Search

Standalone CLI for running the Maestro server

LLM-aware UI context for Django — template tags + auto-inject middleware

A toolkit for LLM-as-a-judge evaluation and arena benchmarks.

Deterministic validation firewall for LLM outputs. Verify AI proposals against ground-truth state using deterministic rules. Zero dependencies.

Visor CLI for LLM-driven mobile app interaction and artifact capture

Turbopuffer vector database adapter for cognee

Local speech-to-speech voice assistant with PySide6 GUI and CLI.

CLI tool for syncing encrypted vaults with SGit-AI

Minimal workspace configuration and versioning for conda projects

n8n AI Agent node with native Slack streaming output

n8n community node for RecRam — AI-powered video survey platform

Nexlogiq Commerce OS - Unified AI E-commerce Engine

The economic proof layer for AI — sealed receipts, Named Chains, per-customer margins, LiteLLM integration

Turn email threads into a searchable knowledge base. Parse EML files, index with embeddings, and use RAG to learn how your best engineers analyze issues.

FastHTML virtual scrollbar component with drag-to-scrub, click-to-jump, and position indication for discrete-navigation containers.

Chat with Mr Chatterbox

Prompt regression testing for RAG pipelines. Like git diff, but for AI.

LangChain - Marketplace Earner Suite v4

Know your AI API costs before you spend. Calculate and compare LLM pricing from the terminal.

Reverse-engineer Anthropic's opaque Claude subscription limits into hard numbers