Search

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Data ingestion service for the Agent Landing Zone. Processes PDFs, images, spreadsheets, transcripts and SharePoint content into grounding knowledge for agents, with smart chunking and multimodal embeddings.

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

[CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

Dynamic Intent Resolution Grounding Engine

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs, camera-conditioned grounding, and exposure-bracketed supervision transfer.

A generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and online proactive response.

A cross-platform AI pointer for screen-aware voice commands, object grounding, and direct desktop actions.

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.