modelscope/AgentJet

auto-research-blueprint-execute-classic

Execute AgentJet reinforcement learning experiments using experiment blueprints in classic (non-swarm) mode. Handles full lifecycle: launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants…

auto-research-blueprint-execute-swarm

Execute AgentJet reinforcement learning experiments using experiment blueprints in swarm mode. Handles full lifecycle: generate blueprint if needed, launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when…

原文语言：多语言混合

conda-install-agentjet-swarm-server

Install AgentJet swarm server using Conda. Handles Python 3.10 environment creation, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.

原文语言：英语

docker-install-agentjet-swarm-server

Install and run the AgentJet Swarm Server in a Docker container with NVIDIA GPU support. Use when the user wants to deploy a swarm server on a GPU machine via Docker, including GPU driver setup, Docker mirror configuration, model weight mounting, and server…

原文语言：英语

download-from-swanlab-url

Download per-step time-series metric data (reward, entropy, response length, etc.) from a SwanLab cloud run URL as a pandas.DataFrame. Use when the user provides a SwanLab URL and wants to fetch or analyze training curves.

原文语言：英语

install-agentjet-client

Install AgentJet client for connecting to a swarm server. Use when the user only needs to run the AgentJet client (not a swarm server) and does not need to run models locally, e.g. on a laptop. Installs basic requirements via `pip install -e .`.

原文语言：英语

map-verl-config

Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters…

原文语言：英语

skill-normalizer

Convert skills in non-standard formats to the standard Agent Skills `SKILL.md` format. Validates YAML frontmatter (name, description, license, compatibility, metadata, allowed-tools), directory structure (SKILL.md, scripts/, references/, assets/), and best…

原文语言：英语

train-complex-blackbox

Train complex blackbox agents (agents without clear reward signals) using AgentJet. Write dataset collectors, episode runners with LLM-as-Judge reward functions, and integrate with the AgentJet training loop.

原文语言：英语

uv-install-agentjet-swarm-server

Install AgentJet swarm server using the UV package manager. Handles virtual environment creation with Python 3.10, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.

原文语言：英语

write-swarm-client

Create an active, dataset-driven AgentJet swarm client. Write agent_roll.py and agent_run.py that iterate through a dataset, execute agent workflows, and compute rewards for reinforcement learning training with AgentJet Swarm.

原文语言：英语

swarm-configuration

How `max_env_worker` caps the "Running Episodes" gauge, and how `AgentJetJob` relates to the YAML config.

原文语言：英语

monitor-with-tmux

Monitor training progress by reading tmux content with exponential backoff intervals (30s, 1min, 2min, 4min, 8min, 16min), analyze logs when anomalies occur, and provide fix suggestions

原文语言：英语

write-passive-swarm-client

Create a passive swarm client that waits for user input instead of iterating through a dataset by itself.

原文语言：英语