
Audits GitHub Actions workflows that run AI coding agents for prompt injection risks
- Open source
- 8.3K GitHub stars
- AI models and LLM tooling

Audits GitHub Actions workflows that run AI coding agents for prompt injection risks

Drafts copy-paste-ready /goal completion conditions for long-running agent tasks

Gives a coordinator bounded, graph-selected code slices to hand smaller models

Run Gemini API calls from the shell for media generation, file analysis and transcription

Guides coding agents through writing Gemini API code for text, media, agents and decisions

Guides an agent in building real-time voice, video and text apps on the Gemini Live API

Generates, extends and edits videos with Gemini Omni 1.2 Flash via the google-genai SDK

Helps an agent find matching Earth2Studio weather and climate models, data sources

Guides an agent through adding a new training method to the NVIDIA FastGen codebase

Guides an agent through adding a new modality to NVIDIA FastGen across data, model

Guides an agent through adding a new diffusion or flow model to NVIDIA FastGen

Builds or adapts NVIDIA FastGen experiment configs for a network, task and method

Guides preparing, registering and verifying NVIDIA FastGen training datasets for an agent

Guides an agent through generating and inspecting NVIDIA FastGen teacher and student

Guides an agent through running, resuming and debugging NVIDIA FastGen training jobs

Grades or filters workflow HDF5 episodes by visual success using a vision model

Guides an agent through fine-tuning GR00T or openpi robot policies on LeRobot data

Guides training, evaluating and exporting reinforcement-learning robot policies for Isaac

Recommends an LLM serving runtime and memory flags for NVIDIA Jetson devices

Benchmarks LLM and VLM serving speed on Jetson devices with structured JSON results

Guides an agent through launching a vLLM or SGLang OpenAI-compatible server on Jetson

Adds EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server

Guides choosing and configuring FSDP2, Megatron FSDP, DDP and parallelism settings in NeMo

Sets up NeMo AutoModel job launches on interactive, Slurm and SkyPilot runs

Guides an agent through adding new model architectures to NeMo AutoModel

Guides an agent through building and changing NeMo AutoModel training and eval recipes

Runs Megatron-LM and Megatron Bridge training and checks their loss curves match

Guides selective and full activation recompute in Megatron Bridge to cut GPU memory use

Configures CPU offloading in Megatron Bridge to cut GPU memory during training

Guides an agent through enabling hierarchical context parallelism in Megatron-Bridge
See every kind of AI for ai models and llm tooling: tools, agents, MCP servers and skills.Ranked: the best AI for ai models and llm tooling.