A focused feed of models, agents, research and open-source releases for people building with AI.
Locals is a new Apache 2.0 local inference server for Apple Silicon, built for agents not chat. Hits up to 3x mlx-lm throughput with 8 concurrent requests on Qwen3.5-4B. Based on the paper Breaking the Space Barrier , moving grammar checks onto the GPU.
OpenAI's autonomous pipeline found and exploited 948 unique Linux kernel privilege escalation bugs in one run. Total API cost was $1,213,430, roughly $1,279 per unique root-access vulnerability discovered and patched.
Nous Research launched the Hermes Marketplace , unifying plugins, skills, and connectors in one storefront. Catalog now lists 976 plugins across Official (213), Verified (9), and Community (1,465) trust tiers.
Gemini API computer use tool is now generally available with no breaking changes from preview. Supports browser, mobile, and desktop environments through a single computer_use tool configuration. Four models supported, with Gemini 3.8 Flash recommended and Gemini 4 Argon for complex tasks.
NVIDIA expanded its open source Agent Toolkit with a new Agent Knowledge Foundation grounding agents in company data. New Kumo open model family covers tabular, relational, time series and forecasting workloads over enterprise data.
Agent Autoloop is a self-hosted middleware that drives CLI agents like Claude Code and Codex in the background. Install with a single curl command on Mac or Linux; no cloud server or public port required.
Shawn Pana open-sourced Phone Harness , a Python toolkit letting agents control iPhones and Androids. Works via iPhone Mirroring plus Apple Vision OCR on macOS, and adb plus the accessibility tree on Android.
Claude users can now auto-connect MCP plugins at login via Enterprise Managed Auth , no per-service OAuth prompts. Admins configure plugins once through their identity provider; access flows from SSO policy. Built on an open MCP extension using ID-JAG and RFC 7523 JWT bearer grants.
SAPPER-v2 is an open-source multi-agent pentest framework with one AI commander dispatching a worker swarm ( repo ) Won 3rd Tencent Intelligent Attack-Defense online qualifier, 80.18/100, beating 633 other teams running 8 hours unattended Used 1B tokens to tie the runner-up's 85 flags, who burned
SGLang HiCache now integrates with context parallelism, pipeline parallelism, speculative decoding, and prefill-decode disaggregation serving iFLYTEK Astron production: cache hit rate jumped from 30% to 95%, median TTFT under 3 seconds on GLM-5.1/5.2 CP sharding raised GPU token hit rate ~40 points
ARTEX is an open-source autonomous pentesting system in Go with a Next.js UI, released under AGPL-3.0 Dual-graph design separates per-task exploration from a globally shared asset graph, linked by anchors Planner dispatches intents, N worker agents claim and execute them with real tools through a
New arXiv paper introduces DR Pixel, a deep research agent that retrieves and reasons over rendered page images instead of OCR text. Operates over a 1.06M-page corpus and beats OCR baselines on GPT-5.4, Gemini-3.5-Flash, and Qwen3.6-27B with fewer tool calls.
AI agent lab at Institute of Science Tokyo ran a full quantum physics study end-to-end. Agents derived an exact L^2 + 1 calibration law for NV-center ensembles in diamond. 75 proposals were generated; only one was accepted after PI-agent review.
Tencent Hunyuan released Hyra 2.0 , an AutoResearch agent that builds reusable scientific tools instead of one-off answers. New Overall/Mission/Worker three-tier architecture supports long-horizon tasks, parallel experiments, and persistent experience accumulation.
Kanzo is a Rust kanban board plus MCP server in one 4.1 MB binary. Agents like Claude Code and Codex read and move cards on the same board you see. Idle memory is 4.5 MB, cold start is 2 ms, agent replies are 10 to 60 tokens.
Scenario Labs open-sourced 70+ Agent Skills for images, video, audio, 3D over MCP Works with Claude Code, Cursor, Codex, Copilot and 70+ other agents via the open Agent Skills format Install with npx skills add scenario-labs/skills --skill "*" and connect mcp.scenario.com Core loop: discover,
DeepSeek open sourced dsh-superagent-prototype , a research prototype of its internal coding super-agent. It is a proactive agent scoped to one GitHub repository, bundled for DeepSeek Harness, MIT licensed.
Agent Sprite Forge 0.4 turns one approved master still into a full six-action sprite set. Pipeline: master still, image-to-video per action, soft-matte key, loop detection, retime, finish, package. Supports OpenAI, Gemini, xAI, BytePlus, fal.ai APIs with Codex/Grok CLI fallback.
Mika is an open-source Android AI agent that operates apps on a hidden background screen while you use your phone Over 2,000 GitHub stars within days, Apache-2.0 licensed, written in Kotlin and available on GitHub Bring-your-own-key design supports OpenAI-compatible, Anthropic and Gemini endpoints
Mainplane is a new open-source, MIT-licensed agent harness written in Go. Replaces lossy context compaction with on-demand retrieval from full session transcripts stored as files. Reported 15s and $0.10 to resume a 400k-token session vs 38s and $1.99 for compaction.
Aura open-sourced Autopilot , an in-editor playtesting agent under Apache 2.0. Supports Unreal Engine 5, Unity 6 and Godot 4 on Windows and macOS. Hit 7/7 on a seven-task Unreal benchmark vs 5/7 for Claude Code, at 1.7x the speed.
Runway Agent now opens files, runs code, and browses the web beyond pure generation Produces brand launch kits, product shots, ad variations, and motion graphics from references Writes Python code when pixel-exact placement, margins, or typography are required Builds on prior Agent additions:
Factory acquired Typedef , a context layer startup for enterprise data, to bolster Droid coding agents. Typedef maps dependencies across data models, pipelines, and dashboards so agents can plan safer migrations.
JEV-9B is an open-weights 9B model combining calibrated System 1 decisions and System 2 reasoning in one engine, via Hugging Face Mean KL divergence of about 0.019 nats from closed TypeSafe Jev 1.13's output distributions on 25,376 held-out questions Trained with Blocks of Experts: 40.2M-parameter
No stories match these filters.
