Starred repositories
A cache for AI agents to learn and replay complex behaviors.
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
DuckDB wrapper for FAISS - Experimental
Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.
DuckDB extension that adds support for SQL/PGQ and graph algorithms
A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).
Tabular Deep Learning Library for PyTorch
Conda Environment MAnager, a library to execute code in isolated environments.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
FrugalScore is an approach to learn a fixed, low cost version of any expensive NLG metric, while retaining most of its original performance
Official Implementation of "KBLaM: Knowledge Base augmented Language Model"
ParadeDB is a modern Elasticsearch alternative built on Postgres. Built for real-time, update-heavy workloads.
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
The AI-native proxy server for agents. Arch handles the pesky low-level work in building agentic apps like calling specific tools, routing prompts to the right agents, clarifying vague inputs, unif…
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
A collaborative note taking, wiki and documentation platform that scales. Built with Django and React. Opensource alternative to Notion or Outline.
Efficient Triton Kernels for LLM Training
Scalable graph analytics database powered by a multithreaded, vectorized temporal engine, written in Rust
The lazier way to manage everything docker
aider is AI pair programming in your terminal
Open-source graph database, tuned for dynamic analytics environments. Easy to adopt, scale and own.
SQL-based prefix tree implementation inspired by pygtrie and python-diskcache
Guaranteed Structured Output from any Language Model via Hierarchical State Machines