Features
Execution strategies for inference scaling
Harness optimization for model-fit
Intelligent model routing across ensembles
Jamba Mini efficient lightweight model ($0.20/1M input)
Jamba Large powerful long-context model ($2/1M input)
Token visibility for usage optimization
Accuracy-engineered reliable outputs
Adaptability to unique environments
Caching strategies for agentic pipelines
Orchestrated test-time compute for long-horizon tasks
Scale-then-enrich execution strategy (SWE-rebench SOTA)
DeepResearch Bench II (DRB II) evaluation
Foundation model APIs & SDKs
Pay As You Go unlimited seats
Local model execution for offline inference
Connect online APIs: OpenAI (ChatGPT), Anthropic (Claude), Google (Gemini), Meta (Llama), Mistral AI, Alibaba (Qwen),
123+ HuggingFace models available
Memory feature (coming soon) for context persistence
Minimalist UI with dark mode
Open source under MIT license on GitHub
Cross-platform desktop app (Mac, Windows, Linux)
Version 0.8.3 with bug fixes and performance improvements