Estimation

Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 30 regions. Semantic search via Qdrant vector DB

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a markdown plan.

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

🐍 Geometric Computer Vision Library for Spatial AI

Learn AI Engineering! Learn it. Build it. Ship it for others.

High-performance Python ASGI backend template for serving streaming LLM tokens, async agent tool endpoints, and OpenAPI schemas.

Analyze uploaded food images to identify food items, estimate macronutrients and micronutrients, assess glycemic index and blood-sugar impact, and recommend healthier alternatives. If the image does not contain food, request a food image and stop.

Open-source (AGPL-3.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. Rooms measured on the wall faces, symbol sweeps, materials + quantities with full provenance, built for preconstruction. Runs entirely in your browser.

Turn any video into a Mixamo-rig animation - GVHMR estimator, spec-driven retarget, FK apply in Blender via MCP. Works with any Mixamo character; built to be operated end-to-end by an AI agent.

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.

AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知

Official DINO-X Model Context Protocol (MCP) server that empowers LLMs with real-world visual perception through image object detection, localization, and captioning APIs.

Keep Claude Code’s prompt cache warm during breaks and show the estimated cost before a cold send.