AI Infra2024
Runs untrusted workloads inside hardware-isolated local microVMs with Docker-like workflows; cross-platform and OCI-compatible, embeddable via SDKs and optimized for fast startups (typical guest boot <100 ms).
AI Audio2024
Provides low‑latency on‑device speech-to-text, intent recognition, and text-to-speech for building real‑time voice agents and interfaces. Streaming-optimized models, incremental caching, multilingual TTS/ASR and cross-platform bindings (Python, iOS, Android, Linux, Raspberry Pi) target live voice use cases where sub-200ms responsiveness matters.
AI Train2024
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.
AI Others2024
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.
AI Client2024
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.
AI Agent2024
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.
AI Train2024
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.
AI Agent2024
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.
AI Video2024
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.
AI Audio2024
Runs text-to-speech, speech-to-text, and speech-to-speech models natively on Apple Silicon via MLX — no CUDA or cloud. Supports 20+ TTS and 15+ STT models (Kokoro, Whisper, Qwen3), low-bit quantization, an OpenAI-compatible API, and a Swift package.
MCP Client2024
Expose Python functions as MCP‑compliant servers and clients so LLMs can call tools and resources directly; includes automatic schema generation, input validation, transport negotiation, authentication, and in‑conversation interactive UIs.
MCP Client2024
Provides a local-first Markdown knowledge graph that LLMs and humans can both read and write via the Model Context Protocol (MCP). Features two-way, editable notes, semantic search (embeddings + hybrid ranking), and optional cloud sync and team workspaces.