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

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
U
Unit 42
GbyAI
GbyAI
M
MIT News - Artificial intelligence
美团技术团队
罗磊的独立博客
雷峰网
雷峰网
量子位
博客园 - 【当耐特】
Last Week in AI
Last Week in AI
D
Docker
小众软件
小众软件
S
SegmentFault 最新的问题
Blog — PlanetScale
Blog — PlanetScale
阮一峰的网络日志
阮一峰的网络日志
宝玉的分享
宝玉的分享
T
Tailwind CSS Blog
WordPress大学
WordPress大学
V
V2EX
博客园_首页
腾讯CDC
The Cloudflare Blog
A
About on SuperTechFans
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC

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 - gelatinousdevelopment/buildermark: How much of y...
davidcann · 2026-04-23 · via Hacker News - Newest: "AI"

How much of your code is written by agents?

Buildermark matches your coding agent diffs with commits. It runs locally in the background archiving your agent conversations and serves a frontend on localhost. Your data never leaves your machine. No accounts, no cloud, no analytics.

  • Coding agent tracking - Measure how much of your code is written by agents.
  • Archive coding agent conversations - Imports conversations from Claude Code, Codex, Gemini, Cursor, Claude Code Cloud, and Codex Cloud... including any history that's still on your machine.
  • Formatting-agnostic diff matching - Buildermark matches agent output to your commits even when formatting differs or code is moved/copied. It analyzes the content of conversations without relying on hooks for each agent.
  • Rate conversations - Rate conversations manually or have the agent do it with the /rate-buildermark skill.
  • Native notifications - See agent attribution for each commit in your system notification center.

Online Demo

Browse all 364 agent conversations that wrote 94% of Buildermark's code

Buildermark project view

Install

Download from buildermark.dev or GitHub Releases.

  • macOS 15 (Sequoia) or later
  • Windows 10 or later
  • Linux CLI

How it works

  1. Imports conversation history from your coding agents.
  2. Imports git commit history from your local repository.
  3. Buildermark matches conversation diffs to commit diffs and calculates agent percentages.

A local app container manages a Go server on localhost:55022. Everything runs on your machine.

Browser Extensions

Browser extensions import your conversations from Claude Code Cloud (https://claude.ai/code) and Codex Cloud (https://chatgpt.com/codex).

  • Chrome (and Chrome-based browsers: Edge, Brave, Helium)
  • Firefox
  • Safari

To import, click through to each conversation's page and wait a few seconds... the extension's icon will show a checkmark when the import is complete.

Support

Future Work

  • Add support for more agents Request more agents
  • More charts and advanced insights
  • Skill for an agent to search conversation history in the sqlite database
  • Team Server (coming soon, with a revenue model to sustain this project)

Documentation

Database

The local sqlite database is stored in ~/.buildermark/local.db.

Configuration

Buildermark stores persistent settings in ~/.buildermark/config.json.

Schema:

{
  "updateMode": "check",
  "extraAgentHomes": ["/home/alice", "/volumes/debianvm/home/user"],
  "extraCORSOrigins": ["http://localhost:5173"]
}
Field Type Default Description
extraAgentHomes string[] [] Additional user home directories to watch for agent activity.
extraCORSOrigins string[] [] Additional origins allowed to make cross-origin requests to the API (e.g. "http://localhost:5173" for a dev frontend).
updateMode string "check" Linux CLI only. Update behavior for updates. Allowed values: "auto", "check", "off".

License

MIT