Developer tools for AI engineering
Calculators, analyzers, and utilities for building with LLMs. Everything runs in your browser — no signup, and your data never leaves your machine.
Calculators, analyzers, and utilities for building with LLMs. Everything runs in your browser — no signup, and your data never leaves your machine.
Answer eight questions and get a well-structured CLAUDE.md or AGENTS.md for your repo.
Agentic DevelopmentPick MCP servers and get correct config JSON for Claude Code, Cursor and OpenCode.
Agentic DevelopmentGrade your system prompt A to F: contradictions, vague verbs, bloat and missing specs.
Agentic DevelopmentCheck provider tier limits against your agent fleet and find out when you hit 429s.
Agentic DevelopmentPaste any provider error and get the cause, fix checklist and correct retry strategy.
Agentic DevelopmentTokens per second by model: estimate how long any output length takes to stream.
Agentic DevelopmentMonte Carlo your agent's retry and loop behavior to see p95 spend and runaway risk.
Agentic DevelopmentA five-question quiz that recommends the right model for your task, latency and budget.
Agentic DevelopmentTranslate API requests between OpenAI and Anthropic formats with per-line mapping.
Agentic DevelopmentBuild function-calling schemas visually — valid JSON for OpenAI, Anthropic and MCP.
Agentic DevelopmentInteractive visualization of how temperature, top-p and top-k reshape token sampling.
Agentic DevelopmentPretty-print agent session logs: threaded turns, tool calls and diffs, all local.
Agentic DevelopmentGrade your existing CLAUDE.md or AGENTS.md A-F: contradictions, bloat and dead rules.
Agentic DevelopmentThe hidden token tax of tool definitions — per provider, per tool, per call, verified.
Agentic DevelopmentDesign exponential backoff with jitter — visualize timing, cost and worst-case delay.
Agentic DevelopmentBuild tool allowlist and denylist configs for coding agents — safe defaults included.
Agentic DevelopmentHeuristic scan of templates and tool outputs for injection patterns — fully local.
Agentic DevelopmentBuild a structured evaluation rubric and export it as JSON or markdown for your evals.
Agentic DevelopmentGenerate MCP server boilerplate in TypeScript or Python from your tool definitions.
Agentic DevelopmentCheck model JSON output against your schema — type errors, missing fields, extras.
96 tools live · across 5 categories — all free, all client-side.