AI Infra2026
Provides a self‑hosted OpenAI‑compatible gateway that exposes one API endpoint to route requests to 40+ model providers, issue revocable virtual keys, enforce budgets before spend, and record usage.
AI Agent2026
Routes Hermes Agent coding tasks to models and skills by work type, then runs independent work units in parallel. Its status system distinguishes reported completion from work verified by tests, review, or CI.
AI Infra2026
Routes agent requests across hosted, bring-your-own-key, and local models through one OpenAI-compatible API. It can also use production traces to optimize routing or train a specialized model.
AI Coding2026
Brings Spotify Portal workflows into coding agents for software catalog search, service briefings, diagnostics, and guarded actions. Its optional shunt plugin delegates large-file reading and boilerplate generation to AiKA worker models.
AI Infra2026
Connect agent runtimes such as Codex, Claude Code, and Hermes to a product through one API, with task streaming, sessions, files, and cancellation handled for you. Self-host it or use managed Cloud; control over credentials and data depends on the deployment.
AI Model2026
A non-autoregressive, multilingual System‑1 decision model that answers typed questions (choice/score/noul) over text or JSON in a single forward pass with probability distributions. Key differences: calibrated-probability design, sub-35ms GPU latency, and built-in multilingual routing; requires per-workflow recalibration and validation on long or low-resource languages.
AI Model2026
Turns a context, a question, and 2–20 candidate answers into a single chosen option for classification, routing, ordered scores, and Boolean decisions. Built on mmBERT-small with a 144.3M-parameter decision head, runs on CPU with up to 8,192 combined tokens; FP32 weights occupy 550.5 MiB and are Apache‑2.0 licensed.
AI Model2026
Performs schema-driven, low-latency classification and structured decision-making over English text. Supports multi-head scoring, constrained joint decoding with confidence/feasibility metadata, span extraction, and local CPU/GPU deployment via the gliner2 runtime.
AI Dataset2026
Provides 150,000 source‑grounded decision examples for training models that pick options, judge yes/no propositions, or assign ordered scores. Each row pairs a 'state' with JEV-style typed questions (CHOICE/NOUL/SCORE); multiple configs and train/test splits are included, license mixed/unknown.
Reduces self-attention complexity to O(N log N) by using a coarse-to-fine (pyramid) Top-K block selection with LogSumExp scoring, implemented with hardware-aware Triton kernels for fused routing and scoring—aimed at long-context LMs and retrieval tasks.
AI Dataset2026
A 180,000-row labeled dataset of agent decision steps for training fast decision models that choose whether to call a tool, which tool to pick, and whether arguments are complete. Provides leakage-safe splits, typed questions, canonical state/request fields, and ready-to-use Parquet format for low-latency routers.
Normalizes each domain's teacher feedback spread during multi-teacher on-policy distillation so that no domain (e.g., instruction following) overwhelms others, improving student recovery of specialist skills and raising average scores across benchmarks.