Cost observability dashboard for AI coding tools — read token usage from 18 providers locally, no proxy needed, with cost tracking, efficiency metrics, and waste detection.

AI AgentsTypeScriptCLI

VIEW DETAILS →

Context token optimizer and visualizer for Claude Code / OpenClaw / Codex, featuring Active Compression, Smart Compaction, quality scoring, and cost dashboards with zero context overhead and zero network calls.

Model & Inference FrameworkLarge Language ModelsNode.js

VIEW DETAILS →

Open-source agentic data engineering harness providing deterministic SQL analysis, column-level lineage, dbt integration, FinOps, and multi-warehouse connections for any LLM.

Model & Inference FrameworkModel Context ProtocolAI Agents

VIEW DETAILS →

A development toolkit that equips AI coding assistants (Claude Code, Cursor, Windsurf) with Databricks platform capabilities, featuring 50+ MCP tools, 19 skill modules, and a Python core library. Supports SQL execution, Jobs management, Unity Catalog, Spark Declarative Pipelines, AI Agent development (Knowledge Assistants, Genie Spaces), and Model Serving.

Model & Inference FrameworkSDKAI Agents

VIEW DETAILS →

An open-source AI agent specialized in monitoring PostgreSQL databases, identifying root causes of issues, and providing fix suggestions and performance improvements.

Agent & ToolingDockerPostgreSQL

VIEW DETAILS →

PGMCP is an MCP server that enables querying any PostgreSQL database through natural language. It connects AI assistants to PostgreSQL databases, allowing users to ask questions in plain English and receive structured SQL results with automatic streaming and robust error handling.

Agent & ToolingGoPostgreSQL

VIEW DETAILS →

EvaDB is a database system designed specifically for AI-powered applications. It provides a powerful SQL API that enables developers to build AI applications with just a few lines of code, supporting both structured and unstructured data processing.

Agent & ToolingPythonMultimodal

VIEW DETAILS →

A "code-first" agent framework for seamlessly planning and executing data analytics tasks by interpreting user requests through code snippets and efficiently coordinating various plugins in the form of functions for stateful execution.

Agent & ToolingPythonDocker

VIEW DETAILS →

LangExtract is a Python library that leverages Large Language Models (LLMs) to extract structured information from unstructured text. It is optimized for long documents, features precise source grounding to map extractions back to their origin, and generates interactive visualizations for easy verification.

Agent & ToolingPythonLarge Language Models

VIEW DETAILS →