Le catalogue réel des outils pour IA

OCR for images and Korean ID documents

Korean ID document verification and PII masking APIs

Document inventory, extraction, summaries and comparison with source quotes and usage billing.

Image/video analysis: NSFW detection, object detection, thumbnails

APICK Korean data, simple-auth lookups, OCR, search, conversion, image, video and TTS

File conversion: PDF, DOCX, STT, asynchronous TTS with MP3/ASS downloads, watermarking

Korean bank account verification: holder name lookup, 1 KRW deposit, bank codes

Korean business, parcel and simple-auth employment, income, pension, license and health data

LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation

Search, quote and run reviewed Skills; points are charged only when a validated result returns

Domain/IP, web capture, Google search/maps, YouTube, Instagram, TikTok, X and Amazon data jobs

Let Codex orchestrate external coding agents through their native harnesses.

Run Claude Code subagents on cheaper opencode models (DeepSeek, opencode Go) with native parity.

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.

Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards.

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

Delegate a self-contained task to opencode's free-tier models as a one-shot subagent.

GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents.

On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.