A Blazing Fast AI Gateway with integrated Guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

An Elixir rate-limiter with pluggable backends

Computational parallel flows on top of GenStage

💎 Robust job processing in Elixir, backed by modern PostgreSQL and SQLite3

Open Source Development Platform for building robust type-safe distributed systems with declarative infrastructure

Write and execute jq programs with the help of LLM

Letta (fka MemGPT) is a framework for creating stateful LLM services.

AutoML tool for RAG

Laminar - open-source all-in-one platform for engineering AI products. Written in Rust 🦀. YC S24.

Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning

Task-based Agentic Framework using StrictJSON as the core

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Optimizing inference proxy for LLMs

Nomadic is an enterprise-grade framework for teams to continuously optimize compound AI systems

Manipulating Python Programs

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

A language model programming library.

make LLMs improve through experience

A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

AdalFlow: The library to build & auto-optimize LLM applications.

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

Late Interaction Models Training & Retrieval

PyTorch native finetuning library

Your first AI prompt engineer

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Aidan Bench attempts to measure <big_model_smell> in LLMs.