Website · Code · Agents · Terminal · Drive · Docs · How Warp Works
Note
OpenAI is the founding sponsor of the new, open-source Warp repository, and the new agentic management workflows are powered by GPT models.
Warp is an agentic development environment, born out of the terminal. Use Warp's built-in coding agent, or bring your own CLI agent (Claude Code, Codex, Gemini CLI, and others).
Warp's Agent Mode supports custom AI providers alongside the built-in Warp cloud models. Configure multiple providers simultaneously and pick a specific provider and model per conversation — all from Settings > AI > Custom AI Providers.
| Provider | API Type | Streaming | Notes |
|---|---|---|---|
| OpenAI | OpenAI-compatible | SSE | GPT-4o, GPT-4 Turbo, o-series, and any OpenAI-compatible endpoint |
| Anthropic | Native Messages API | SSE | Claude Opus, Sonnet, Haiku via api.anthropic.com or self-hosted relays |
| Ollama | Native /api/chat |
NDJSON | Local models (Llama, Mistral, Qwen, etc.) with native tool-call support |
| Google Gemini | Native generateContent |
SSE | Gemini 1.5/2.0 via generativelanguage.googleapis.com |
| DeepSeek | OpenAI-compatible | SSE | DeepSeek-Chat and DeepSeek-Reasoner (chain-of-thought rendered separately) |
Any OpenAI-compatible endpoint (LM Studio, vLLM, text-generation-inference, LocalAI, etc.) works out of the box with the OpenAI API type.
- Multiple providers at once — run Ollama locally, Anthropic in the cloud, and a remote OpenAI-compatible box side by side. Each conversation picks its own provider and model.
- One-click model discovery — the Fetch models button queries each provider's upstream model-list endpoint; the Browse catalog modal pre-fills metadata from the open-source models.dev catalog.
- Multimodal attachments — attach images, PDFs, and audio files to agent turns via the file-picker button, drag-and-drop, or paste-from-clipboard. Each adapter translates attachments into the provider's native wire format. Per-model capability chips (image / pdf / audio) in settings control which modalities are allowed.
- Dedicated compaction model — route conversation summarization to a separate, cheaper model (e.g., Haiku or a local Ollama model) while the primary agent model handles reasoning and tool use. Configure via the Summarization model dropdown in the BYOP settings section.
- Test connection — per-provider probe button confirms endpoint reachability before you start a conversation.
- Auto-migration — existing single-provider configurations are migrated automatically on first launch.
Providers are stored in settings.toml under agents.warp_agent.providers. API keys are stored in the OS keychain. See specs/multi-local-llm/design.md for the full architecture and specs/multi-local-llm/README.md for per-phase implementation status.
You can download Warp and read our docs for platform-specific instructions.
Explore build.warp.dev to:
- Watch thousands of Oz agents triage issues, write specs, implement changes, and review PRs
- View top contributors and in-flight features
- Track your own issues with GitHub sign-in
- Click into active agent sessions in a web-compiled Warp terminal
Maintaining a popular open-source project? Apply for Oz credits to explore Oz for OSS.
Oz for OSS is our partner program for bringing the same agentic open-source management workflows used in this repository to select partner repositories. We work directly with maintainers to implement workflows for issue triage, PR review, community management, and contributor coordination in a way that fits each project.
Warp's UI framework (the warpui_core and warpui crates) are licensed under the MIT license.
The rest of the code in this repository is licensed under the AGPL v3.
Warp's client codebase is open source and lives in this repository. We welcome community contributions and have designed a lightweight workflow to help new contributors get started. For the full contribution flow, read our CONTRIBUTING.md guide.
Tip
Chat with contributors and the Warp team in the #oss-contributors Slack channel — a good place for ad-hoc questions, design discussion, and pairing with maintainers. New here? Join the Warp Slack community first, then jump into #oss-contributors.
Before filing, search existing issues for your bug or feature request. If nothing exists, file an issue using our templates. Security vulnerabilities should be reported privately as described in CONTRIBUTING.md.
Once filed, a Warp maintainer reviews the issue and may apply a readiness label: ready-to-spec signals the design is open for contributors to spec out, and ready-to-implement signals the design is settled and code PRs are welcome. Anyone can pick up a labeled issue — mention @oss-maintainers on an issue if you'd like it considered for a readiness label.
To build and run Warp from source:
./script/bootstrap # platform-specific setup
./script/run # build and run Warp
./script/presubmit # fmt, clippy, and testsSee WARP.md for the full engineering guide, including coding style, testing, and platform-specific notes.
Interested in joining the team? See our open roles.
- See our docs for a comprehensive guide to Warp's features.
- Join our Slack Community to connect with other users and get help from the Warp team — contributors hang out in
#oss-contributors. - Try our Preview build to test the latest experimental features.
- Mention @oss-maintainers on any issue to escalate to the team — for example, if you encounter problems with the automated agents.
We ask everyone to be respectful and empathetic. Warp follows the Code of Conduct. To report violations, email warp-coc at warp.dev.
We'd like to call out a few of the open source dependencies that have helped Warp to get off the ground: