Search

Static embedding table for Veto's semantic transcript search — potion-base-8M (Minish Lab, MIT) repacked to int8.

ElizaOS plugin for pay-per-request LLM inference via x402 on Solana USDC - no API keys, no accounts

Vercel AI SDK adapters for @orchestral/core — wrap an AI SDK language / vision / image / speech / transcription model instance as a ModelCapability envelope, so a host serves text-generation, image-to-text, text-to-image, text-to-speech and automatic-spee

A NestJS module for the Vercel AI SDK with Ollama — streaming/generation clients, model catalog, and warm-up.

Vercel AI SDK adapter for the GraphMind live agent debugger: wrap models and tools to stream execution events and honour pause / step / inject / retry / abort gates.

NiceKit - AI toolkit for prompt building, model transport, and response parsing, plus core business logic

Common Type Signatures for @vscode-logging/logger

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

DEPRECATED — renamed to @error-bar/tracing. This package re-exports it so existing installs keep working; switch your import.

Minimal desktop automation for Deno using native operating-system APIs and AAF scenarios.

Framework-agnostic core for LLM extraction + human-in-the-loop review: the shared field/prompt-version vocabulary, the JSON-Schema round trip, OCR token matching, a fetch client with actionable errors, the ParseResult contract, and the date/timezone helpe

Local PaddleOCR tools and image-admission bridge for DeepSeek Harness

Track your brand across ChatGPT, Perplexity, Gemini, Copilot and Google AI Mode with CitedSpy

Mentra Engine — miniapp registry, WebView bridge, and miniapp store

Simple, predictable, and lightweight QR code generation library for JavaScript and TypeScript.

Seed your projects with AI configurations

A knowledge graph for your codebase, written in markdown

Advanced auto-memory plugin for DSH: layered memory (episodic/semantic/profile) + knowledge graph + worldline versioning + vector/RAG retrieval + incremental graph building

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

一鉴到底核心库 - AI操作行为实时审计和安全监控