Search

Statsig helps you move faster with feature gates (feature flags), and/or dynamic configs. It also allows you to run A/B/n tests to validate your new features and understand their impact on your KPIs. If you're new to Statsig, check out our product and cre

Distributed training and serving framework for models up to 405B parameters.

Unified AI guardrail enforcement layer. One API for NeMo, Presidio, Lakera, LlamaFirewall, LLM Guard, Azure, AWS and more.

Drop-in Anthropic client wrapper with token counting, cost analysis, and semantic compression

Kyriba Payment Automation AI skill for coding agents

Fix Chinese (CJK) punctuation in a single Markdown / HTML file via a Claude Code /zhfix skill — a thin wrapper on top of AutoCorrect.

Codex skill for A-share after-hours stock review with portable JSON history.

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

AI model API prices for when quality matters: first-party-sourced, dated, point-in-time, and human-verified. Automation keeps it current; a human signs off before anything ships. CC BY 4.0.

Validation control plane for AI-generated code changes.

The runtime that replaces you as the person who prompts the agent.

Local vision (describe images), STT (speech-to-text), and TTS (text-to-speech). macOS uses MLX (Apple Silicon GPU). Windows/Linux use whisper, edge-tts, and transformers.

Lightweight browser-side image processing before upload — compress, convert to WebP, and resize using Canvas API. No server needed.

Shared funnel runtime contracts and helpers.

An opinionated, dependency-light React rich-text prompt input with trigger-based chips (@mentions, /commands, #tags), inline markdown, undo/redo, file & image attachments, and a complete chat-input layout. Ships as an npm package or a shadcn registry.

CLI to install reusable React components like shadcn/ui

Zero-Config Milvus DB Studio — An AI-native GUI for the Milvus vector database. Browse collections, inspect records, run vector search and scalar queries, and fire raw REST requests — all without any configuration. Launch instantly with a single command:

High-performance Holographic Memory System (HMS) — privacy-preserving semantic search using hyperdimensional computing.

OpenClaw context-engine plugin — OpenViking AI memory, long-term memory, knowledge base, semantic search, RAG, context engine. 长期记忆 · 知识库 · 语义检索 · 上下文引擎

Real-time model routing dashboard for OpenCode - track which models are used, token costs, and complexity classification