AI Agent2026
Runs a persistent, self-modifying AI agent locally with durable identity, memory, and versioned history across tasks. Provides native desktop and headless CLI runtimes, coordinated subagent swarms, configurable remote or local GGUF models, and reviewed self-evolution via Git.
AI Train2026
Provides a one-command CLI to fine-tune and post-train LLMs, with layer streaming that lets an 8B model be fine-tuned on a 4 GB laptop GPU. Auto-configures quantization, LoRA adapters, batching and evaluation gates, and supports export and serving workflows.
AI Dataset2026
Provides 6,000 runnable, operator-level PyTorch tasks for training and evaluating CUDA kernel generation models; each sample includes executable code, operator descriptors, and provenance tags, with execution-driven filtering to ensure reproducibility and contamination control.
AI Train2026
Runs transformer forward+backward training directly on Apple's Neural Engine by reverse-engineering private ANE APIs; includes per-layer ANE kernels, INT8 optimizations and benchmarks. Proof-of-concept only—relies on undocumented APIs, has low utilization and CPU fallbacks.
AI Dataset2026
Benchmarks LLM agents on realistic legal work by packaging lawyer-style assignments with client materials and expert, per-deliverable rubrics. Includes an execution harness to run, score, and compare agents across a large, evolving task set spanning multiple practice areas.
AI Agent2026
Monitors and detects risky behavior in enterprise AI agents via high-fidelity telemetry, security benchmarking, and a two-tier detector. Comprises ADR Sensor, ADR-Bench, and ADR Detector; deployed in production at Uber and validated on public benchmarks.
AI Infra2026
Provides high-performance CUDA/CUTLASS kernels implementing Kimi Delta Attention (KDA), accelerating KDA prefill on SM90+ (Hopper) GPUs. Integrates as a drop-in backend for flash-linear-attention, supports native variable-length batching, and targets K=V=128; requires CUDA 12.9+/PyTorch 2.4+.
AI Deploy2026
Provides reusable Docker compose files, scripts and benchmarked configs to serve modern LLMs (Qwen, Gemma, etc.) on 1–2 NVIDIA RTX 3090/4090/5090 GPUs. Multi-engine (vLLM, llama.cpp, ik_llama), measured TPS/context tradeoffs, and validated single/dual‑GPU recipes.
AI Dataset2026
A collection of biology-focused 'mystery' tasks for benchmarking model performance on biomedical reasoning, evidence synthesis, and problem solving; curated by Anthropic and hosted on Hugging Face, designed for granular evaluation of scientific decision-making.
AI Dataset2026
Provides 545,431 math problems with model-generated solution traces (chain-of-thought and Python tool-integrated reasoning) verified against reference answers for training and evaluating LLM mathematical reasoning. Parquet-format dataset; DeepSeek‑V4‑Pro generated traces and mixed CC BY / CC BY‑SA licensing.
AI Infra2026
Ingests and normalizes security telemetry, runs multi-model AI agents to produce replayable investigations and automated triage/response; key features include a step-by-step Investigation Ledger, CI-gated eval harness, and self-hostable deployments.
AI Deploy2026
Runs local LLMs on Apple Silicon using native MTP speculative decoding to accelerate token generation while preserving the model's output distribution. Leverages the model's own MTP heads with batched verification and exact rejection sampling; ships with a Mac app, CLI, local OpenAI/Anthropic-compatible server, auto-tune, and Forge for building/verifying MTP adapters.