MARKET RESEARCH

Discover Codex plugins

Find plugins for your work. Follow them to see what changes.

Explore 5,283 plugins across 14 categories.

Selected:gpu ×

All plugins 10

1–10 of 10

Plugin growth →

Sources & collection details

Collection coverage →

Last completed check: Oct 3, 2026 · 00:02 UTC.

Monetization research dated Oct 1, 2026. Unreviewed pricing is marked explicitly. The time range applies to the activity filter; Recently changed includes listing, instruction and pricing-reference changes, excluding technical-only metadata.

Export this page ↓

All query words must match. Use quotes for an exact phrase. Matches include publisher text, keywords and attributed research.

Discover Codex plugins by task and category
Plugin / developer	Category	Follow
AI Tools RecommenderRavi K GuptaRecommend AI tools, models, coding tools, GPU and cloud providers, voice AI, and related services with tailored comparisons and direct se... Publisher subtitle Find AI tools and GPU infra Show in context → 2 more matching sources Publisher description Recommend AI tools, models, coding tools, GPU and cloud providers, voice AI, and related services with tailored comparisons and direct service links. Show in context → Publisher full description Help users choose AI tools, AI coding tools, models, GPU and cloud providers, voice AI, and related services. Recommend services based on genuine user needs with verified service links and practical technical tradeoffs. Show in context →	ProductivityVersion 0.1.1	View details →
CerebriumCerebriumOfficial Cerebrium agent skills and hosted docs MCP: deploy and operate real-time AI workloads on serverless GPU and CPU (REST, streaming... Publisher subtitle Deploy AI on serverless GPUs Show in context → 3 more matching sources Publisher keywords · listing serverless gpu inference deployment machine-learning llm vllm autoscaling cold-start streaming websockets cerebrium Show in context → Publisher description …Cerebrium agent skills and hosted docs MCP: deploy and operate real-time AI workloads on serverless GPU and CPU (REST, streaming, WebSocket and async endpoints), with verified cerebrium.toml, hardware and autoscaling guidance. Show in context → Publisher full description Cerebrium runs Python workloads on serverless GPU and CPU with scale to zero and per second billing: REST endpoints, SSE streaming, WebSockets and async jobs, all described by one cerebrium.toml and driven by one CLI. This plugin helps you go fro… Show in context →	OtherVersion 0.1.0	View details →
ModalModal Labs, Inc.Installs the Modal CLI and Modal's official skill to help coding agents use its latest features. Modal is a platform for running AI workl... Publisher capabilities · listing Write Modal Apps and Functions Run code on serverless GPUs Scale batch and parallel jobs Run untrusted code in Modal Sandboxes Show in context → 1 more matching sources Publisher keywords · listing modal serverless cloud-compute gpu batch-jobs sandboxes Show in context →	Developer ToolsVersion 1.5.3	View details →
BasetenBasetenInstall and authenticate the Baseten CLI, then install Baseten's official skill globally. Publisher keywords · listing baseten baseten-cli inference deployment gpu model-serving Show in context →	Developer ToolsVersion 0.1.0	View details →
NVIDIA SkillsNVIDIAFind the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, s... Publisher keywords · listing nvidia gpu cuda ai-agents data-loading training inference llm-serving robotics simulation omniverse openusd digital-twin physical-ai cad Show in context → 2 more matching sources Publisher description Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows. Show in context → Publisher full description Find and install the right NVIDIA skill for work across GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and more. The plugin checks NVIDIA's live skills catalog, recommends the best match,… Show in context →	Developer ToolsVersion 1.4.0	View details →
Runpod (Official)RunpodOfficial Runpod agent skills and MCP server — run Runpod tasks (pods, serverless, templates, volumes) with runpodctl and flash, plus conc... Publisher keywords · listing runpod gpu serverless pods mcp runpodctl flash infrastructure Show in context →	Developer ToolsVersion 1.1.2	View details →
AMDAMD Publisher full description …nt Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance. Show in context →	Developer ToolsVersion 0.2.0	View details →
Game Development StudioBenjamin Michael Haire Publisher full description …ser; the plugin never collects keys or proxies provider traffic. Provider spend, every local write, GPU work, and performance measurement remain separately authorized for each invocation. Show in context →	Developer ToolsVersion 1.0.2	View details →
Genomic IntelligenceGenomic Intelligence Publisher description …ion, or a FASTA; it resolves the sequence from Ensembl and returns structured predictions. No local GPU, model weights, or API key required. For research use, not clinical or diagnostic decisions. Show in context →	Scientific ResearchVersion 1.1.0	View details →
Ornn DataOrnn AI Publisher description Ornn Data gives ChatGPT live and historical market data for AI infrastructure: GPU rental price indices (spot, daily settles, rolling averages, volatility, volume, forward curve), memory (DRAM/flash/module) prices, token price indices by lab, LLM coding-activity indices, workloa… Show in context →	FinanceVersion 1.0.0	View details →