Added first-class support for Cerebras as an OpenAI-compatible LLM provider in anything-llm, enabling chat and agent workflows to use Cerebras models via existing infrastructure with minimal configuration changes.
Enabled chat and agent workflows to natively consume Cerebras LLMs using the same provider abstraction as Groq and SambaNova, including dynamic model discovery and optional native tool calling.
Developers and operators using anything-llm can now deploy AI agents or chat interfaces with Cerebras models without rewriting provider logic — reducing integration friction and expanding available inference backends. Teams must monitor per-model tool-call support variance (like Groq) and ensure API keys are configured correctly to avoid silent failures. Also watch for model availability changes that may affect context windows or token limits.