21 tagged multimodal, measured the same way as everything else here.
Browse within: agent-runtime 9content-generation 9creative-tools 9generative-ai 9Distributed Training 5GRPO 5Multi-Agent 5Post-Training 5agentic-rl 5caching 5data 5metadata 5pipelines 5python 5
Agent Codex
Search local Fern documentation for content related to a topic. Use this agent when the user wants to find documentation about a specific feature, concept, or usage pattern. Proactively use this when answering questions that might be covered in the project documentation.
Agent Codex
Search GitHub issues, discussions, and PRs for content related to a topic. Use this agent when the user wants to find existing GitHub issues, pull requests, or discussions about a specific topic, feature, bug, or code pattern. Proactively use this when researching whether something has been discussed or implemented…
Agent
Ray orchestration & service deployment expert. Fire when working on Ray Serve deployment, placement groups, service lifecycle, rollout engine management, health monitoring, or troubleshooting job launch and GPU allocation issues.
Agent
An expert assistant for integrating and configuring Megatron, a system for training very large machine-learning models across multiple processors or machines.
Agent
Ray framework expert. Fire when working on Ray cluster management, ray.init/ray.remote/ray.get patterns, placement groups, scheduling strategies, Ray Serve deployments, ray job submit, runtime environments, or troubleshooting Ray-specific errors (serialization, object store, GCS, scheduling failures).
Agent Claude Code
Use this agent when you need to create GitHub issues for the project. The agent will collaborate with planner and python-dev agents to properly scope and describe the issue, then format it according to project standards before seeking user confirmation.\n\nExamples:\n- \n Context: The user wants to create a GitHub…
Agent Claude Code
Use this agent when the user presents a complex, multi-step task that requires clarification, decomposition, or planning before execution. This includes:\n\n \nContext: User requests a large feature implementation that spans multiple components.\nuser: "I need to add support for PostgreSQL as a metadata store…
Agent Claude Code
Use this agent when you need to write, refactor, or review Python code that requires expert-level quality, maintainability, and adherence to best practices. This includes:\n\n- Writing new Python modules, classes, or functions from scratch\n- Refactoring existing code to improve design, performance, or…
Agent
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Agent
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Agent
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.