Konjugate's causal inference tool now supports interaction terms and input replay, enabling models to represent relationships where the effect depends on multiple variables jointly, such as predator-p…
Konjugate's model assistant now supports real AI providers, including Ollama, OpenAI, NVIDIA NIM, Hugging Face Inference Providers, and Google Gemini, with API key management and encrypted credential …
Konjugate's documentation introduces a new causal inference workflow that recovers model structure directly from CSV time-series data, proposing directed relationships via Granger-style lagged predict…
The model assistant, a new feature from an unspecified developer, lets users describe model changes in plain language and generates a proposal of nodes, states, relationships, and equations for review…
Konjugate v0.7.0 introduces a causal inference feature that recovers causal graphs from CSV time-series data, demonstrated on an 8-node synthetic thermal/vibration system with a known structure. The t…
Konjugate, a graph-native visual simulation engine with AI modeling workflows, is now available in alpha, enabling users to compose stateful nodes, define relationships, and run simulations with local…