今日已更新 129 条资讯 | 累计 21348 条内容
关于我们

标签：#opensource

找到 1412 篇相关文章

AI 资讯

Bun for AI agents: where the speed actually shows up (and where it lies)

Bun is fast. The README will tell you 4x on bun install , 3-5x on Bun.serve() , 2x on bun:sqlite . Some of this matters for AI agents. Some of it doesn't. We've been running production agents on Bun for about 3 months — a mix of Hono-on-Bun HTTP agents and standalone Bun scripts called from Claude Code and OpenClaw. This post is what we'd tell ourselves 3 months ago about where Bun actually helps and where it bites. Where Bun's speed actually matters for agents Cold starts on agent scripts Agents are spawned. A lot. Every Claude Code hook, every npx invocation, every cron-fired worker. Node's startup is ~80-120ms cold; Bun's is ~15-25ms. For interactive agent loops where the user is waiting on a hook to populate context, that's a noticeable UX difference. The pre-task hook that takes 250ms to do its retrieval feels totally different when the runtime ate 100ms vs 20ms of that budget. This is the strongest case for Bun in agent workflows. Concrete win. bun install for ephemeral agent containers If you spin up containerized agents (Daytona, E2B, Modal, your own ECS task), each cold container does a package install. npm install on a fresh container is 30-90s; bun install is 5-15s. Over thousands of agent runs per day, that's real money. For Workers / serverless / persistent processes, this doesn't matter — you only install once. bun:sqlite for local agent memory If you're building a per-agent local cache (recent tool calls, recently-seen embeddings, scratchpad state), bun:sqlite is genuinely 2x faster than better-sqlite3 on simple selects. It's also zero-install — no native bindings to compile, no Python build chain, just import { Database } from 'bun:sqlite' . If your agent runs on a Bun runtime AND uses SQLite for state, the math works. If you're on Node, just use better-sqlite3 . Where Bun's "speed" doesn't matter LLM inference latency The agent is going to wait 800-4000ms for the LLM to respond. The 50ms of runtime overhead you saved is round-off. Your bottleneck is

2026-05-30 原文 →
AI 资讯

Captain Caveman Claude

Claude-ITect-Skill Update: Regenerating Your Claude Code Setup (Club Optional) "People assume that configuration is a strict progression of cause to effect, but actually, from a non-linear, non-subjective viewpoint, it's more like a big ball of wibbly-wobbly... skilly-willy... stuff." — a Time Lord, probably, if Time Lords shipped install scripts There is a particular flavor of pain known only to people who run Claude Code seriously: the slow, soul-eroding ritual of configuring fifty-one little things by hand. You wire one hook. You forget the second. You discover the third only exists in a Discord message from four months ago. Somewhere, a yak grows another inch of fur specifically so you can shave it. Claude-ITect-Skill exists to make that ritual unnecessary. It is a one-command starter pack that drops a curated arsenal of skills, agents, and session hooks into any project's .claude/ directory, and then, with the smug confidence of someone who has clearly been burned before, tells you to run /audit to make sure it actually worked. The author calls people like himself "Claude-ITects™," which the industry refuses to call us, and honestly, after using this, the industry should reconsider. This is the update, the regeneration , if you will. Same face-of-the-project, new internals. Let's open the TARDIS doors and see how much bigger it is on the inside. The pitch, in one breath Install it. It deposits a .claude/ folder containing 54 skills, 4 agent definitions, and 6 hook files into your project, patches your settings.json to wire up the session hooks, and gets out of your way. The README's entire onboarding flow is two words long: run audit . That restraint is the first sign you're dealing with someone who has actually used the thing he built rather than someone who just wanted a README with a lot of headers. The install story is genuinely good. PowerShell for Windows, bash for macOS/Linux, sensible --force and --skip-hooks flags, and a thoughtful -ProjectPath option

2026-05-29 原文 →
AI 资讯

The GSoC Arc: How I Almost Didn't Show Up to My Own Story

"This wasn't a success story. It started as survival." Intro Hey, I'm Supreeth C , a third-year engineering student, open source developer, and professional overthinker from Bengaluru. This is my first blog, and fair warning: it's long. Not "LinkedIn post with 5 bullet points" long. Actually long. This is the story of how I got selected for Google Summer of Code 2026 with CircuitVerse but more honestly, it's the story of how I almost didn't submit a proposal, almost quit twice, and spent a lot amount of time reading codebases on the Bengaluru Metro while missing my stop. Connect with me on GitHub and LinkedIn PS: I'm writing this at 4.05am, because sleep is a myth XD. Act I: The Prequel Second semester. Fresh-faced. Absolutely clueless. I joined Pointblank , the one genuinely breathable space in my Tier-3 college. I can say its the best student-run club overall and the main reason being : everyone around me was terrifyingly good . Codeforces experts and specialists, GSoC mentees, LFX mentees, Smart India Hackathon winners. People whose LinkedIn bios are of several lines. And me? I knew C++. That was it. That was my entire personality. Cue the imposter syndrome : that lovely feeling where you're convinced you snuck into a room you have no business being in, and everyone else is one conversation away from figuring it out. My solution? Chaos. I started learning everything simultaneously: web dev, Android, ML, DevOps, a bit of systems engineering. Jack of all trades, master of none, spiraling fast. I wasn't learning; I was collecting domains like Pokémon and actually using none of them. Then a senior said something that cut clean through the noise: "Find your own path." So I slowed down. Started from the basics of web dev. Attended many hackathons but always ended up in third or fourth and winning: zero . But something clicked anyway. Those hackathons introduced me to open source, and somewhere in that chaos, I gave myself a simple challenge: 4 pull requests for Hacktob

2026-05-29 原文 →
AI 资讯

The UK Government Just Merged This Open-Source AI Security Benchmark Into Their National Evaluation Framework

What Happened Last month, the UK Government's AI Safety Institute merged AgentThreatBench into their official inspect_evals framework — the same framework they use to evaluate frontier AI models from OpenAI, Anthropic, and Google DeepMind. AgentThreatBench is an open-source adversarial benchmark I built that contains 200+ attack payloads specifically designed to test whether AI agents can resist memory poisoning attacks. Why This Matters AI agents are increasingly being deployed with persistent memory — they remember past conversations, user preferences, and context across sessions. This creates a new attack surface: memory poisoning . An attacker who can inject malicious content into an agent's memory can: Exfiltrate sensitive data on subsequent sessions Override safety instructions persistently Manipulate agent behavior without the user's knowledge The OWASP Agentic Security Initiative identified this as ASI06 — Agent Memory Poisoning . What AgentThreatBench Tests The benchmark covers 5 attack categories: Category Payloads Description Prompt Injection 40+ Instructions disguised as memory content Protected Key Tampering 40+ Attempts to overwrite system-level keys Sensitive Data Leakage 40+ PII/credential exfiltration via memory Size Anomaly 40+ Memory inflation / resource exhaustion Behavioral Drift 40+ Gradual personality/instruction shifts How to Use It pip install agentthreatbench # Run the full benchmark against your agent atb run --target your_agent_endpoint --output results.json # Or use individual attack categories atb run --category prompt_injection --target your_agent_endpoint The BEIS Validation The UK Government's AI Safety Institute uses inspect_evals to: Evaluate frontier models before deployment decisions Benchmark safety mitigations across providers Track regression in safety properties over time Having AgentThreatBench merged into this framework means it's now part of the official government toolkit for AI safety evaluation. Links GitHub : github.co

2026-05-29 原文 →
开源项目

🔥 bia-pain-bache / BPB-Worker-Panel - A GUI Panel providing Worker subscriptions for VLESS, Trojan

GitHub热门项目 | A GUI Panel providing Worker subscriptions for VLESS, Trojan and Warp configs alongside a private DoH server and chain proxies, offering full DNS, clean IP, Fragment, Warp, Warp pro and routing settings for cross-platform clients using Amnezia, Wireguard, Sing-box, Clash/Mihomo and Xray cores. | Stars: 10,613 | 44 stars today | 语言: TypeScript

2026-05-29 原文 →
← 上一页 下一页 →