Run parallel research agents with any model

Textbook on reinforcement learning from human feedback

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

Python API for Monarch Money

BrainPilot: Automating Brain Discovery with Agentic Research

Official code for AdaJEPA: An Adaptive Latent World Model

Harbor dataset for Senior SWE-Bench (v2026.06)

Authoritative, source-cited Claude Code plugin/skill that lets a coding agent autonomously build production-grade AI agents on AWS (Strands Agents, Amazon Bedrock, Bedrock AgentCore) with official …

Search Airbnb using your AI Agent

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 14 supported tools.

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

Evaluation-driven agent that automatically tunes and evaluates transformer-based RAG pipelines using measurable retrieval and groundedness metrics.

The headless browser for AI agents and web scraping

Customize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock pri…

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Agent skill that removes signs of AI-generated writing from text

in preparation...

Agent samples built using the Strands Agents SDK.

Experiment framework for: When Agents Disagree — Quorum-Based Consensus and Adaptive Orchestration Topology for Multi-Agent LLM Pipelines

A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

KISS Sorcar: Keep it Simple, Stupid AI General Purpose Agent Framework for Long Horizon Tasks and AI Discovery

AI agents running research on single-GPU nanochat training automatically

Python functions powered by AI agents - with runtime post-conditions for reliable agentic workflows.