Skip to content
OpenSmartRoute

Marketplace

Everything your AI needs, in one place.

Ready-made agents, skills, personas, prompts, templates and tools. Each one is checked before it goes live, works with any model, and installs in a click. Rate what you use so the best rises to the top.

143.8K
listings
1
installs
0
reviews
38.7K
publishers
18 results
Skill

gdpr-expert

Expert in GDPR compliance, data protection, privacy by design, consent management, DPO responsibilities, and EU data regulations. Use when the user mentions privacy, data protection, compliance, conse

by personamanagmentlayerskills.sh
(0)
0Free
Skill

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

by davila7skills.sh
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by davila7skills.sh
(0)
0Free
Skill

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed a

by davila7skills.sh
(0)
0Free
Skill

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align

by davila7skills.sh
(0)
0Free
Skill

trl-training

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

by huggingfaceskills.sh
(0)
0Free
Skill

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

by orchestra-researchskills.sh
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by orchestra-researchskills.sh
(0)
0Free
Skill

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed a

by orchestra-researchskills.sh
(0)
0Free
Skill

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align

by orchestra-researchskills.sh
(0)
0Free
Skill

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

by ovachieverskills.sh
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by ovachieverskills.sh
(0)
0Free
Skill

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed a

by ovachieverskills.sh
(0)
0Free
Skill

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align

by ovachieverskills.sh
(0)
0Free
Skill

soup

Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO, QLoRA/DoRA/LoRA+, layer streaming for 4-8 GB GPUs,

by akillnessskills.sh
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by gabrielmoreiraGitHub
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by fabioeducacrossGitHub
(0)
0Free
Skill

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

by masoud180mohd-labGitHub
(0)
0Free
1

Find

Search or browse by kind. Every card shows who made it, how many people installed it and what they think.

2

Install

One click. You get a manifest the router understands, plus copy-paste snippets for the CLI, Python and YAML.

3

Rate and publish

Leave a star rating after you have used it. Made something useful? Publish it - free listings go live immediately.

Prefer the terminal? osr stack apply registry://starter installs the starter template.