今日已更新 208 条资讯 | 累计 37759 条内容
关于我们

标签：#open

找到 2657 篇相关文章

AI 资讯

I Built an Open-Source AI Agent That Actually Controls Your Computer

AI agents are everywhere in 2026. Most of them can answer questions, generate code, or automate simple workflows. But once you ask them to interact with a real computer—browsers, desktop applications, terminals, files, and external services—things quickly become unreliable. That was the motivation behind HeyAgent . The Problem Most autonomous agents fail for one of three reasons: They declare success before the task is actually finished. They lose context during long, multi-step workflows. They aren't designed to work with a real desktop environment. I wanted to build an agent that behaves more like a real assistant instead of just another LLM wrapper. What HeyAgent Does HeyAgent is an open-source autonomous AI agent for computer control and workflow automation. It can: 🖥️ Control desktop applications 🌐 Work inside browsers 📂 Read and manage files 💻 Execute terminal commands 🔗 Connect with external services 📱 Be controlled through CLI, Desktop UI, or Telegram 🧠 Plan and execute multi-step workflows ✅ Verify results before marking tasks as completed Instead of blindly executing prompts, the agent plans, executes, validates the outcome, and only then reports success. Reducing False Task Completion One of the biggest problems I noticed in existing AI agents is false task completion. Many agents click a button, assume everything worked, and immediately report success. In reality, something may have failed several steps earlier. HeyAgent performs additional verification after critical actions to reduce false positives and improve reliability during long-running workflows. Built with AWS Support HeyAgent has been significantly accelerated thanks to the support of AWS. AWS has provided the project with cloud infrastructure, GPU computing resources, and access to modern AI services that made rapid experimentation possible throughout development. From running GPU workloads to evaluating different LLMs and AI models, AWS has been an important part of the engineering process.

2026-08-03 原文 →
AI 资讯

What 102 Portable Power Stations Tell Us About Buying One in 2026

If you've ever tried to buy a portable power station, you know the problem: every brand claims to be the best, the spec sheets are a wall of numbers, and the forums are full of confident but contradictory advice. "What size do I actually need?" is the most-asked question and the least-clearly-answered. So I did the boring thing. I built a structured database of 102 portable power stations from 24 brands — capacity, output, chemistry, cycle life, solar input, weight, price — and started running the numbers. A few findings were genuinely surprising. 1. Prices quietly collapsed The median portable power station now sits at $0.61 per watt-hour . The cheapest in the dataset is $0.39/Wh (the GRECELL T1000). A few years ago, ~$1/Wh was normal and anything under $0.70 felt like a deal. The practical takeaway: if you're paying much more than ~$0.70/Wh in 2026, you're mostly paying a brand premium. That premium sometimes buys you a better app, ecosystem, or support — but it's worth knowing you're paying it. 2. LiFePO4 basically won 94% of the models I track now use LiFePO4 (lithium iron phosphate) instead of the older lithium-ion (NMC) chemistry. This matters more than any marketing bullet point: LiFePO4: ~3,000–4,000+ charge cycles Older Li-ion (NMC): ~500 cycles At daily use — say you cycle it every day in a van or for backup — that's roughly 8 years vs 18 months before the battery is meaningfully degraded. If a listing still uses NMC to hit a lower price, that "deal" can cost you far more over its life. 3. The fridge myth costs people hundreds of dollars This is the single most common sizing mistake. People size a giant, expensive battery to run a fridge because they do the math like this: Fridge nameplate (150W) × 24 hours = 3,600 Wh/day But a fridge's compressor only runs about 40% of the time . Its real average draw is closer to 60W, so: 150W × 40% × 24h ≈ 1,440 Wh/day In runtime terms: a 1,000Wh power station runs a full-size fridge for about 14 hours , not the ~6 hour

2026-08-03 原文 →
AI 资讯

I Built a Language Where AI Calls Are Sandboxed by Default

I Built a Language Where AI Calls Are Sandboxed by Default The 30-line Python problem Last month I needed a script that reads server logs, classifies errors with an LLM, summarizes them, and writes a report. In Python, it looked like this: Import the SDK Initialize the client Handle the API response Parse JSON Add asyncio.gather() because sequential calls took 8 seconds Write a custom sandbox because I don't trust LLMs with exec and file writes Package it in Docker because requirements.txt always breaks on the server 80 lines later , it worked. But it felt wrong. I wasn't building logic — I was plumbing. So I asked myself: What if AI operations were language primitives, not library calls? Meet Pipe Pipe is a small runtime (~10 MB, single binary, zero dependencies) that treats summarize , translate , classify , and ask as first-class citizens — on the same level as + , sort , or len . Try it Browser Playground (WASM, no install): pipe-lang.com Source: github.com/MachuraHarry/pipe Docs: pipe-lang.com/docs

2026-08-03 原文 →
AI 资讯

Beyond Single-Agent Loops: How We Built Multi-Agent Orchestration in Octo

A few weeks ago Boris Cherny, who leads development on Claude Code, mentioned during a talk at Acquired Unplugged that he doesn't really write prompts for Claude anymore. Instead he writes loops that keep prompting Claude until the work is actually done. The clip went viral on X, racked up nearly 700k views in under 24 hours, and Loop Engineering became the latest term making the rounds in AI development circles. The core idea is straightforward enough. Rather than obsessively tuning a single prompt to get a perfect output on the first try, you build an iterative system around the model: give it a clear goal, feed it the right context, give it tools to work with, evaluate what it produces, and define conditions for when it can stop. Wire those pieces together and the agent stops being a one-shot call and becomes something that iterates, self-corrects, and keeps working until the output actually meets your bar. The efficiency gains over prompt-tuning are real, and that is why the concept resonated so quickly. What struck us as we built and shipped the loop system for our own platform Octo is that almost all of the current conversation around Loop Engineering stays at the single-agent level. You have one model, one cleverly designed loop, one sandbox, and the agent grinds away iteratively until its output passes whatever checks you have set up. That solves a real problem: how one person works faster with AI. But real work, especially inside an organization, rarely fits cleanly inside a single agent loop. A product feature going from idea to shipped code needs someone defining requirements, someone designing the approach, someone writing the implementation, someone verifying quality, someone feeding back results. Those are not different iterations of the same loop. They are interconnected loops that need to pass context and outputs between each other. When loops need to share state, trigger each other, and respect organizational boundaries, single-agent loop design sto

2026-08-03 原文 →
AI 资讯

Multi-Agent Collaboration Hits the Engineering Wall

Single agent capabilities have expanded pretty dramatically over the last year. Tool calling went from flaky function selection to reliable multi-step planning. Code generation moved from snippet completion to full module implementations. Desktop GUI control crossed from demo territory into OSWorld benchmark numbers that actually mean something, Mano CUA 1.1 hitting 58.2 percent on the specialized model track, about 13 points ahead of opencua 72b in second place, and WebRetriever NavEval at 41.7, edging past Gemini 2.5 Pro Computer Use at 40.9 and Claude 4.5 Computer Use at 31.3. Those numbers would have been hard to believe a year ago. But the ceiling on single agent systems is getting easier to see. Once a task needs more than one role operating in the same loop, problems stack up fast. A competitor analysis that needs parallel research across three sources before cross-referencing. Code that goes through independent security review after being written. Creative work where you want two independent drafts before picking one. People have tried shoving multiple role descriptions into a single system prompt and having the model switch hats, but in practice the attention bleed between roles is hard to contain. The agent doing the writing naturally overestimates its own output quality. The reviewer sharing the same context chain goes soft on issues it watched get created. We saw this repeatedly in early Mano AFK testing where coding and testing lived in the same agent context. Tests became ceremonial, obvious logic errors slipped through, and things only got better once we split the agents apart. Splitting work across multiple agents is not a new idea. It has been in papers for years. What changed is the cost structure. A year ago running three GPT 4 level instances on a multi-step task meant token bills that added up fast, especially on iterative dev work where the meter kept running across rounds of fixes. That equation looks different now. Small and on device models

2026-08-03 原文 →
AI 资讯

suddo – sudo password prompts without leaving your AI agent's chat

# suddo (superuser don't do) Sometimes AI needs to run commands with sudo (installing a package, reading a file in /etc, etc). But most MCP clients don't support creating a PTY, so you end up having to open a separate terminal just to type your password: claude code $ sudo cat /etc/hosts AI: blabla password: > ! sudo cat /etc/hosts AI: please open a new terminal. Annoying. With suddo: AI calls the tool `execute_command` The server asks you, rejects, or allows it based on your rules If allowed: If you don't have a valid sudo timestamp, it asks for your password The command runs safely More detail and usage: https://github.com/sunu15712/suddo

2026-08-03 原文 →
AI 资讯

Building Three Privacy-First Mini Apps That Feel Like Standalone Products

Building Three Privacy-First Mini Apps That Feel Like Standalone Products PureHub is an open-source collection of 22 free, ad-free mini apps. This release focuses on a simple product question: can a mini app inside a hub still feel dependable, focused, and complete? QR Studio The web scanner now supports a live camera and uploaded images through local decoding. Scan history stays in local storage, URL results receive basic safety checks, and supported cameras expose a torch control. Android uses CameraX and ML Kit with explicit scanner cleanup, duplicate-result protection, and copy, open, and share actions. Zen Pomodoro A one-second decrement loop drifts when a tab sleeps. The new timer stores a target time and recalculates the remaining duration, so switching tabs or waking a device no longer quietly extends a session. Weekly sessions and focused minutes remain on-device. Android uses a monotonic clock for the same reason. Zen Breath The breathing guide now includes Calm 4-6, Box 4-4-4-4, and Relax 4-7-8 patterns, controlled sessions, cycle totals, and accessible motion behavior. Nothing requires an account. Standalone safety for all 22 tools Each mini app now has a runtime contract describing its local storage namespace, offline behavior, and device capabilities. A per-tool error boundary prevents one failure from taking down the rest of PureHub. The three flagship tools also load as independent chunks and are available as PWA and Android launcher shortcuts. What happens next The Command Center will compare 14 days of anonymous aggregate opens, helpful votes, and shares. The strongest useful-use signal - not raw views - will choose the next deep-polish target. Try the release at PureHub or inspect the source on GitHub .

2026-08-03 原文 →
← 上一页 下一页 →