Open-weight Mixture-of-Experts LLM with 671B total parameters but 37B activated per token, trained on 14.8T tokens for 2.788M H800 GPU-hours. Matches leading closed models at a fraction of typical training cost via FP8 and architectural tricks.
AI Agent2024
Simulates a trading firm using LLM agents in specialized roles — fundamentals, sentiment, news and technical analysts feed bull/bear researcher debates, then a trader and risk team decide. Works across US, global and crypto markets and 10+ LLM providers.
AI Agent2025
Lets teams build, deploy, and manage AI agents from chat, visual workflows, code, knowledge bases, tables, and more than a thousand integrations.
AI Agent2025
Runs penetration tests autonomously: a multi-agent system (researcher, developer, executor) plans attacks, writes and runs exploit code, and chains 20+ tools like nmap, metasploit and sqlmap in isolated Docker containers — for authorized testing only.
Embodied AI2025
Turns camera, audio, LIDAR and web inputs into robot motion, navigation and speech by routing them through pluggable LLMs and VLMs. Hardware-agnostic Go runtime configured via JSON5, with ROS2/Zenoh middleware for real robots and simulators.
Provides end-to-end PyTorch scripts to download/prepare data, implement a transformer from scratch, train LLMs (13M→billion-scale) and generate text. Emphasizes educational clarity and single‑GPU experiments; useful for researchers or hobbyists, but large-scale training still requires substantial compute and engineering.
MCP Server2025
Wires retrievers, rerankers, and generators as standalone MCP servers orchestrated in YAML, so iterative RAG logic fits in dozens of lines instead of glue code. Adds loops, conditional branches, one-command web UIs, and shared evaluation benchmarks.
A concise textbook-style book that explains foundational concepts and techniques for large language models, covering pre-training, generative models, prompting, alignment, inference, and reasoning. Structured as self-contained chapters for readers with some ML/NLP background or those seeking a principled introduction to LLM foundations.
AI Agent2025
MCP-native agent framework built around the Model Context Protocol from the start, with end-to-end tested Sampling and Elicitation. Define agents and multi-step workflows in Python, run terminal-first, and swap Anthropic, Google or local models.
AI Agent2025
Drives your computer from natural language: a vision-language model reads raw screenshots and works the mouse and keyboard like a person, controlling any GUI app without APIs or accessibility hooks. Local or remote operator modes on Windows and macOS.
AI Train2025
Bundles a dataset, an interaction harness, and rubric-based reward functions into one RL environment for training and evaluating LLMs — also usable as an eval, synthetic-data pipeline, or agent harness for any OpenAI-compatible endpoint.
Shows that LLM reasoning can be incentivized through pure reinforcement learning, with no human-annotated reasoning traces. Self-reflection, verification, and strategy-switching emerge on their own, and the patterns transfer to distill smaller models.