Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Repository Index
98,836 visible repositories in the index
1–16 of 16 · Most stars
Open-source JavaScript form library for React, Angular, Vue, and plain JavaScript. Render dynamic JSON-driven forms, multi-step form wizards, surveys, quizzes, and other data-entry tools.
- survey
- javascript
- typescript
- angular
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
- agentic-ai
- agentic-workflow
- agents
- function-calling
The type-safe way to build multi-step experiences in React.
- primitive
- react
- react-native
- shadcn-ui
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
- forecasting
- scikit-learn
- machine-learning
- python
⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.
Natural language workflows that enable AI agents to perform complex, multi-step tasks with consistency and reliability.
- strands-agents
The CLI for codemods: scaffold, share, and run multi-step transformations of any size. First-class ast-grep support. Fast, reliable, polyglot.
- codemod
- jscodeshift
- migration
- ts-morph
✨ React component library for building declarative multi-step flows.
- react
- multi-step
- wizard
- one-app
Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch
- python3
- pytorch
- reinforcement-learning
- deep-reinforcement-learning
CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.
Multi-step forms for your Symfony project.
- php
- symfony
- symfony-bundle
- bundle
An AI lab for Blender where manager–worker–reviewer agent teams run multi-step scene briefs as supervised experiments—a live task board, review findings, one correction attempt per blocked task, named undo, and a built-in MCP server. · blender-ai-copilot-lab · blender · blender 3d · blender addon · blender plugin · blender extension
- 3d-automation
- 3d-modeling
- blender
- blender-addon
Desktop-first, open-source (MIT) application for running parallel agents, and multi-step custom workflows triggered by schedules, webhooks or events from tools like Linear and Sentry, across your already-used providers.
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
(THIS IS THE PUBLIC VERSION) Muse-by-Meta usage audit companion designed for those who want to understand Muse’s actions during a multi-step task without pretending to have telemetry they can’t actually access.Check out Muse, your personal AI agent. Code: 5F2V31 https://muse.ai/join
- meta
- metaai
- metaai-api
- metaai-download