Reference code for the Meta-Harness paper.

This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Agent that read, write and edit documents.

Get your documents ready for gen AI

A vector index built on TurboQuant, written in Rust with Python bindings

A fast, helpful, and open-source document parser

Fully-local search engine with Liteparse, transformers.js and Qdrant Edge

Open Source Identity and Access Management For Modern Applications and Services

AI agents running research on single-GPU nanochat training automatically

LLMs in Finance - Generative AI - AI Agents

Full audit of the LoCoMo benchmark

ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its go…

Uplift modeling and causal inference with machine learning algorithms

Graph-Native Infrastructure for Context and Accountable AI Systems

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

Build effective agents using Model Context Protocol and simple workflow patterns

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

bb25 is a fast, self-contained BM25 + Bayesian calibration implementation with a minimal Python API.

Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

Rapid and cost-effective operator and best practice for agent sandbox lifecycle management.

Official Python SDK for the Agent2Agent (A2A) Protocol

Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating…

🧱 easy fast local-first microVM runtime and library