Agents
OncoAgent: Privacy-Preserving Oncology Decision Support
Hugging Face Bloghigh confidence
Why it matters
- →OncoAgent enhances privacy by enabling on-premises deployment, avoiding cloud API dependencies.
- →The dual-tier architecture ensures efficient processing of clinical queries based on complexity.
- →It addresses the critical issue of hallucinated recommendations by grounding outputs in validated guidelines.
OncoAgent, developed by the OncoAgent Research Group, is a new open-source framework for oncology clinical decision support that emphasizes privacy preservation. It employs a dual-tier LLM architecture to process clinical queries, using either a speed-optimized or deep-reasoning model based on complexity. The system is designed to operate on AMD hardware, allowing for on-premises deployment and eliminating the need for cloud-based APIs. This approach ensures that patient data remains secure while providing accurate, guideline-based recommendations, addressing key issues in existing clinical AI systems.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Google Launches Agentic AI Governance Platform
AI News · May 4, 2026 · Background
What happened next
- 2Google Unveils Agentic RAG for Complex Queries
Google Research Blog · June 5, 2026 · Background
- 3MosaicLeaks Tackles Privacy in AI Research Agents
Hugging Face Blog · June 18, 2026 · Background
- 4Scaling AI Agents with Redis Iris
Cole Medin · July 9, 2026 · Background
- 5ThunderAgent Boosts Agentic Inference Efficiency
Together AI Blog · July 29, 2026 · Background
- 6AI Tool Prioritizes Biomarkers from Wearable Data
Google Research Blog · August 21, 2026 · Background
More from Hugging Face Blog
© Hugging Face BlogAgentsagents
NVIDIA Nemotron powers interactive Halloween agent
An NVIDIA engineer built a fully local voice agent for a Halloween attraction using the new Nemotron Voice Agent framework. The system chains Nemotron ASR, the Bolt E4B small language model, and Magpie TTS to create a grumpy pirate persona that responds to trick-or-treaters in real-time. Running on dual RTX PRO Blackwell GPUs, it achieves sub-2-second latency for uncached responses, proving these open models can handle complex, multi-turn interactive tasks without cloud dependency. This demonstrates the practical viability of local AI agents for consumer-facing applications.
Hugging Face Blog
© Hugging Face BlogModels & Labsmodels
Granite Switch 4.1.1 patches adapters without retraining base
IBM’s Granite Switch 4.1.1 proves modular architectures can move with the speed of standard software updates. By keeping the base model untouched and only updating specialized adapters like the multilingual ASR and decision logic, they sidestep the massive compute cost of full retraining. This approach lets developers compose new expertise on a single endpoint without migration headaches. It signals a shift toward composable AI where models evolve incrementally rather than in disruptive leaps.
Hugging Face Blog
© Hugging Face BlogGeneral AIresearch
Project ProtoStar launches to make public science AI-ready
Hugging Face and a coalition of major universities are launching Project ProtoStar to solve the 'last mile' problem of scientific data: making it machine-actionable. With $190 billion in annual U.S. federal R&D funding, the initiative pushes institutions like CMU and Purdue to release datasets in standardized formats rather than static files. The kickoff challenge tests AI's ability to predict urban climate conditions using historical weather records from 210 cities. This shifts the focus from mere publication to actual interoperability, creating a reusable infrastructure for AI-driven discovery.
Hugging Face Blog
More in Agents
© The AI Daily BriefAgentscoding
Spawn ships 77k code changes monthly with AI agents
Ten-person team at Spawn utilizes an always-on fleet of AI agents to achieve massive monthly code output.
The AI Daily Brief
© WIRED AIAgentsagents
AI Agent Performs Live Mouse Brain Injection
Exin Therapeutics has demonstrated an AI agent physically controlling a robotic arm to inject drugs into a live mouse's brain. The experiment reveals a critical divergence in model behavior: Anthropic’s Claude Opus refused the procedure due to safety concerns, while Sonnet proceeded. This suggests that as agents gain direct access to physical lab equipment, their alignment and refusal mechanisms become operational realities rather than theoretical safeguards. It marks a shift from AI merely analyzing data to actively manipulating biological systems under human supervision. The team initially tested Claude Opus 5.5, but it halted the injection, citing potential harm. Switching to Claude Sonnet 5 allowed the procedure to complete, though with delays caused by coordinate system glitches. A secondary Opus agent had to fix code errors without knowing a live surgery was underway. Human oversight remains essential as researchers test more complex tasks like craniotomies.
WIRED AI
© TechCrunch AIAgentsagents
Zest launches AI restaurant concierge in text messages
Zest is betting that the future of discovery lives in your iMessage thread, not a standalone app. By linking credit card history via Plaid, the startup skips the cold-start problem, using actual dining habits to fuel an agent that books tables through OpenTable and Resy directly from text. It even handles group indecision with in-thread voting, turning a simple recommendation engine into a transactional concierge. This moves AI agents beyond chat into real-world commerce, proving that personal data integration is the key to utility.
TechCrunch AI