The request names gemma-2b-it, oasst2 and aya, which are model and dataset names rather than software tools, so the closest fit is a way to run Gemma 2 2B instruction-tuned models. Replicate hosts the Gemma2 2b instruction-tuned variant 15, and SGLang is a serving framework for running language models at scale 2; the sources do not show oasst2 or aya datasets as products.
- 1
- 2
SGLangsglang.iowebsite read, tools not yet checked
Open-source serving framework for large language models that provides fast, scalable inference for running a model such as Gemma 2.
+2 community tools built for it
- 3
E2Be2b.devfound in code, not yet checked
Runs Python code in an isolated sandbox through its run_code action, which could be used to execute training or inference scripts for these models 37.
official:MCP server · e2b-mcp-serverSDK · e2brepository · e2b-cookbookMCP server · mcp-demo
for agents: run_code
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2SGLang – Fast, Open-Source LLM & Multimodal Serving Frameworksglang.io · read 2026-10-29
- 3E2B | The Enterprise AI Agent Cloude2b.dev · read 2026-10-29
- 5google-deepmind/gemma-2-2b-it: declares "google-deepmind/gemma-2-2b-it" (the record we read and signed)unfragile.ai · read 2026-10-24
- 7e2b-mcp-server: declares "run_code" (the record we read)github.com · read 2026-10-24
For agents: the 10 actions behind this answer
google-deepmind/gemma-2-2b-it · google-deepmind/gemma-2-2b-it verified and signed
Gemma2 2b Instruction-tuned variant by Google
google-deepmind/gemma-2b-it · google-deepmind/gemma-2b-it verified and signed
2B instruct version of Google’s Gemma model
google-deepmind/gemma2-27b-it · google-deepmind/gemma2-27b-it verified and signed
Google's Gemma2 27b instruct model
google-deepmind/gemma2-9b-it · google-deepmind/gemma2-9b-it verified and signed
Google's Gemma2 9b instruct model
google-deepmind/gemma-7b-it · google-deepmind/gemma-7b-it verified and signed
7B instruct version of Google’s Gemma model
google-deepmind/gemma-3-27b-it · google-deepmind/gemma-3-27b-it verified and signed
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
google-deepmind/gemma-3-12b-it · google-deepmind/gemma-3-12b-it verified and signed
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
lucataco/gemma-4-31b-it · lucataco/gemma-4-31b-it verified and signed
Gemma 4 31B Instruct - Google open-weight VLM (image + text in, text out)
google-deepmind/gemma-3-4b-it · google-deepmind/gemma-3-4b-it verified and signed
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
google-deepmind/shieldgemma-2-4b-it · google-deepmind/shieldgemma-2-4b-it verified and signed
ShieldGemma 2 is a model trained on Gemma 3's 4B IT checkpoint for image safety classification across key categories that takes in images and outputs safety labels per policy.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.