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

MyScale Blog
MyScale Blog
U
Unit 42
The Register - Security
The Register - Security
S
Security Affairs
博客园 - 【当耐特】
Latest news
Latest news
爱范儿
爱范儿
T
The Exploit Database - CXSecurity.com
F
Full Disclosure
C
Cisco Blogs
宝玉的分享
宝玉的分享
C
Cyber Attacks, Cyber Crime and Cyber Security
L
LangChain Blog
P
Privacy & Cybersecurity Law Blog
腾讯CDC
C
CXSECURITY Database RSS Feed - CXSecurity.com
V
Vulnerabilities – Threatpost
Jina AI
Jina AI
Apple Machine Learning Research
Apple Machine Learning Research
博客园 - 叶小钗
www.infosecurity-magazine.com
www.infosecurity-magazine.com
博客园_首页
博客园 - 三生石上(FineUI控件)
D
DataBreaches.Net
WordPress大学
WordPress大学
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Microsoft Security Blog
Microsoft Security Blog
N
News and Events Feed by Topic
Recorded Future
Recorded Future
Scott Helme
Scott Helme
Hacker News: Ask HN
Hacker News: Ask HN
Webroot Blog
Webroot Blog
AWS News Blog
AWS News Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
人人都是产品经理
人人都是产品经理
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
T
Tor Project blog
F
Fortinet All Blogs
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
H
Hacker News: Front Page
J
Java Code Geeks
A
About on SuperTechFans
The GitHub Blog
The GitHub Blog
博客园 - 聂微东
Last Week in AI
Last Week in AI
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
W
WeLiveSecurity
V2EX - 技术
V2EX - 技术
T
Troy Hunt's Blog
Attack and Defense Labs
Attack and Defense Labs

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 - claude-schwabe/schwabe
schwabe · 2026-06-11 · via Show HN

schwabe — the token burner · too thrifty to let a token expire

Your token limit just reset, and it expires before you'll ever use it honestly. The only responsible thing to do is not to waste them.

schwabe is a token burner: it spins up a fleet of real AI agents that burn through every token you paid for — and logs every one. It runs entirely in your terminal. Full utilization is the deliverable: nothing left on the table.

Quick start

npm i -g schwabe   # install — puts `schwabe` on your PATH (alias: tokenburner)
schwabe            # the menu

schwabe opens a small arrow-key menu — pick what to do, pick a model, go. Everything runs right there in your terminal (↑/↓ move · enter select · ← back · q quit). Prefer flags? node burn.js takes them directly.

What it burns on

🔥 Burn — each agent gets one magnificently over-the-top task (a sonnet about a runaway semicolon, an argument over whether water is wet, release notes for the heat death of the universe…) and commits fully.

🌲 Offset your consumption (--forest) — each agent "plants" an ASCII tree into a growing FOREST.txt, and we tally the virtual CO₂ savings (using real per-species sequestration rates) against the very real CO₂ we just emitted burning the tokens. Certified carbon-negative™. (It is not.)

node burn.js — the flags

node burn.js                                # burn, default tier (rich/opus) — spends real money
node burn.js --forest --schwabe --count 25  # 5×5 forest on haiku (cheap)
node burn.js --dry                          # mock backend — same UI, ZERO spend (safe preview)
node burn.js --plain                        # headless line output (no full-screen TUI)
flag meaning default
--forest plant a virtual forest instead of burning text off
--schwabe / --student / --rich / --whale budget tier → haiku / sonnet / opus / fable 5 🐋 --rich
--mode <tier> · --model <id> same, long form · override the model from tier
--count N (alias --fleet) how many agents in total ∞ (endless)
--concurrency N (alias --parallel) how many run at once (~1 GB RAM each) 6
--unlimited open the floodgates (as many as your RAM survives) off
--backend <name> claude · gemini · codex · mock claude
--dry mock backend, no spend off
--plain headless renderer auto (non-TTY)
--no-retry give up instead of waiting out rate limits off
--share <platform> print a brag link after the receipt off

⚠️ node burn.js with no flags spends real tokens on opus. Watch it free first with node burn.js --dry.

The live dashboard is btop-style — heat-graded progress, per-agent spinners, a tokens/sec graph, and a running LEDGER with lifetime totals. Colors auto-adapt to a light or dark terminal. Press q to bail.

The live btop-style burn dashboard, in your terminal

It logs everything, and survives running dry

Every agent is recorded to burns.csv (metrics) and ashes.jsonl (the output), with lifetime totals carried across runs. Hit a rate / budget limit mid-burn and the fleet waits and keeps retrying until it clears, then resumes — --no-retry opts out.

Brag (optional, off by default)

node share.js x              # prints a prefilled tweet link from your last burn

share.js reconstructs your most recent run from the ledger and hands you a prefilled share link — it never opens a browser, you press the button — behind a quick "heads up before you post" confirmation. --yes skips it.

Bonus: the Claude Code fleet

Inside Claude Code, /burn [N] runs a parallel swarm of agents and forges the funniest wreckage into HALL_OF_FLAME.md.

How it's built

Clean, dependency-free, ESM. Add a burn engine or a share platform by dropping one spec file into lib/backends/ or lib/integrations/ — both share one tiny lib/core/registry.js. Every module is unit-tested with Node's built-in runner and zero test dependencies: npm test.

burn.js              entry: fleet → live dashboard → receipt
launcher.js          the `schwabe` menu (alias: tokenburner)
lib/core/            util · config (flags + MODES tiers) · registry (name→spec)
lib/backends/        claude · gemini · codex · mock  (registry + factory)
lib/engine/          fleet · retry · metrics · tasks · prompts · ledger
lib/forest/          the ASCII forest + real per-species CO₂ data
lib/ui/              tui.js (btop) · plain.js (headless) · widgets.js
lib/integrations/    brag/share platforms (prints links; never opens a browser)
test/                node:test unit suite (npm test) — no test deps

Every lib/ entry is a domain directory — no loose files — and every module is unit-tested.

Why this repo exists — die schwäbische Doktrin 🪙

This whole thing is built for the Schwabe.

If you've never met one: a Schwabe is from Baden-Württemberg, the part of Germany known for not spending money.* He doesn't throw out food, doesn't leave the lights on, and will circle the block for twenty minutes to dodge a parking fee. Sunk cost isn't a fallacy to him, it's just not a concept he accepts. Paid for it? Then you use all of it, bis auf den letzten Token.

Now think about your token limit. You paid for it, it resets on a timer, and any tokens you didn't use are simply gone when the window closes. Most people don't notice. A Schwabe can't think about anything else. Owning something and not using it physically hurts.

Now the real nightmare: the tank refills two days before the plan expires. Fresh tokens, already paid for, on a countdown. A normal person shrugs and uses what they need. The Schwabe clears his calendar. He burns day and night — breakfast, lunch, 3 a.m. — feeding the fleet until every last token is spent, because letting them expire unused is simply not something he can live with.

That's what schwabe is for. You sit down, burn through every token you're owed, and hit a clean 100% with a clear conscience. It was never about the output. Nichts verschwendet.

And for the Green Schwabe — the one who drives a 1,000 hp, 3-tonne, "AA++" hybrid SUV basically a bicycle — there's --forest option. Plant a whole virtual forest to offset the emissions. It cancels out about as much CO₂ the tokens cost you, but the conscience stays spotless.

Nett hier. Aber waren Sie schon mal in Baden-Württemberg?


* The one time a Schwabe spends all his money at once is buying a house. And the moment he signs, he bumps up the loan so he can also drive home a Mercedes, then spends the next 40 years paying both back. Sparsamkeit is a long game.

License

WTFPL. Do what the fire wants.