Remote agents in Vibe. Powered by Mistral Medium 3.5.
Introducing Mistral Medium 3.5, remote coding agents in Vibe, plus new Work mode in Le Chat for complex tasks.
Get smart on it
Mistral AI has released remote agents for its Vibe coding tool, powered by a new model called Mistral Medium 3.5. These agents can run coding tasks in the cloud asynchronously, allowing developers to start them from a command line interface or chat interface and receive notifications when complete, rather than waiting for each step locally. Mistral Medium 3.5 is a 128-billion parameter model designed for long-horizon tasks that can handle instruction-following, reasoning, and coding, and it can run on as few as four GPUs for self-hosting. The remote agents integrate with existing developer tools like GitHub, Linear, Jira, and Slack, and can work through tasks like module refactors, test generation, and bug fixes while keeping humans in the loop where needed.
Related news
Mistral OCR 4 Brings Citation-Ready Structured Output to RAG, Agentic, and Enterprise Search Pipelines
Today, Mistral AI released OCR 4, its latest document-understanding model. This new release adds bounding boxes, block classification, and inline confidence scores alongside extracted text. It supports 170 languages across 10 language groups and runs in a single container for fully self-hosted deployments. OCR 4 also serves as an ingestion component for enterprise search, RAG, and domain-specific retrieval pipelines. TL;DR OCR 4 returns bounding boxes, typed-block labels, and per-word c
Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
Datalab has released lift, a 9B open-weights vision model for structured extraction. You pass it a JSON schema, and it returns a JSON object that matches. The model reads PDFs and images directly, then decodes against your schema. This is Datalab’s first model built purely for extraction. The team already ships open-source OCR tools: chandra, marker, and surya. lift extends that work into schema-driven field extraction. lift scores 90.2% field accuracy on Datalab’s 225-documen
