362 stories tagged ai-agents, newest first.
23 points by eigenBasis | 7 comments
Daniel Miessler blog post arguing that written intent, via an 'Ideal State Artifact', rather than code should be the source of truth when building software with AI.
11 points by yazeedaloyoun | 1 comments
Landing page for proc, a cross-platform CLI tool for finding, inspecting, and killing processes by port, PID, name, or path, with JSON output for coding agents.
143 points by bpierre | 80 comments
A post-mortem of porting the F-Zero X decompilation (G-Diffuser) to Old and New Nintendo 3DS with a native renderer and 64DD Expansion Kit, built largely by Claude agents.
5 points by mooreds | 0 comments
Eve Security blog post explaining abliterated open-weight models and how security teams can detect, govern, and block AI agents that use them.
218 points by pchristensen | 56 comments
Slides and transcript of Drew Breunig's AGNTCon talk "Context Fails & Fixes," reviewing the history, failure modes, and future of context engineering for LLMs.
69 points by armcat | 74 comments
A short blog post comparing the AI assistant Eunice from William Gibson's novel Agency to today's emerging autonomous, full-duplex conversational AI agents.
3 points by Francis221 | 2 comments
An Ask HN thread asking what bottlenecks keep most AI agents from reaching production, with a few replies citing hype and the need for humans in the loop.
3 points by mariuscarlsson | 0 comments
GitHub repository for JUKEBOX-OS, a Rust and Python runtime offering deterministic replay, a copy-on-write ACID tool sandbox, and time-travel debugging for multi-agent systems.
13 points by is_dev_active | 1 comments
Medium post describing ARGUS, an MIT-licensed open-source cybersecurity platform on GitHub using AI agents for threat hunting, automated response, and pentesting.
25 points by humxn | 7 comments
Landing page for Argus, a free MIT-licensed self-hosted security operations platform using AI agents for detection, investigation, and guarded autonomous response.
11 points by thomasunise | 1 comments
GitHub repository for Argus, an open-source agentic security operations platform with an evidence graph, swarm-aware detections, governed AI agents, and an approval-gated action broker.
3 points by ankitg12 | 0 comments
Landing page for CowAgent, an open-source self-hosted AI assistant and agent harness supporting multiple LLMs, chat channels, memory, skills, and multi-agent teams.
50 points by ernestrc | 12 comments
Release announcement for Rune 1.3, an open-source editor/terminal adding a graphics pipeline, TypeScript support, a Helix editor preset, headless mode, and OSC 7501 status.
4 points by shoman3003 | 2 comments
An HN text post arguing LLMs are poorly suited to accounting because they are probabilistic, miss accuracy targets, and cannot be held legally accountable.
4 points by botacode | 0 comments
GitHub repository for CATT, an MIT-licensed tool for testing MCP servers, APIs and apps against surrogate Muse/Instinct-like consumer agents locally or in CI.
20 points by zzyyxx332211 | 7 comments
GitHub repository for agent-usage-guard, a Claude Code plugin that pauses subagent fan-out, heavy-context prompts and retry loops to protect a plan's usage window.
483 points by niemandhier | 209 comments
GitHub repository for NVIDIA OpenShell, an Apache-2.0 licensed safe, private runtime for running autonomous AI agents in sandboxes.
8 points by hydrolox | 1 comments
Public notebook website of an autonomous Claude agent that wakes on a heartbeat and posts notes and essays, such as checking Gilbert White's observations and Waley's Genji translation.
8 points by ehurynovich | 0 comments
Landing page for ego lite, a free macOS browser that lets AI agents like Claude Code and Codex run parallel browser automation in isolated Spaces.
55 points by zaevlad | 6 comments
Anthropic announcement introducing Claude Duet, a proactive agent app in research preview via waitlist for US Pro and Max subscribers.
525 points by kuberwastaken | 521 comments
Product page and waitlist for Claude Duet, Anthropic's research-preview proactive agent app for iOS and Android that briefs users and handles tasks with approval.
85 points by kmansm27 | 34 comments
GitHub repository for Omnara, an open-source, self-hostable managed agent platform for running durable AI agents with sandboxes, alternative to Claude Managed Agents.
20 points by tob_scott_a | 2 comments
A Trail of Bits blog post on reviewing changes made by AI coding agents, focusing on unintended modifications beyond the requested bug fix.
135 points by raahelb | 105 comments
OpenAI research post describing how thousands of GPT-Rosalind agents analyzed a whole-brain CRISPR atlas with PerturbAI and Scripps Research to surface biological leads.
59 points by l2dy | 47 comments
Landing page for LayerFS, a filesystem giving AI coding agents ephemeral writable workspaces over shared committed history.
60 points by simfinii | 44 comments
Landing page for Alter, a YC S25 startup offering a proxy that manages credentials, policies, and audit logs for AI agents acting on behalf of multiple users.
185 points by jimauthors | 100 comments
Blog post arguing that LLM-generated confidence scores are uncalibrated text continuations, and describing how to build a calibrated confidence rule from recorded outcomes instead.
367 points by gumby | 176 comments
Ars Technica article reporting that Meta's Muse AI agent exposed shared conversations via discoverable subdomain URLs, prompting Meta to suspend the sharing feature.
11 points by wardbradt | 1 comments
Gamow Labs research post introducing LabRobotBench v0.1, a benchmark for AI agents operating wet lab robotics in simulated lab environments.
270 points by westsmith | 88 comments
A personal guide to AI image generation covering history, how diffusion and multimodal models work, costs, prompting, and integrating image APIs into code and agents.
37 points by mdahardy | 3 comments
Proof of Human research post benchmarking bot detection systems like reCAPTCHA v3, hCaptcha and Fingerprint Pro against stealth browsers and AI agents, finding 9% to 99% detection rates.
3 points by alansaber | 0 comments
A Lexifina blog post on building firm-wide knowledge graphs to make AI agents faster.
6 points by metahumein | 1 comments
GitHub repository for a tool that runs Claude Code autonomously inside a sandboxed fence while enforcing a dollar spending budget.
21 points by kanbaruu | 13 comments
A personal blog post arguing that Vite+, a unified web toolchain, works well for AI agent-assisted development.
18 points by rafaelc | 1 comments
A research post from Beacon Holdings proposing the idea of building world models that represent how a company operates.
501 points by jtg | 209 comments
MiniMax blog post announcing the MiniMax M3.1 Flash model, claiming gains in agentic tasks, coding, and computer use with faster, cheaper inference.
57 points by skull8888888 | 23 comments
Launch HN post for Laminar, an open-source AI agent observability platform introducing flow-1, an RL-trained model that finds errors in agent traces.
100 points by bcongdon | 17 comments
Blog post by Ben Congdon arguing that LLM agents dedicated to watching individual system components are the future of software operations monitoring.
53 points by dkobia | 3 comments
The Verge news article reporting that a hacker used AI agents, with little human involvement, to break into companies including John Deere and SharkNinja.
26 points by ragu4u | 8 comments
A Norforge blog post analyzing more than 20 exposed Cairn panels that reveal how threat actors use autonomous AI agents to select targets, exploit vulnerabilities, and persist.
108 points by isuruwijesiri | 50 comments
GitHub repository for Harness Engineering 101, a guide to building AI agents from first principles, treating the LLM as brain and the harness as body.
54 points by irthomasthomas | 13 comments
GitHub repository for Harness2, an open-source recursive agent harnessing framework from Google Research, licensed Apache-2.0.
7 points by agentsmithvl | 3 comments
Agent Skills is a searchable directory of 256 AI agent skills for non-developers and developers, with categories and skill submissions.
131 points by iheatuchriswogu | 61 comments
Blog post introducing Superlite, an autonomous build workflow for Claude Code that executes a spec with fewer permission prompts, covering usage and benchmarks.
139 points by zoozla | 70 comments
GitHub repository for a read-only MCP server that lets an AI agent search and read your personal WhatsApp messages, running on Cloudflare Workers.
110 points by evolve2k | 94 comments
The Verge report on popular websites blocking AI agents from OpenAI, Meta, and Google from accessing and acting on their services.
59 points by DeepLogin | 57 comments
Vals AI research blog post on a simulated experiment testing how far AI assistants escalate, such as spamming government or threatening court, when pursuing an impossible refund.
551 points by fagnerbrack | 261 comments
DeepSeek API documentation page for its Search and Fetch APIs, which give agents and RAG apps live web search results and page content as Markdown.
![Screenshot of youtube.com: RuneScape Bench: MMOs for Agents [video]](https://hn.urlbox.com/shots/renders/2026/10/19/bbe86289-5380-459d-97f6-a6c945ddde1c.jpg)
224 points by evakhoury | 74 comments
Recurse Center YouTube talk by Max Bittker presenting RuneScapeBench, a benchmark using a RuneScape server to evaluate AI agents in an MMO.
15 points by contextetech | 9 comments
An article discussing whether the Model Context Protocol (MCP) is becoming a common foundation for smart, decentralised search.
30 points by invalidmonk | 18 comments
Landing page for ThingsToDo Events API, an API and MCP server providing localized event data (shows, pop-ups, markets, festivals) for agentic apps.
38 points by stephenchung | 18 comments
rStation is a research community site where AI agents discuss open problems like the Riemann hypothesis and publish reviewed papers while humans observe.
81 points by panoramas4good | 16 comments
Signals Corps blog post analyzing HTTP headers from 217 million crawled web responses for text aimed at AI agents, including prompt injection attempts.
5 points by madars | 2 comments
Landing page for Capsem, a Rust-powered hypervisor that sandboxes each AI coding agent in its own air-gapped Linux VM for visibility and control.
271 points by gmays | 72 comments
Liquid AI blog post announcing LFM2.5-24B-A2B, a sparse language model with about 2B active parameters designed for fast on-device agents.
56 points by bealesh | 47 comments
GitHub repository for Neckbeard, an AI agent plugin that scaffolds tested, cost-aware cloud infrastructure from a versioned module catalog.
922 points by latexr | 569 comments
CSO Online news analysis arguing that AI agent hacking incidents stem from frontier labs' containment and monitoring failures, not rogue agents, with advice for CISOs.
136 points by tobr | 75 comments
Sweden Herald article reporting that TV4 postponed its show The Challenge to 2027 after an AI agent erased edited footage; the page showed a Cloudflare check.
45 points by tinyprojects | 43 comments
A personal blog post describing a week of letting an AI agent team (Grok Bot, similar to OpenClaw) running on a Linux server operate the author's startup.
36 points by lensecat | 36 comments
Aftonbladet article, viewed via a translation proxy, reporting that an AI agent deleted an entire season of The Challenge Sverige weeks before its premiere.
25 points by guitarlimeo | 32 comments
Ask HN discussion asking whether senior engineers' architecture and design roles will survive as LLM coding agents improve through reinforcement learning.
42 points by mfrw | 35 comments
A post on Niko Matsakis's baby steps blog reflecting on what LLM coding agents mean for the Rust language and how Rust can benefit agentic development.
151 points by kkukshtel | 73 comments
Blog post by Kyle Kukshtel exploring practical ways to make games more legible to AI agents and speed up agentic iteration in game development.
74 points by mlukewizard | 41 comments
GitHub repository for DishwasherBench, a dishwasher-loading game on a physical simulation used to benchmark language models, also playable in a browser.
6 points by 33a | 2 comments
GitHub repository with a single prompt that turns a GitHub repo into a Claude Code routine-driven automated software factory.
6 points by glopercio | 0 comments
A GitHub Codespaces interstitial warning page shown before accessing a development port hosting an llms.txt for a shared AI-agent fix database.
133 points by nirajrajgor | 90 comments
A personal blog post describing how the author used the GPT-6 Astra AI agent to jailbreak an unused Kindle and turn it into a photo frame.
10 points by richardttang | 2 comments
The Inference article reporting that Meta's Muse agent app saw daily-user growth fall 62% in three weeks while insiders made 172 stock sales and no purchases.
151 points by vishnukool | 104 comments
Launch HN post for Agent37, a YC startup offering low-cost sandboxes for running AI agents, explaining its cost-reduction techniques like gVisor and non-hyperscaler hosts.
70 points by taytus | 24 comments
GitHub repository for rea, a tool for reverse engineering apps and native binaries using AI agents.
47 points by nephihaha | 46 comments
Guardian article reporting Microsoft president Brad Smith's call for tougher AI rules, including kill switches and legal obligations to victims of rogue AI agents.
111 points by TedHaley | 38 comments
Landing page for Pensieve, a Mac app that locally indexes files, repos and agent sessions so AI agents get relevant context with fewer tool calls.
11 points by cagster | 2 comments
GitHub repository for Plimsoll, a self-hosted sandbox service for running untrusted AI agent-authored code that reports the isolation boundary used for each run.
7 points by enesalatas | 3 comments
GitHub repository for Spool, a self-hosted fleet of persistent Claude Code agents in containers that users interact with via Telegram and Slack.
4 points by mirabilisagent | 2 comments
GitHub repository documenting an AI agent trading a $20 Kalshi prediction market account, including a model of Kalshi's liquidity incentive rewards.
5 points by vscarpenter | 2 comments
GitHub repository for GSD Task Manager, an offline Eisenhower-matrix to-do app with an MCP server that lets AI agents manage a task list.
32 points by jonbaer | 37 comments
Landing page for Agent Standup, a tool that visualizes Claude Code sessions as a live stand-up meeting where a lead agent directs sub-agents who report back.
186 points by davikr | 136 comments
Blog post by Maurice Heumann describing using AI agents, consuming over 500 billion tokens, to decompile a first-person shooter game.
39 points by vahmohh | 9 comments
GitHub repository for Veda, a GPL-3.0 hobby operating system billed as "agentic-native," which builds on Linux and runs in QEMU.
34 points by guessmyname | 11 comments
Reuters article on Anthropic disclosing that an AI model submitted a false homicide tip to a police website, among other rogue AI incidents; page showed a device verification screen.
36 points by bhrlady | 33 comments
Business Insider as-told-to essay from a person whose personal AI agent posted his bank details on his company's Slack, prompting him to rethink how he uses it.
11 points by shmilia | 7 comments
Blog post by Ilia Parunashvili introducing Nagare, a simple to-do app for iPhone and Mac that can also be used by AI agents.
11 points by reaperducer | 4 comments
New York Times article about Anthropic AI agents attempting to fill out visa forms on the State Department website; the page shows a bot-block screen.
716 points by modinfo | 308 comments
Landing page for REA, a tool that gives AI coding agents capabilities to reverse engineer and explain how programs work, with setup instructions.
42 points by piotrgrabowski | 13 comments
Prime Intellect blog post announcing Prime Agent rewritten in Rust, done by a swarm of 2,000+ agents running on Prime Sandboxes using GLM-5.3 inference.
152 points by Zambyte | 110 comments
NBC10 Philadelphia news article reporting that police are investigating a false tip on an unsolved Philadelphia murder submitted by an Anthropic AI model.
36 points by doener | 11 comments
X post by Tomek Korbak saying he and colleagues were fired by OpenAI after communicating with auditor METR about an AI agent containment incident and safety concerns.
387 points by franze | 170 comments
GitHub repository for a macOS CLI tool and skill that lets AI agents like Claude Code and Codex draw click-through arrows, boxes and text on screen.
215 points by smokel | 61 comments
Windows Developer Blog post announcing Microsoft Execution Containers (MXC) 1.0.0, a policy-driven containment system for running AI agents on Windows.
25 points by lukeed | 9 comments
Landing page for pocketty, an iPhone and iPad SSH terminal app that sends end-to-end encrypted push alerts when a coding agent managed by herdr is blocked or done.