Search

Semantic-release predefined presets.

Inspect TensorFlow.js model architecture and weights from the CLI or programmatically

Prism — OpenAI-compatible optimizing inference proxy. Self-Consistency, Best-of-N, PlanSearch, RTO, Memory (WiM), DeepConf, plus privacy/readurls/json plugins.

Official SDK integration for ThesisAI Research Agent

Core middleware that aggregates on-chain state and AI inference into a single optimized JSON for Next.js frontends.

Nx governance plugin for workspace health, boundaries, ownership, and architecture reporting.

GEIANT Hive provider for OpenClaw — cryptographically-signed distributed local AI inference with EU AI Act compliant agent identity

Browser-side cellular segmentation via Cellpose-SAM, running on WebGPU.

Hardened single-user AI gateway for classified-enclave deployment. Hard fork of Enclawed with cloud channels, cloud LLM providers, and external search/web extensions removed; classification-policy framework always on.

UI Toolkit

Single-operation code relocation tool for OpenCode agents — move code between files without copy-then-delete

Locally converts recorded audio, like WAV files and MP3s, to text using OpenAI Whisper.

React component package for Reinvent WP Text To Speech.

LMNT text-to-speech adapter for @absolutejs/voice

Browser SDK for Xfyun speech-to-text and text-to-speech

ElevenLabs text-to-speech with mac-style say UX.

Local text-to-speech via sherpa-onnx (offline, no cloud)

3-level LLM cache (exact, semantic, partial) with real-time token cost tracking

Brain-inspired cognitive memory database for LLMs

AI-native embedded database: Vector + Graph + Relational in one file