标签：#cli

Most terminal coding agents are architecturally similar: a loop, a tool registry, some context management, a TUI. Reasonix picks a different thing to optimize for, and it is a thing that shows up on your bill rather than in a demo video. The tagline is "engineered around prefix-cache stability — leave it running." That phrase is doing a lot of work, so let's unpack it. Why prefix caching is the whole pitch DeepSeek's API, like several others, caches the prefix of your prompt. If the next request starts with the exact same token sequence as the previous one, the provider serves those tokens from cache and bills them at a small fraction of the normal input rate. Cache hits are dramatically cheaper than cache misses. Here is the catch: it is a prefix cache. The match has to start at token zero and run forward. Change one character near the top of your context and every token after it is a miss. Now think about what a typical agent harness does over a long session. It re-summarizes the conversation. It injects a fresh timestamp or a re-scanned directory tree at the top. It reorders tool definitions. It rewrites the system prompt when you switch modes. Every one of those is a mutation near the front of the context, and every one of them silently invalidates the entire cache. The result is an agent that feels fine and costs several times what it should. You do not notice, because nothing errors. You just watch the number go up. Reasonix's central design constraint is: don't do that. Keep the front of the context stable, append rather than mutate, and put churn where it costs least. What that looks like in practice A small, stable environment summary is injected at startup rather than regenerated each turn. Stale tool output gets snipped and pruned before summary compaction kicks in, so a giant cat result from twenty turns ago is not still sitting in your prefix. The built-in tool schema contract is documented and regression-reviewed, because a silent tool-definition reshu

I switch between Claude Code, Codex, and Gemini CLI depending on the day and the task. Each one is genuinely good. Each one also has zero idea what the other one knows. I'd explain a decision to Claude Code — "we're using Postgres here because we need concurrent writes, don't suggest SQLite again" — and it'd remember, because it reads CLAUDE.md . Then I'd switch to Codex for the same repo and it would suggest SQLite. Again. Because nothing I told Claude Code ever made it into whatever context Codex was reading. Multiply that by every "we tried X, it didn't work, don't suggest it again" conversation, and you start explaining the same three things to three different tools every week. That got old fast. What I actually built Mythicator is a CLI called mythicator . It does one thing: keeps a single memory file per repo, and pushes it out to whatever context file each AI tool already reads. mythicator init mythicator add "Chose Postgres over SQLite" --type decision --reason "needs concurrent writes from multiple workers" mythicator sync That sync command writes the same memory into CLAUDE.md , AGENTS.md , GEMINI.md , and .cursorrules — wrapped in a marker block so it never touches anything I've written by hand in those files. Update the memory once, every tool gets it. The canonical data lives in .agent-memory/memory.json , committed to the repo. It's not fancy — decisions, rejected approaches, bugs, conventions, notes, each with an optional reason and tags. No vector search, no embeddings, no hosted service. Just a JSON file and a sync step. Why not just use one of the existing memory frameworks There are already solid tools doing "memory for AI" — Mem0, Zep, that kind of thing. I looked at them before building this. They're aimed at developers building agents that need long-term memory at runtime, with similarity search over a big pile of facts. That's a different problem than mine. I didn't need semantic search. I needed "the four tools I personally switch between all

Climate nonprofits can again access their federal funding more than a year after the Trump EPA ordered Citibank to freeze their accounts.

Mitti Labs plans to expand beyond India and enter the Philippines and Indonesia while growing its carbon credits and agricultural data business.

The purchase illustrates just how interconnected Elon Musk's universe of companies are.

Learn how to build tools to simplify how you work—without writing a single line of code. The post How the GitHub legal team used Copilot CLI to streamline their workflows appeared first on The GitHub Blog .

"Because typing the same 15 commands every day is so 2026." A command-line utility that turns your chaotic terminal sessions into a beautiful, interactive menu. Stop memorizing commands. Start executing like a pro. 🚀 What Makes This Tool Special? Feature What It Does For You 🎯 Zero Memorization Never type kubectl get pods --all-namespaces --context=prod again ⚡ Lightning Fast One binary. No dependencies. Runs everywhere. 🔗 Command Chaining Execute complex workflows with --exec "1-2-3-4" 📁 Team-Ready Share menu.yml with your team. Onboard new devs in 30 seconds. 🔐 Env Variables Store secrets safely in env.ini — never hardcode credentials 📦 Installation (30 seconds or less) Option 1: One-Liner (if binary is hosted) curl -sSL https://example.com/hello | sudo tee /usr/local/bin/hello && sudo chmod +x /usr/local/bin/hello Option 2: Build from source git clone https://github.com/yourrepo/hello cd hello go build -o hello main.go ./hello --help Option 3: Copy & Go # Anywhere you want: cp hello ~/hello # Home folder cp hello /usr/local/bin/ # Global access (recommended) 🎮 Usage That Will Make You Smile Interactive Mode — The "I'm Feeling Lazy" Way # Just run it. The menu will greet you. ./hello # Using your own config ./hello -c ./deploy_menu.yml Headless Mode — The "I'm Automating Everything" Way # Execute a single command ./hello --exec "1" # Execute a whole pipeline (1 → 2 → 3 → 4) ./hello --exec "1-2-3-4" Perfect for: CI/CD pipelines, morning standup scripts, and impressing your boss. 📂 Example Menu (Your New Best Friend) items : 1 : title : " 1. 🚀 Deploy to Production" commands : - " git checkout main" - " git pull origin main" - " docker build -t myapp:latest ." - " docker push myapp:latest" - " kubectl rollout restart deployment/myapp" 2 : title : " 2. 📊 Check System Health" commands : - " htop" - " df -h" - " free -m" - " netstat -tulpn | grep LISTEN" 3 : title : " 3. 🔥 Clean Up Docker Garbage" commands : - " docker system prune -af --volumes" - " echo '✨ Saved 47 GB

Texas Governor Greg Abbott has paused new data center development until an audit has been completed.

The 0.5.4 release notes carried an unusual section: Known issue shipped with 0.5.4 . We had spent that whole release fixing the first minute of using the CLI — twelve corrections to help text, exit codes, path handling, and MCP behaviour — and in the middle of it we found one more that did not make the cut. mendapi scan -h did not print help. It ran a scan. Every other subcommand normalized -h to --help before dispatching. scan did not, so the short flag fell through to the scanner, which happily ignored an unrecognized argument and started working. Nobody loses data over this. But it is exactly the kind of thing that makes a first-time user close the terminal, and we had just shipped a release about first impressions. We wrote it down rather than quietly patching over it, because a tool whose entire premise is upstream changes should be visible before they surprise you does not get to hide its own. What 0.5.5 does One change. -h is normalized to --help before any subcommand spawns, so all nine subcommands behave identically: $ npx mendapi@0.5.5 scan -h Usage: mendapi scan --repo <path> --provider <name> --change-id <id> --out <file.json> --json --quiet --include-prereleases The regression gate that covers this now asserts on all nine subcommands, plus a negative control that fails if the assertion ever becomes vacuously true. That second part matters more than the fix: a test that passes because it stopped testing anything is worse than no test. Also in this release The MCP registry entry has been refreshed. com.mendapi/mendapi now carries an icon set and a website URL alongside the package metadata, so clients that render a server picker have something to render. Nothing else changed. scan , fix , deps , review , and pr still run entirely on your machine. No network primitives exist in those files at all, and the build fails if any appear. Install npx mendapi@latest scan Or wire it into an agent: claude mcp add mendapi \ -- npx mendapi mcp Requires Node.js 22.13 o

Valar Atomics raised $1 billion at a $6 billion valuation after signing a development deal with Nvidia in June.

Base Power’s $1 billion round will help the startup ramp production of its home batteries.

I built a zero-config CLI that deploys the current folder to a live site. Anonymous by default, with a single-use claim link if you want to keep it. Every static hosting tool I've used asks for the same ritual before you can see your site online: create an account, verify an email, install a CLI, log in, answer a config wizard. That's a lot of ceremony for "put these files on a URL". So I built hosting — a CLI where the entire flow is: npx hosting That's it. No account, no config, no login. Your folder is live: Uploading 3 files (12.4 KB)... Live site: https://1freehosting.com/s/happy-panda-482 Claim link: https://1freehosting.com/claim/xxxxxxxx-... The claim-link model The interesting part isn't the upload — it's the ownership model. Deploys are anonymous by default . You get two links back: Live site — the public URL, share it with anyone. Claim link — private and single-use. Open it, sign in, and the site attaches to your account so you can manage it from a dashboard. Unclaimed sites expire 24 hours after the last deploy. That keeps throwaway experiments truly throwaway — no zombie sites, no cleanup — while anything you actually care about is one click from permanent. This inverts the usual order: instead of authenticate, then deploy , you deploy, then decide if it was worth authenticating for . Updating the same site The first deploy writes a .hosting.json file with the site's deploy token. Every later hosting run from that folder updates the same site — before and after you claim it. vim index.html hosting # same URL, new content Some details I sweated: .hosting.json is added to your .gitignore automatically (it contains the token). Hidden files ( .env , .git , …) are skipped client-side , so secrets never leave your machine. node_modules and OS junk are skipped too. Want a fresh URL? hosting --new . Deploying from CI or another machine? Grab the token from the dashboard and run hosting link <subdomain> --token <token> (or set HOSTING_DEPLOY_TOKEN ). Commands C

Everything you need to know about the solar eclipse and lunar eclipse that will occur in August 2026.

Hi everyone! I just released v0.1.0 of Falco — a browser engine I've been building in Rust on nights and weekends. No WebKit, no Gecko, no Chromium — every module is written from scratch in ~36,000 lines. 🔗 GitHub : https://github.com/poxk/Falco 🔗 Releases (prebuilt binaries for Linux/macOS/Windows): https://github.com/poxk/Falco/releases/tag/v0.1.0 What's inside All modules are from scratch, with no dependency on existing browser engines: HTML5 ( html5/ + html.rs ) Tokenizer — all 80 states of WHATWG §13.2.5, including script-data escape/double-escape state machine, attribute parsing with duplicate detection, named + numeric character references with Windows-1252 quirks table Tree builder — all 22 insertion modes of WHATWG §13.2.6, stack of open elements with scope algorithms (default/button/table/select/list-item), active formatting elements list, adoption agency algorithm (8-iteration outer loop with full inner loop and bookmark tracking), foster parenting for table content XML parser — strict, with namespace bindings, CDATA, PIs Encoding detection — BOM, HTTP Content-Type charset, <meta charset> , <meta http-equiv> , heuristic UTF-8/UTF-16 detection, decoders for UTF-8 / UTF-16LE / UTF-16BE / Windows-1252 innerHTML/outerHTML serialization — void elements, <template> contents fragment, raw text elements, full attribute value escaping DOM ( dom2/ ) NodeRef = Rc<RefCell<Node>> with parent/firstChild/lastChild/previousSibling/nextSibling pointers per spec MutationObserver with observe()/disconnect()/take_records(), subtree ancestor matching, attributeFilter Shadow DOM — attachShadow() with open/closed modes, host validation, named + default slots, fallback content, slot distribution (flatten tree algorithm) Custom elements — customElements.define() with name validation, observedAttributes, lifecycle callbacks (connected/disconnected/adopted/attributeChanged/form-associated), pending upgrades, customized built-in elements (is="...") Accessibility tree — parallel tree

More EVs reaching the end of their life means more batteries to recycle. But waste management companies have yet to catch up to the new reality.

Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is...

A suite of developer tools you run with the curl you already have: UUIDs, hashes, JSON End-points, JWTs, JSON, QR, File Transfers and more. Nothing to install, and no signup required. "curl curlhub.sh" to see list of commands or visit https://curlhub.sh to view all tools full details and soon contribute. root@web01:~# curl curlhub.sh curlhub.sh — CLI-first developer utilities Zero-setup tools you curl straight from the terminal. Generators /uuid RFC 4122 v4 UUID. /pass High-entropy password / API key / token. CLI: server-side CSPRNG over TLS; web: client-side. Never logged. ( https ) Utilities /qr ANSI/UTF-8 QR code from ?data. Nothing stored server-side; use HTTPS or pipe stdin for sensitive payloads ( a ?data = value appears in request URLs ) . Encoding /b64 Base64 encode / decode. (https) /hash MD5 / SHA-1 / SHA-256 / SHA-512 of input. (https) Developer /json Validate + prettify + colorize JSON. (https) /jwt Decode & pretty-print JWT header/payload. No verify; token never logged. ( https ) /status Explain an HTTP status code + troubleshooting. /cron Translate a cron expression to English + next run times. /ua Parse the User-Agent you sent (browser / OS / engine / device). /headers Echo the request headers you sent (+ the edge view). Your own request, not a remote audit. /hook Webhook inspector: mint a temp endpoint, inspect incoming HTTP. (https) Text & Logs /md Render Markdown to colorized ANSI (safe, bounded parser). (https) /p Pastebin: pipe text/logs to a short URL (plaintext in terminal, highlighted on web). (https) Network /cidr Subnet / CIDR math: range, netmask, broadcast, host count. /ip Your public IP (thin). Geo/ASN live at worldip.io. /whois Domain registration / registrar / dates (public OSINT; rate-limited + cached ) . Security /ssl Decode a PEM certificate or CSR you paste (expiry, issuer, SANs, key). No outbound connection. (https) File Transfer /u Ephemeral file drop (<=100 MB). ANSI QR; auto-purge after 1 download or TTL. ( https ) Docs /man Com

Look at chemistry of batteries and motors shows big opportunity for recycling.

SpaceX is building a new power plant for xAI's Colossus data centers, but it won't remove existing, unpermitted turbines for many more months.

Heat waves are simultaneously hitting Europe, North America, and Asia, driven in part by the hot waters in the tropical Pacific—and climate change.