AI Train2022
Reproduces GPT-2 (124M) from scratch on OpenWebText in ~4 days on an 8xA100 node, with the whole stack kept to two ~300-line files: train.py for the loop and model.py for the architecture. A char-level Shakespeare run finishes in ~3 minutes on one GPU.
AI Image2023
X-AnyLabeling is a powerful annotation tool integrated with an AI engine for fast and automatic labeling. Designed for multi-modal data engineers, it offers industrial-grade solutions for complex tasks. Supports images and videos, GPU acceleration, custom models, one-click inference for all task images, and import/export formats like COCO, VOC, YOLO. Handles classification, detection, segmentation, captioning, rotation, tracking, estimation, OCR, VQA, grounding, etc., with various annotation styles including polygons, rectangles, rotated boxes.
AI Infra2023
Lets you write compositional Python programs that compile into self‑improving LLM pipelines — replacing brittle prompt engineering with a declarative, programmatic approach and built‑in algorithms to optimize prompts and weights for RAG, multi‑stage pipelines, and agent loops.
MLOps2023
Centralizes logs, metrics, traces, frontend RUM and LLM observability into one self-hostable platform, using Parquet + S3-native storage and SQL/PromQL querying to reduce long‑term storage costs and unify telemetry analysis.
AI Agent2023
Runs an agentic RAG loop over scientific papers: searches literature, gathers and re-ranks evidence chunks, then answers with in-text citations. Adds metadata-aware embeddings, retraction checks, and contradiction detection across full PDFs.
AI Client2023
Locally hosted frontend that connects to many text, image, and TTS backends (KoboldAI, Ooba, Tabby, OpenAI, Claude, OpenRouter, Mistral, NovelAI, Horde). Built around character cards, lorebooks, group chats, and extensions for deep prompt control.
AI Agent2023
Drives autonomous penetration testing and CTF solving via cooperating LLM sessions that track a pentest task tree. Scored 86.5% on the XBOW benchmark suite at ~$1.11 per solved task, and works with OpenAI, Claude, Gemini, and local Ollama models.
AI Client2023
Cross-platform client for interacting with multiple LLM providers and image models, offering local data storage, a prompt library, streaming replies and built-in image generation. Ships as desktop apps, a web version and mobile apps for shared/team and personal workflows.
AI Infra2023
Runs large language models entirely in C/C++ with no external dependencies, using 1.5-to-8-bit integer quantization and CPU+GPU hybrid inference to fit models larger than available VRAM. Backs Ollama, LM Studio, and most local-inference tooling.
AI Client2023
Bring-your-own-key chat client that keeps every conversation in the local browser, never a server. One UI reaches OpenAI, Claude, Gemini, DeepSeek and a dozen more providers across web, desktop and mobile, with MCP, plugins, and one-click self-hosting.
AI Agent2023
Builds production RAG systems around deep document understanding, explainable chunking, hybrid retrieval, citations, and agent workflows for messy enterprise documents.
AI Dataset2023
Provides 52,000 English instruction–response pairs generated by OpenAI's text-davinci-003 for instruction-tuning language models. Released under CC BY-NC 4.0; low-cost synthetic data useful for research but contains model-generated biases and errors.