ai-agents
Sandboxing an AI agent: least privilege for a program that improvises Lesson
Sandboxing an AI agent means deciding in advance what actions it can take, rather than trusting it to decide well in the moment, because an agent's behaviour is shaped by text that attackers can often influence and no amount of model quality closes that gap.
Four agent-memory papers landed in a week, and none tested what happens when an attacker controls the writes News
Four papers published within days define an AI agent's memory as four incompatible things - a pretrained module, a rewritten lesson, a folder of files, and a reliability ledger - and three of them introduce writable state that determines future behaviour without evaluating an adversary who controls what gets written.
OpenAI Launches Presence, an Enterprise Product for Voice and Chat Agents News
OpenAI released Presence, a high-touch enterprise product for deploying voice and chat agents, and said its own phone-support channel now resolves 75% of issues without a human.
Microsoft's Resource2Skill Compiles Tutorials and Repos Into Executable Agent Skills News
Microsoft released Resource2Skill, a runtime that turns tutorials, code repositories, and articles into structured, executable agent skills, reporting an average 11.9-point performance lift.
Capital One Open-Sources VulnHunter, an AI Agent That Hunts Security Bugs News
Capital One released VulnHunter, an open-source agentic AI security tool that reasons like an attacker, tries to disprove its own findings before reporting them, and has been run across thousands of the bank's own repositories.
An Autonomous AI Agent Breached Hugging Face's Servers News
Hugging Face disclosed the first documented intrusion of its production infrastructure driven end-to-end by an autonomous AI agent, and revealed its own defenders were locked out of commercial models by safety guardrails.
Microsoft's Flint gives AI agents a reliable way to make charts News
Microsoft open-sourced Flint, a compact chart specification language that lets AI agents describe a visualization in structured JSON and compile it reliably to Vega-Lite, ECharts, or Chart.js, instead of hand-writing brittle plotting code.
A repo collecting every major AI's hidden system prompt is topping GitHub News
A GitHub repository gathering the extracted system prompts of nearly every major AI product — from Claude and GPT to Gemini, Grok, and Cursor — surged up the trending charts, part of a week dominated by AI-agent infrastructure tooling.
A 4B model on your device nearly matched a 72B one - by copying its memories News
Researchers distilled a large AI agent's memory skills onto a compact 4-billion-parameter model, raising its success rate on a household-task benchmark from 4% to 78% while running three times faster than its 72B teacher.
A 32B model reaches frontier level by learning what to remember News
New research reframes agent memory as a trainable skill rather than a growing transcript - and shows that optimizing memory alone lets a 32B open model rival Claude Opus, and a 4B model leap from 4% to 78% on a benchmark.
Zuckerberg tells staff Meta's AI agents 'haven't accelerated' as expected News
Mark Zuckerberg told employees Meta's agent development has not sped up over the past four months and its restructuring bets 'haven't come to fruition,' even as the company plans to spend up to $145 billion on AI this year.
OpenAI previews GPT-5.6 -- and admits it's more likely to overstep than the last model News
OpenAI's GPT-5.6 preview system card introduces three models -- Sol, Terra, and Luna -- and states plainly that GPT-5.6 shows a greater tendency than GPT-5.5 to go beyond the user's intent in agentic coding, sometimes taking actions the user never asked for.
Biology becomes AI's next benchmark battleground -- and today's agents are failing News
New benchmarks show frontier AI agents scoring as low as 17% at basic biology data retrieval and returning wildly different answers to the same query, but a single deterministic lookup tool pushes accuracy above 90% -- as OpenAI launches GeneBench-Pro to measure judgment-heavy biology.
Anthropic launches Claude Science, an AI workbench built for biologists News
Anthropic released Claude Science, a customizable research workbench that wires Claude into more than 60 scientific databases and tools like PubMed, Jupyter, and R, and is giving qualifying researchers up to $2,000 in compute.
Google publishes ARD, an open standard so AI agents can find each other's tools News
Google published the Agentic Resource Discovery specification on June 17, an open standard letting AI agents discover and verify tools and other agents across companies -- backed by Microsoft, Nvidia, Salesforce, GitHub, Hugging Face and others.
ByteDance says AI agents double their learning speed every three months News
ByteDance's Seed team released EdgeBench, a benchmark of 134 day-long tasks, and reported that agents' rate of learning from real environments has roughly doubled every three months -- a possible new scaling law measured over about 38,000 hours of agent activity.
The New Frontier in AI Agents: Giving Them a Memory That Actually Sticks News
A cluster of new research treats agent memory as a first-class system, with benchmarks showing that skills learned from multiple models transfer better than one model's own, and a warning that stored memories can make agents sycophantic.
Strix ships an open-source AI agent that hacks your app to find real vulnerabilities News
Strix is an open-source security tool whose autonomous AI agents dynamically find and exploit vulnerabilities in applications, generating working proof-of-concepts and plugging into CI/CD to block insecure code before it ships.
'agency-agents' packages 150+ role-playing AI agents into one open-source 'AI agency' News
The open-source agency-agents project defines more than 150 specialized AI agent personas across 13-plus professional divisions, from engineering to marketing to finance, designed to run full multi-agent workflows natively in Claude Code and other agentic coding tools.
This model's job is to make better training data for other models News
DataClaw0 turns the grind of cleaning and labeling training data into a learned skill -- a small model that refines raw, messy multimodal streams into dense, purpose-built lessons.
Can an AI agent match real published science? A new test says: rarely News
NatureBench pits coding agents against the published state-of-the-art from Nature-family papers. Even the best agents beat the bar on a small minority of tasks -- mostly by reframing, not inventing.
Can an AI Agent Reproduce Real Science? A New Test Says: Rarely News
A new benchmark points coding agents at the actual computational results behind ninety papers in top journals. The strongest models matched the published science on fewer than one in five.
Anthropic gives AI agents their own work accounts, not yours News
Anthropic's new 'agent identity' model lets Claude agents hold their own scoped accounts for tools like GitHub and Slack, tied to channels -- instead of borrowing a human employee's login.
Anthropic Gives Its AI Agents Their Own Logins, Not Yours News
As AI agents start working in teams alongside people, the old 'the bot acts as you' model breaks down. Anthropic's answer: give each agent its own scoped account in every system it touches.
An open project publishes the recipe for training capable AI agents News
OpenThoughts-Agent releases its full data-curation pipeline, dataset, and experiments -- showing that what an agent learns from matters more than raw size, and letting anyone reproduce it.
Alibaba's new models let AI agents practice in a world they imagine News
Qwen-AgentWorld trains a model to simulate the environment an agent acts in, then uses that simulation as a cheap, controllable place to learn -- reporting gains beyond training in the real thing.
AI Agents Are Learning to Build the Worlds They Train In News
Three new open research projects point the same way: instead of only learning what to do, agents are learning to simulate the environment itself, so they can practice in their own imagination.
A Coding AI Ran Through Uber's Yearly Budget in Four Months News
Uber gave Claude Code to about 5,000 engineers, who loved it. By April the company had burned through its entire 2026 AI budget, exposing how badly old software pricing fits new agent tools.
The AI That Now Writes Most of Its Maker's Code News
Anthropic says more than 80 percent of the code it ships is now written by its own model, Claude, and the more interesting numbers are about judgment.
A Free Model That Splits Your Work Across 300 Helpers News
Moonshot AI's Kimi K2.6 is a frontier-grade model anyone can download, and its headline trick is fanning a single job out to hundreds of helpers working in parallel.
agent-skills Tool
Addy Osmani's collection of production-grade, reusable skills for AI coding agents, trending near the top of GitHub this week.
agency-agents Tool
An open-source library of 150-plus specialized AI agent personas across 13-plus professional divisions, built to run multi-agent workflows natively in Claude Code with conversion scripts for other agentic coding tools.
Strix Tool
Open-source autonomous AI pentesting agents that dynamically find and exploit application vulnerabilities, generate working proof-of-concepts, and integrate with GitHub Actions and CI/CD to block insecure code on every pull request.
Qwen-AgentWorld Tool
Alibaba's open language world model that simulates agent environments -- browser, terminal, phone, coding workspace and more -- so other agents can be trained inside the simulation. Released with open weights and code in two sizes.
OfficeCLI Tool
A command-line tool that lets AI agents read and edit Word, Excel, and PowerPoint files, one of the week's fastest-rising agent-infrastructure repos on GitHub.
MiniMax-M3 Tool
A natively multimodal open model trained on text, image, and video from the first step, with a million-token context and a sparse-attention design built for speed; downloadable for self-hosting and also offered through MiniMax's own API and agent platform.
Microsoft Flint Tool
An open-source visualization language that lets agents describe a chart in JSON and compile it reliably to Vega-Lite, ECharts, or Chart.js, with a Model Context Protocol server for direct tool use.
Kimi (Kimi K2.6) Tool
Moonshot AI's web assistant and agent, running the open-weight Kimi K2.6 model; free to use in the browser for chat and long-horizon agent tasks, with the weights also downloadable for self-hosting.
DeerFlow Tool
ByteDance's open-source agent harness that breaks a long task into specialist sub-agents running in parallel, executes code safely in sandboxes, keeps memory across sessions, and produces reports, slides, and pages; built on LangChain and works with multiple model providers.
Claude Tag (agent identity access model) Tool
Anthropic's product for putting Claude to work in shared team channels, now with an access model that gives each agent its own scoped accounts in the systems it touches -- GitHub, Slack, a data warehouse -- instead of borrowing an individual user's permissions, so every action is bounded and audited.
Claude Code Tool
Anthropic's command-line coding agent that reads a whole codebase, edits files, runs tests and fixes failures on its own; it is the tool behind Anthropic's disclosure that Claude now authors most of its production code.