Search

Catch brittle prompts before production does — brittleness score and CI gate for LLM prompts under paraphrase

Define, version, and enforce behavioral contracts on LLM function calls

Semantic specification drift detector for LLM outputs — catches semantic violations Pydantic cannot see.

Mutation testing for LLM prompts. Find the gaps in your eval suite before production does.

Test whether your LLM retrieves information from every position in its context window.

Generate themed AI control center dashboards with voice, real-time widgets, and Claude AI chat

Diagnose RAG pipeline failures by type and location. Four Soils classification. Epistemic mismatch detection.

Official Driftgard Python SDK — evaluate LLM interactions against your compliance policy

Free AI coding assistant — Claude Code alternative

Generates production-ready React components, tests, and Storybook stories from structured spec deltas using an LLM-powered multi-stage pipeline.

An LLM adapter that lets Google ADK agents use Claude Code as their backing model.

Unified native Node.js bindings — single omni.node for LLM, STT, TTS, and Image/Video generation

Security assistant plugin by Alibaba Cloud that provides LLM request/response protection, tool call security checks.

AI-Powered Content Translation for Strapi

Contact: [email protected]

Executable Extensions - Build system for double-extension files

openclaw plugin for ckcloud - save your llm cost

Private semantic search engine for your local files, powered by Starbucks 2D Matryoshka embeddings

In-memory driver for pynosqlc — zero-dependency dict-backed storage for testing

Export/import OpenClaw skills, workspace context files, and config fragments as portable .tar.gz bundles