惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Cisco Talos Blog
Cisco Talos Blog
The Hacker News
The Hacker News
L
LINUX DO - 最新话题
P
Privacy & Cybersecurity Law Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
S
Secure Thoughts
S
Schneier on Security
MyScale Blog
MyScale Blog
月光博客
月光博客
U
Unit 42
www.infosecurity-magazine.com
www.infosecurity-magazine.com
AI
AI
N
News and Events Feed by Topic
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
爱范儿
爱范儿
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
S
Securelist
B
Blog RSS Feed
Spread Privacy
Spread Privacy
H
Help Net Security
Know Your Adversary
Know Your Adversary
I
Intezer
Hacker News - Newest:
Hacker News - Newest: "LLM"
V
V2EX
MongoDB | Blog
MongoDB | Blog
GbyAI
GbyAI
博客园 - 叶小钗
D
DataBreaches.Net
T
Troy Hunt's Blog
Project Zero
Project Zero
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
P
Privacy International News Feed
The Last Watchdog
The Last Watchdog
K
Kaspersky official blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Latest news
Latest news
S
Security @ Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
V2EX - 技术
V2EX - 技术
Hacker News: Ask HN
Hacker News: Ask HN
The GitHub Blog
The GitHub Blog
C
Cisco Blogs
C
CERT Recently Published Vulnerability Notes
Attack and Defense Labs
Attack and Defense Labs
T
Threatpost
O
OpenAI News
Recorded Future
Recorded Future
Help Net Security
Help Net Security
罗磊的独立博客

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
GitHub - tozzilla/claudebar: ClaudeBar — a native macOS menu bar app that shows your live Claude usage: current session %, weekly limits, reset times, and extra-usage credits. Reads the same data as the official Claude console.
mr_tox · 2026-06-24 · via Show HN

ClaudeBar is a lightweight, native macOS menu bar app that shows your live Claude usage at a glance: your current session percentage, weekly limits, reset times, and extra-usage credits — the exact same numbers as the official Claude usage console, right in your status bar.

Built for developers using Claude Code, Claude Pro, Claude Max, and Claude Team who want to keep an eye on their rate limits without opening a browser tab.

Platform: macOS 13+ Apple Silicon Swift 5.9 Dependencies: none


Preview

 menu bar ▸   8% · 4h47m

 ┌─────────────────────────────────────────────┐
 │  Sessione corrente                          │
 │    8% utilizzato · reset tra 4h 47m (17:39) │
 │  ──────────────────────────────────────────│
 │  Limiti settimanali                         │
 │    Tutti i modelli: 41% · reset lun 02:59   │  ← active limit in bold
 │    Sonnet: 24% · reset lun 02:59            │
 │  ──────────────────────────────────────────│
 │  Crediti extra                              │
 │    €90,01 / €150,00 (60%)                   │
 │  ──────────────────────────────────────────│
 │  Aggiornato 12:52:52                        │
 │  Aggiorna ora    ⌘R                         │
 │  ✓ Avvia al login                           │
 │  Esci            ⌘Q                         │
 └─────────────────────────────────────────────┘

The menu-bar title shows current session % · time until reset. Click it for the full breakdown.


Features

  • Live session usage — current 5-hour session percentage and a countdown to the reset, ticking locally every 30 seconds.
  • Weekly limits — "all models" and per-model (e.g. Sonnet) weekly usage with their reset day/time; the currently active limit is highlighted.
  • Extra-usage credits — your monthly credit spend in your billing currency (e.g. €90.01 / €150.00).
  • Color-coded at a glance — a tinted dot and percentage in the bar: 🟢 ≤64 · 🟡 65–84 · 🔴 ≥85.
  • Threshold notifications — optional macOS notification when any limit crosses your alert threshold (default 85%), once per reset window.
  • Choose what the bar shows — current session, top weekly limit, or automatic (whichever is most binding).
  • Exact console parity — reads the same authenticated endpoint the Claude console uses, so the numbers always match.
  • Gentle on the API — fetches at most once every few minutes (configurable), ticks the countdown locally in between, refreshes on wake/network return, and backs off automatically on HTTP 429 (honoring Retry-After).
  • Native & tiny — a single Swift binary for Apple Silicon, zero dependencies, no Electron, negligible memory and CPU.
  • Private by design — reads your token from the macOS Keychain at runtime and talks only to Anthropic's API. Nothing is logged or sent anywhere else.
  • Preferences in the menu — bar metric, notifications, alert threshold, refresh interval, launch at login, and a quick link to the usage console.

Why ClaudeBar (and how it differs from ccusage)

Tools like ccusage read your local transcript logs in ~/.claude/projects/**/*.jsonl and estimate usage from token counts. That's great for cost analysis, but those logs contain only token counts — the console's real percentages are not derivable from them, so a token-log estimator can't match the official "you've used X%" numbers.

ClaudeBar takes the other approach: it reads the same authenticated usage endpoint the Claude console itself uses, so what you see in the menu bar is exactly what you'd see in the console — no estimation, no drift.

Token-log estimators (ccusage-style) ClaudeBar
Data source local JSONL token logs official api/oauth/usage
Session / weekly % estimated exact (console parity)
Reset times inferred authoritative
Extra-usage credits (€/$)
Dollar cost estimate ✗ (shows plan %, not $ per token)

Use ccusage for per-project token/cost accounting; use ClaudeBar to mirror your plan limits live.


How it works

flowchart LR
    A[ClaudeBar] -->|reads OAuth token| B[(macOS Keychain<br/>Claude Code-credentials)]
    A -->|GET /api/oauth/usage<br/>Bearer token| C[Anthropic API]
    C -->|session % · weekly % · reset · credits| A
    A --> D[Menu bar title + dropdown]
Loading
  1. Reads the Claude Code OAuth token from the macOS Keychain (generic password, service Claude Code-credentials).
  2. Calls GET https://api.anthropic.com/api/oauth/usage with that token.
  3. Renders session/weekly limits, reset times, and credits in the menu bar.

The token is re-read from the Keychain on every fetch, so it stays valid as long as you use Claude Code (which refreshes it). If it expires, ClaudeBar shows ⚠︎ login — just reopen Claude Code to refresh it.


Requirements

  • macOS 13 (Ventura) or later — tested on Apple Silicon.
  • Swift toolchain — the Xcode Command Line Tools are enough (swift --version).
  • Claude Code installed and logged in (so the OAuth token is in your Keychain).

Installation

Homebrew (recommended)

brew install --cask tozzilla/claudebar/claudebar
open /Applications/ClaudeBar.app

The cask installs the signed and notarized build, so it opens with no Gatekeeper warnings.

Download

Grab the notarized ClaudeBar-<version>.zip from the latest release, unzip, and move ClaudeBar.app to /Applications.

Build from source

git clone https://github.com/tozzilla/claudebar.git
cd claudebar

# Build a standalone ClaudeBar.app
./build.sh

# Install and launch
cp -r ClaudeBar.app /Applications/
open /Applications/ClaudeBar.app

Then open the menu and enable Avvia al login ("Launch at login") to keep it running.

For development you can run it in the foreground instead:

./init.sh            # build + run; Ctrl-C to stop

First run: Keychain permission

The first time ClaudeBar reads your token, macOS may ask for permission to access Claude Code-credentials. Click "Always Allow" — after that it reads the token silently.


Configuration

ClaudeBar works out of the box. To tweak it, edit and rebuild:

  • Refresh intervalfetchInterval in Sources/ClaudeBar/AppDelegate.swift (default 180s; the endpoint updates roughly once a minute).
  • Countdown tick ratetickInterval (default 30s, network-free).
  • Menu-bar textupdateTitle() in AppDelegate.swift.

Debug / one-shot

.build/release/ClaudeBar --print   # fetch once, print the snapshot, exit

Privacy & security

  • The OAuth token never leaves your machine except in the Authorization header of the request to Anthropic's own API.
  • The token is not stored in the app, the source, or the repository — it is read from the Keychain at runtime.
  • No telemetry, no analytics, no third-party services.

Rate limiting

The usage endpoint is designed for occasional refreshes (the console has a manual refresh button). ClaudeBar therefore:

  • fetches at most once every ~3 minutes,
  • never fetches just because you opened the menu (it rebuilds from cache),
  • ticks the reset countdown locally without hitting the network,
  • and, on HTTP 429, backs off (using the Retry-After header) while continuing to display the last good data.

FAQ

Does this work with Claude Pro / Max / Team? Yes. It reads whatever plan limits the API returns for your account (session, weekly, per-model, and credits where applicable).

Why don't my numbers match ccusage? They measure different things. ccusage estimates from local token logs; ClaudeBar reads the official usage endpoint. See Why ClaudeBar.

It shows ⚠︎ login. Your OAuth token expired. Open Claude Code to refresh it; ClaudeBar picks up the new token automatically.

It shows a 429 / rate-limit note. Too many requests in a short window. ClaudeBar backs off and recovers on its own — no action needed.

Does it need Xcode? No. The Command Line Tools provide everything (swift build links AppKit from the macOS SDK).


Tech

Swift + AppKit (NSStatusItem), built with Swift Package Manager into a native arm64 binary, wrapped into a LSUIElement (agent) app bundle so it lives only in the menu bar with no Dock icon. Launch-at-login via SMAppService.

License

MIT — see LICENSE.