Gemini Spark, Google’s Agentic Assistant, Now Available on Mac⭐9

Google's Gemini Spark AI assistant launches on Mac, adding Keep and Tasks integrations, local file control, and real-time updates to compete with desktop rivals...

Anthropic Launches Claude Sonnet 5: A Cheaper Path to Autonomous Agents⭐9

Anthropic's Claude Sonnet 5 offers powerful agentic capabilities at a lower cost, shifting competition from features to affordability and reliability.

Building Supervised Fine-Tuning Data from NVIDIA Open-SWE-Traces: Trajectory Parsing, Patch Analysis, Token Budgets, and Tool-Use Metrics⭐6

Build supervised fine-tuning data from NVIDIA's Open-SWE-Traces dataset: parse trajectories, analyze patches, manage token budgets, and filter by tool-use metri...

Perplexity Launches Computer for Counsel: A Multi-Model Agentic Layer for Legal Workflows⭐8

Perplexity launches Computer for Counsel: a multi-model agentic layer routing 20+ AI models per legal task. Available now for Enterprise and Max subscribers to ...

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems⭐9

A practical guide to building autonomous AI agents in 2026, covering foundations, alignment, and multi-agent systems for engineers.

Mistral OCR 4 Delivers Citation-Ready Structured Output for RAG, Agentic, and Enterprise Search Pipelines⭐6

Mistral OCR 4 delivers citation-ready structured output with bounding boxes, confidence scores, and 170-language support for self-hosted RAG, agentic, and enter...

The AI World Gets ‘Loopy’: Why Autonomous Agent Cycles Are the Next Big Thing⭐8

Meta’s @Scale conference highlights AI loops as the next big step, with autonomous agents continuously improving code and running unsupervised by 2026.

Nous Research Updates Hermes Agent With a Blank Slate Mode That Pins Toolsets via platform_toolsets.cli and disabled_toolsets⭐6

Nous Research updates Hermes Agent with Blank Slate mode, requiring users to define toolsets via platform_toolsets.cli and disabled_toolsets for precise, effici...

Deontic Policies for Runtime Governance of Agentic AI Systems⭐10

AgenticRei proposes deontic policies for runtime governance of AI agents, managing obligations, waivers, and conflict resolution beyond traditional access contr...

Is It Agentic Enough? Benchmarking Open Models on Your Own Tooling⭐9

Benchmark open models on custom tooling to evaluate real agentic abilities like task decomposition, tool use, and error recovery.