Trident is a desktop AI workspace where Anthropic, OpenAI, and Gemini run side‑by‑side on the same project. Same documents, same context, two chat panels. Pick the right model for each turn.
Free and open source on GitHub
Bring your own provider credentials, encrypted and stored locally.
Bring your own API keys. Trident routes each turn to the model you pick, with shared project documents and generated images available to both chat panels. You can also connect Amazon Bedrock, Google Vertex AI, or Azure OpenAI using your own cloud account.
Flagship and legacy models. Long-form thinking, careful editing, the voice that shows up in product copy.
Flagship and legacy models with reasoning effort dialed per conversation, from low latency to slow, careful work.
Flagship and legacy models. Deep multi-modal reasoning or fast iteration. Pull either side onto the same project at any moment.
Trident is built around collaboration between you and the models, and between the models themselves. Every feature is a way to keep that conversation moving on one body of work.
Two models, one project. Bounce a draft between them, ask them to critique each other, or split the work: outline on the left, prose on the right.
Both models and you work on the same files. Edits made by either side appear instantly on the other. No copy-pasting between tabs.
Enable OpenAI semantic indexing to search project documents by meaning. Document text is sent to OpenAI for embeddings.
Generated images live alongside their prompts and the conversation that produced them. Re-run with a different model in one click.
⌘K opens to your projects, conversations, and documents. Searches embeddings inline.
Dial reasoning effort per conversation: Low for quick passes, Max for slow, careful collaborators. Same model, different temperament.
Trident is at its best on the work that takes weeks, not minutes, where the strengths of different models actually compound.
Outline a chapter with Sonnet, then have Gemini stress-test the argument against your sources. Switch to Opus for the final pass when the prose has to sing. Every conversation stays attached to the same draft.
Drop interview transcripts and papers into a project. Ask GPT-5 to surface themes while Claude drafts a synthesis, both reading the same corpus, both citing the same files. Compare the takes side-by-side.
Keep a project per book with chapters, character notes, and a timeline. Use one panel as your editor, the other as a second reader who's been with the manuscript from page one. Continuity becomes the workspace's job, not yours.
One model plays optimist, the other plays critic. The spec doc sits between them, picking up edits from both sides and from you until the design is ready to share with the team.
Contracts, RFPs, grant proposals. Ask both panels to flag risks independently. When they agree, you have a real issue. When they disagree, you have a question worth asking.
Outline lessons with one model, generate worked examples and exercises with the other: same syllabus document, two voices, all the way through to slides and handouts.
Add Anthropic, OpenAI, or Gemini API keys, or connect your cloud account. Credentials are encrypted and stored locally.
Pick a folder. Add documents. Embed the project once and the agent can navigate it by meaning.
Two conversations, two models, one project. Swap providers per turn: same context, different perspective.
Ask any model to make an image and Trident hands you a config card. Write the prompt, pick the image model, set dimensions and quality, and the result drops straight into your project gallery.
Trident stores your workspace on your computer. AI features send the content needed for each task directly to the configured provider. Trident has no backend that receives your prompts.
Provider credentials are encrypted with your operating system’s secure storage and used to authenticate directly with your providers.
Documents, conversations, and embeddings live in a local database. Project documents and images are also saved as ordinary files on your disk.
No analytics or usage tracking. Update checks, pricing refreshes, and provider logos make background requests. See the privacy policy for details.
Chat and image requests send the required content to your selected provider. Optional semantic indexing sends document text to OpenAI, regardless of your chat provider.
Free and open source. Bring your own provider credentials.
v0.6.0 · macOS 13 Ventura or later · Apple Silicon
