DuckDB is an analytical in-process SQL database management system

📎 Public API for companies funded by Y Combinator

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Framework for evaluating and improving agents

The open source coding agent.

🦋 A tool to manage versioning and changelogs with a focus on monorepos

An agentic skills framework & software development methodology that works.

Validate Skill content against Agent Skill specification, with additional content density and quality checks.

Agent Skills for Neon Severless Postgres

An embedded, local-first MongoDB engine built on redb and Rust. Same document model, same MQL, same wire protocol. No mongod, no Docker, no network. Just import and go.

The agent that grows with you

Use the official MongoDB Skills with your favorite coding agent to build faster.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Agent Skills to help developers using AI agents with Supabase

Manages Unified Access to Generative AI Services built on Envoy Gateway

MongoDB Search

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

TypeScript SDK for the Voyage API

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

A simple task management system for managing AI dev agents

Lightweight coding agent that runs in your terminal

Convert MCP server to CLI application

Concatenate a directory full of files into a single prompt for use with LLMs

MongoDB AI Benchmarks and Datasets

Synthetic MongoDB database generation

Vercel AI SDK and middleware for models that do not support function calls (Part of Project Wrench)

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!