Desktop finance analytics terminal that combines CFA-level models, real-time trading and 100+ data connectors with embedded Python for analytics; includes 37 AI agents and local/multi-provider LLM support for automated research and decision workflows.
Gives LLM agents self-editing memory that persists across sessions, so they keep learning about a user instead of resetting each chat. Model-agnostic: bring your own LLM while it handles the memory and agent state, run via API or open source.
Official Python implementation of the Model Context Protocol. Build servers that expose tools, resources, and prompts to any MCP host, or clients that connect to any server; type hints and docstrings become the schemas, so a server fits in ~15 lines.
Converts PDFs, Office files, HTML, images and audio into one structured DoclingDocument, with deep PDF layout, reading order, table-structure and formula recognition, OCR, and native LangChain/LlamaIndex/Haystack integrations for RAG pipelines.
A compact domain-specific language for writing high-performance GPU/CPU kernels (GEMM, FlashAttention, sparse kernels) with Python-like syntax. It provides tiling/pipelining primitives, a TVM-based compiler and multiple backends (CUDA/CuTeDSL, NVRTC, WebGPU, Metal, Ascend) for operator-level performance work.
Parses, generates, and filters training data from noisy sources like PDFs and weak QA, then feeds it into LLM pre-training, SFT, RL, or RAG cleaning. Ships 100+ operators and ready-made pipelines for text, reasoning, Text2SQL, and agentic data.
Python web scraping framework that automatically relocates elements when a site's HTML changes, so selectors survive redesigns. Bundles Cloudflare Turnstile bypass, TLS fingerprint impersonation, and a Scrapy-like async spider for full crawls.
Self-hostable alternative to Google NotebookLM: organize PDFs, videos, audio, web pages, and Office docs, then chat over them, take AI-assisted notes, and search via full-text and vector. Routes to 18+ model providers and generates 1-4 speaker podcasts.
Turns any website into a structured, text-like interface that LLM agents can read and act on, handling clicks, forms, scraping, anti-detection and CAPTCHAs. Ships as an open-source Python library plus a hosted cloud API for running browser agents at scale.
High-accuracy biomolecular structure prediction suite: open-source models (protenix-v2/v1), a benchmark/evaluation toolkit, and a web server for inference. Targets protein/antibody–antigen and ligand-aware predictions with inference-time sampling and constraint support.
Framework for building and orchestrating multi-agent LLM systems, with agent types, tool integration, and human-in-the-loop workflows. Supports multi-agent conversation patterns, multiple LLM providers, and RAG-style tooling for research and prototyping agentic workflows.
Custom ComfyUI nodes that run Lightricks' LTX-Video diffusion-transformer models for text-to-video and image-to-video, adding IC-LoRA control over depth, pose, edges, and motion plus distilled and low-VRAM variants for node-based workflows.