by modelship-ai · Agent Tool · ★ 53
Modelship Modelship runs the AI stack your agents call — chat, the Responses API with server-side conversation state (durable with Redis), universal tool calling, and reasoning, alongside embeddings, speech, and image generation — behind one OpenAI-compatible endpoint on your own GPUs (or CPU). Built on Ray Serve: state is shared across gateway replicas, deploys are declarative, and everything is observable. Point the OpenAI SDK at it and your agent runs unchanged — private, with no per-token bill.
| Stars | 53 |
| Forks | 4 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.5410608406845/100 |
| Last Updated | 2026-10-13 |
| Created | 2025-08-05 |
| Platforms | python |
| Est. Tokens | ~17k |
These tools work well together with modelship for enhanced workflows:
Explore other popular agent tool tools:
modelship is Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GP. It is categorized as a Agent Tool with 53 GitHub stars.
modelship is primarily written in Python. It covers topics such as agentic, diffusers, embeddings.
You can find installation instructions and usage details in the modelship GitHub repository at github.com/modelship-ai/modelship. The project has 53 stars and 4 forks, indicating an active community.
modelship is released under the Apache-2.0 license, making it free to use and modify according to the license terms.