by ARahim3 · Codex Skill · ★ 215
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
| Stars | 215 |
| Forks | 40 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 56.7413440058258/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-15 |
| Created | 2026-08-31 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~13k |
These tools work well together with kaggle-tpu-lab for enhanced workflows:
Looking for a kaggle-tpu-lab alternative? If you're comparing kaggle-tpu-lab with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex,
Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch
The production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/
Multi-account pool proxy for Windsurf — 113+ models (Claude/GPT/Gemini/Grok/Kimi) via OpenAI & Anthropic APIs,
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code Or Codex Or Opencode!
Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool pars
Explore other popular codex skill tools:
kaggle-tpu-lab is Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, C. It is categorized as a Codex Skill with 215 GitHub stars.
kaggle-tpu-lab is primarily written in Python. It covers topics such as anthropic-api, claude-code, coding-agents.
You can find installation instructions and usage details in the kaggle-tpu-lab GitHub repository at github.com/ARahim3/kaggle-tpu-lab. The project has 215 stars and 40 forks, indicating an active community.
kaggle-tpu-lab is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kaggle-tpu-lab on Agent Skills Hub include helix, the-pair, flama. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: