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

Recent Announcements
Recent Announcements
雷峰网
雷峰网
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
Hugging Face - Blog
Hugging Face - Blog
博客园 - 司徒正美
人人都是产品经理
人人都是产品经理
博客园 - 【当耐特】
量子位
有赞技术团队
有赞技术团队
博客园 - 三生石上(FineUI控件)
博客园 - Franky
M
MIT News - Artificial intelligence
U
Unit 42
Last Week in AI
Last Week in AI
酷 壳 – CoolShell
酷 壳 – CoolShell
The Cloudflare Blog
J
Java Code Geeks
V
Visual Studio Blog
Engineering at Meta
Engineering at Meta
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
MyScale Blog
MyScale Blog
T
Tailwind CSS Blog
T
The Blog of Author Tim Ferriss
V
V2EX

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
Tokoscope — See Inside Your Token Usage
Tokoscope · 2026-06-21 · via Hacker News - Newest: "LLM"

npm version npm downloads

LLM token optimization

See inside your
bloated prompts.

Tokoscope audits, compresses, and monitors your LLM token usage so you ship leaner prompts and smaller bills.

4070%

of tokens in average prompts are waste

$0.003

per 1K tokens adds up fast at scale

3x

typical reduction after prompt compression

What it does

Full visibility between
your app and the API.

Drop in one SDK line. Tokoscope sits in the middle, tracks every call, and shows you exactly where money is leaking.

🔭

Prompt inspector

Scans your system prompts and inputs for bloat — repeated instructions, redundant context, unnecessary preamble — and scores each one.

Smart caching

Detects semantically similar requests and serves cached responses. Near-identical prompts stop hitting the API twice.

✂️

Auto-compression

Rewrites verbose prompts to their minimum effective form without changing intent. Ships leaner, costs less, still works.

📊

Cost attribution

Break down spend by feature, endpoint, user, or team. Know which part of your product is burning the most — and why.

🚨

Budget alerts

Set spend thresholds per workspace or per key. Get notified before costs spike, not after the invoice lands.

🔌

Any LLM, one SDK

Works with OpenAI, Anthropic, Gemini, Mistral, and any OpenAI-compatible endpoint. One integration, full visibility.

Dead simple setup

Two lines.
Full visibility.

Wrap your existing client. No infrastructure changes. Works in Node, Python, or any HTTP stack.

Get API key →

// Before
import OpenAI from 'openai';
const client = new OpenAI();

// After — that's it
import { wrap } from 'tokoscope';
const client = wrap(
  new OpenAI(),
  { apiKey: 'ts_live_...' }
);

// All your existing calls, unchanged.
// Tokoscope handles the rest.
const res = await client.chat
  .completions.create({
    model: 'gpt-4o',
    messages: [...]
  });

Pricing

Pay less than you save.

Tokoscope pays for itself. If it doesn't cut your LLM bill, cancel anytime.

Free

$0

forever

  • 500K tokens / month monitored
  • Usage dashboard
  • Basic prompt scoring
  • 1 workspace

Start free

Most popular

Pro

$49

per workspace / month

  • Unlimited tokens monitored
  • Auto-compression
  • Semantic caching
  • Cost attribution
  • Budget alerts
  • 5 workspaces

Get early access

Team

$99

per month + usage

  • Everything in Pro
  • Unlimited workspaces
  • Per-user attribution
  • Slack / webhook alerts
  • Priority support

Contact us

Your LLM bill is too high.
Let's fix that.

Join the waitlist. Early access ships this quarter.