts into code and tests, supporting static .md and dynamic .js plugins. It outputs staged artifacts (output/stages/) for Git history and a current runtime version (output/current/) aggregated from all stages with a "Last-Wins" strategy. It can compile itself using its own structure.

Project Structure

vgrichina

Minimalistic AI Coding Assistant

1. ./context - Code Context Generator

Purpose

Generate contextual information from a codebase to send to an LLM.

Arguments

--files=<pattern>        File pattern to include (e.g., "src/*.js")

vgrichina

select
	format_timestamp('%m/%d/%Y %H:%M:%S', timestamp_millis(div(block_timestamp, 1000000))) as `Date`,
	parse_bignumeric(json_value(args, '$.deposit')) / POW(cast(10 as bignumeric), 24) as `Sent Quantity`,
	'NEAR' as `Sent Currency`
	, receipt_predecessor_account_id
	, receipt_receiver_account_id
from `bigquery-public-data.crypto_near_mainnet_us.receipt_actions`
where receipt_predecessor_account_id in
	(
	'vlad.near',

vgrichina

// Tokenize the JSON string by splitting on `{`, `}`, `[`, and `]`, unless the character is inside a string
char* token = strtok(jsonCopy, "{}[],");
bool inString = false;
int depth = 0;
while (token != NULL) {
    if (!inString && depth == 0 && strcmp(token, path) == 0) {
        // The requested path was found, so return the next token as the value
        token = strtok(NULL, "{}[],");
        slice_t value = {
            .len = strlen(token),

vgrichina

const std = @import("std");

// NOTE: In smart contract context don't really have to free memory before execution ends
var arena = std.heap.ArenaAllocator.init(std.heap.page_allocator);
var allocator = arena.allocator();

// Import host functions provided by NEAR runtime.
// See https://github.com/near/near-sdk-rs/blob/78c16447486285fd952765ef3e727e16d6c8c867/near-sdk/src/environment/env.rs#L117
extern fn input(register_id: u64) void;
extern fn read_register(register_id: u64, ptr: u64) void;

vgrichina

select
	to_timestamp(receipt_included_in_block_timestamp / 1000000000) as timestamp,
	(args->>'deposit')::numeric / (10 ^ 24) as deposit,
	receipt_predecessor_account_id
from action_receipt_actions
where receipt_receiver_account_id = 'root.near'
and receipt_predecessor_account_id != 'system'