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

Apple Machine Learning Research
Apple Machine Learning Research
爱范儿
爱范儿
博客园_首页
博客园 - 【当耐特】
V
Visual Studio Blog
博客园 - 叶小钗
月光博客
月光博客
美团技术团队
J
Java Code Geeks
小众软件
小众软件
Y
Y Combinator Blog
博客园 - Franky
Martin Fowler
Martin Fowler
博客园 - 聂微东
Microsoft Azure Blog
Microsoft Azure Blog
IT之家
IT之家
MyScale Blog
MyScale Blog
人人都是产品经理
人人都是产品经理
Microsoft Security Blog
Microsoft Security Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
阮一峰的网络日志
阮一峰的网络日志
酷 壳 – CoolShell
酷 壳 – CoolShell
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
云风的 BLOG
云风的 BLOG

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - realalonw/agent-receipts: Open-source receipts f...
walon · 2026-05-03 · via Hacker News - Newest: "AI"

AI Receipt Ledger

A structured audit trail for AI agent sessions.

One function call. Works with any model. No database required.

Why use this?

Most AI features are "black boxes." AI-Receipt-Ledger turns that answer into an auditable document. Use it whenever the cost of a mistake is higher than zero.

  • Human-in-the-Loop: Give reviewers the evidence they need to sign off (Sources, Assumptions, Checklist).
  • Compliance: Create a defensible record of reasoning for regulated industries (Legal, Finance, Medical).
  • Debugging: Capture tool calls and risk flags at the moment of the run to catch hallucinations early.
  • Trust: Show users a "Confidence Score" and verified sources to prove your agent isn't just guessing.

Installation

Install directly from GitHub to use it in any project:

npm install github:realalonw/agent-receipts

Usage: The 1-Line Vibe (Zero Config)

If you're vibecoding and don't want to map fields, quickReceipt auto-detects common AI response shapes (OpenAI, Claude, etc.).

import { quickReceipt, exportReceiptToMarkdown } from "agent-receipts";

// Just wrap the call. No mapping required.
const { answer, receipt } = await quickReceipt(task, openai.chat.completions.create({ ... }));

// Export as a "Mini Slip"
console.log(exportReceiptToMarkdown(receipt));

Manual Integration

If you need full control (e.g., adding specific sources or assumptions), use the attachReceiptToResponse helper.

import { attachReceiptToResponse } from "agent-receipts";

const { answer, receipt } = await attachReceiptToResponse(task, async () => {
  const res = await openai.chat.completions.create({ ... });
  
  return {
    text:            res.choices[0].message.content,
    model:           "gpt-4o",
    confidenceScore: 95,
    sources:         [{ title: "My PDF", url: "..." }],
  };
});

Export Modes

Generate a "Mini Slip" for Slack/PRs or a "Full Audit Log" for reports.

// Compact "Mini Slip" (default)
const mini = exportReceiptToMarkdown(receipt, { mode: "mini" });

// Detailed Audit Log
const full = exportReceiptToMarkdown(receipt, { mode: "full" });

Structure

  • src/core — The Receipt engine (Types, Validation, Export).
  • src/react — Drop-in components & hooks for your UI.
  • examples/ — Integration guides (Node, React, Next.js).

Quickstart (Dev)

git clone https://github.com/realalonw/agent-receipts.git
cd agent-receipts
npm install
npm test