So, no more login to open the terminal ?

This feels like the right strategic move at the right time. With today's AI/vibe-coding capability, the advantage of a closed-source product with a similar UX can erode very quickly: people can now prototype, fork, and iterate on missing pieces much faster than before.

In that environment, the durable moat is less about keeping the client private and more about trust, review quality, product taste, extension surface, and the speed at which the community and maintainers can turn good ideas into shipped improvements.

Open-sourcing the client makes Warp much more credible as the workbench for agentic development. Excited to see how the contribution flow around Oz works in practice.

This is fantastic news! Maybe now we can get local models to integrate!

🚀 Congrats to the team and fair winds to Warp! It's a rare case when a product of this scale - a million active developers, five years of work - doesn't lock its work behind closed doors but instead entrusts it to the community.

For me personally, this isn't just a chance to "use a tool" - it's a chance to actually shape what a developer's workspace looks like in the age of agents. Truly grateful for the opportunity to take part.

To fellow community members: don't sit this one out. The future of agentic IDEs is literally being written in the open right now - and it will be exactly what we make of it. If everyone contributes even a small issue, a bug report, a patch, or an idea on the roadmap, we'll end up with a tool built around real-world needs, not someone's vision in a vacuum. Moments like this don't come often; it would be a shame to let it slip.

Good luck, Warp! 🚀

Can we bring our own AI model and skip login?

@zachlloyd Hi Warp team, can you upload the redistribution archives for all OS in the GitHub release page?

I have tried several times to download the Warp from your official website(warp.dev) or from winget under windows, all failed due to the transfer is terminated in the middle way.

Quick update on one of the big themes in this thread: Zach shared our plan for BYOK, arbitrary OpenAI-compatible endpoints, local models, and ACP support. Near term, BYOK is planned for the free plan and arbitrary OAI-compatible endpoints; longer term, we’re working toward client-side local model support and ACP so users can bring their own inference without routing through Warp’s servers. Details: #9619 (comment)

Enable full support for bringing your own llm apis, it's basically open source, but not open source at the same time with the core being gated still.

Without being able to modify the models URL and use whatever model provider you want / local it seems like a obvious win for everyone. Enterprises often use custom URL's. It is very common across the board so adding it would help paying and open source users!

Very weird its not in

Buying some ads with this move? The software still requires login.

Quick update on one of the themes in this thread: we’ve shipped BYOK on the Free plan for individual users, and Warp now supports custom inference endpoints compatible with the OpenAI Chat Completions API.

That means you can use your own OpenAI, Anthropic, or Google API key, or connect Warp to an OpenAI-compatible endpoint such as OpenRouter, LiteLLM, z.ai, an internal gateway, or a hosted/self-hosted inference setup.

Docs:

• BYOK: https://docs.warp.dev/agent-platform/inference/bring-your-own-api-key/
• Custom inference endpoints: https://docs.warp.dev/agent-platform/inference/custom-inference-endpoint/

Fully client-side local model support and external harness support are still separate directions. We’re planning a lightweight local client harness for direct local model connections, and support for Agent Client Protocol so developers can bring other harnesses into Warp’s terminal UI.

If you try the new inference setup and hit a specific issue, please open a focused GitHub issue with the provider, endpoint, model, and error so we can track it directly.