Free tools for developers working with AI.

See the real BPE tokens, token IDs, and character ratio for pasted text.

Build Cursor and Claude MCP configurations for stdio, SSE, and HTTP servers.

Generate concise AGENTS.md or CLAUDE.md project instructions from a questionnaire.

Ten simple agent skills for Cursor, Claude Code, and Codex. One command to install, one job per skill.

Estimate your monthly LLM inference bill and compare models across OpenAI, Anthropic, Google, and more.

Paste a prompt, get an approximate token count and what it costs as input across every major LLM.

Is ChatGPT Plus or Claude Pro worth it vs paying per token? Find your break-even point.

Paste your prompt stack and see which LLMs fit — with a bar showing how much of each model’s context window you use.

Compare two prompt variants: token delta and dollar savings per model, per call and per month.

Estimate embedding API cost, chunk counts, vector storage size, and rough monthly bills for your corpus.

Estimate LLM response time by output length — compare time to first token and total wait across models.

See how multi-step agent runs get expensive as context grows each step — per-step cost table with monthly totals.

Seven questions to pick budget, workhorse, or flagship LLM tier — with honest advice to start cheap.

Seven questions to pick fine-tuning, RAG, or prompt engineering — with honest cost ranges and anti-recommendations.

Lint system prompts in your browser: contradictions, vague wording, missing format spec, wasted tokens. Rule-based, not AI.

Estimate VRAM for quantized weights plus KV cache, and see which RTX cards and Apple Silicon tiers fit your model.

Buy a GPU or pay per token? Amortized hardware + electricity vs API pricing, with the break-even point in months.

Chunk count, embedding cost, vector storage size, and whether top-k retrieved chunks actually fit your context window.

Generate an llms.txt file for your site — a curated markdown index that helps LLMs and AI crawlers understand your content.