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.
AI Dataset2025
A curated dataset of ~30,000 CUDA kernels generated by an agentic pipeline, including reference PyTorch implementations, runtime metrics, NCU/Torch/Clang-Tidy profiles, error messages and correctness labels — released under CC-BY-4.0 for model fine-tuning and offline RL/optimization research.
AI Dataset2025
A benchmark dataset for evaluating MLLM-driven interactive webpage code generation: provides prototyping screenshots, action.json interaction metadata, and example generation scripts across 127 webpages and 374 interactions to test dynamic UI-to-code capabilities.
AI Dataset2025
Provides 5 million instruction–response pairs for supervised fine-tuning of code LLMs, with inputs, outputs, unit tests, and automated LLM judgments. Uses hybrid automated/synthetic generation and is released under CC BY 4.0 for large-scale SFT workflows.
MCP Server2025
Provides a long‑lived, in‑process file and content search library for editors and AI agents, with typo‑resistant fuzzy matching, frecency‑ranked results, background watchers, and a lightweight in‑memory content index — optimized for repeated searches in long‑running processes.
AI Dataset2025
Benchmark dataset for evaluating agents on long-horizon software-engineering tasks (repo-level patches, test-driven fixes). Includes golden patches, related tests, and problem statements in parquet format; aimed at agent debugging and code-modification evaluation but requires full test environments.
AI Agent2026
Teaches LLMs to detect and remove “AI tells” from prose using curated phrase/structure lists, before/after examples, and a 5‑dimension scoring rubric. Delivered as a reusable skill (SKILL.md + reference files) designed to plug into Claude or any LLM workflow for automated style sanitization.
MCP Server2026
Pre-indexes a project's code into a local semantic knowledge graph that Claude Code can query—fewer tool calls and faster exploration with all data kept on-device. Features FTS5 search, call/impact analysis, auto-sync watcher, and multi-language support.
AI Agent2026
Terminal-native coding agent that streams reasoning blocks, makes controlled edits to local workspaces behind approval gates, and includes an auto mode that chooses model and thinking level per turn — designed for in-terminal code review, debugging, and automation workflows.
AI Client2026
Desktop + CLI agent-native client for managing multi-session conversations, connecting to multiple LLM providers and external data sources, and creating shareable agent skills and automations without editing code.
Embodied AI2026
Train robot reinforcement-learning agents with a heterogeneous runtime that streams CPU-parallel physics simulations (MuJoCo / Motrix) via shared memory into GPU/accelerator policy learners; provides a unified CLI, cross-platform backend support and demo checkpoints.
MCP Server2026
Indexes codebases into a persistent, queryable knowledge graph for AI coding agents, enabling full-repo indexing in minutes and sub-millisecond structural queries. Bundles 158 vendored tree-sitter grammars, a Hybrid LSP resolver, built-in embeddings, and 14 MCP tools for search, trace, and architecture analysis.