🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Ryu, a fork of Kuzu, is an Embedded Property Graph Database built for speed with vector search and full-text search built in. Implements Cypher.

LadybugDB a graph database

GEPAzilla: open-source GEPA prompt optimizer with datasets, scorers, and telemetry.

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Run Graph Queries with Lance

Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it!

HelixDB is an open-source graph-vector database built from scratch in Rust.

Minimal agent runtime built with DSPy modules and a thin Python loop. Includes CLI, FastAPI server, and eval harness with OpenAI/Ollama support.

prompt engineering experiments with DSPy GEPA and TextGrad

📑 PageIndex: Document Index for Reasoning-based RAG

Performance centered DSPy rewrite to(not port) Rust

Context Engineering Course with DSPy

Claude Memory MCP Visualizer

"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…

MCP Toolbox for Databases is an open source MCP server for databases.

DSPy: The framework for programming—not prompting—language models

A curated list of resources for graph-related topics, including graph databases, analytics and science

A repository to help you learn to build with AI. Let's make useful things, together.

State-of-the-art prompting techniques implementation with DSpy - Manager-style prompts, role personas, meta-prompting, and more

Build reliable AI and agentic applications with DataFrames

A collection of sample agents built with Agent Development (ADK)

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

A Python library for generating and loading synthetic and real-world datasets tailored for graph-based applications.

Lakekeeper is an Apache-Licensed, secure, fast and easy to use Apache Iceberg REST Catalog written in Rust.

⚙️🦀 Build modular and scalable LLM Applications in Rust

Open source RAG evaluation package

Getting started with BAML for creating and querying knowledge graphs with LLMs