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

阮一峰的网络日志
阮一峰的网络日志
博客园 - 司徒正美
D
DataBreaches.Net
宝玉的分享
宝玉的分享
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 【当耐特】
人人都是产品经理
人人都是产品经理
博客园 - Franky
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
IT之家
IT之家
博客园 - 三生石上(FineUI控件)
J
Java Code Geeks
腾讯CDC
博客园_首页
The Cloudflare Blog
S
SegmentFault 最新的问题
C
Check Point Blog
美团技术团队
爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
Hugging Face - Blog
Hugging Face - Blog
T
The Blog of Author Tim Ferriss
A
About on SuperTechFans
Blog — PlanetScale
Blog — PlanetScale

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
Stord — The Undo Button for AI Agents
ishwantsingh · 2026-06-24 · via Hacker News - Newest: "AI"

Open source · MIT · works with Claude Code, Codex & more

Let your agents run with permissions skipped. Stord records every file they read and write — attributed to the agent that did it — and makes every change reversible.

See it in action

Every Operation, On the Record

An agent reads your .env and rm -rfs your build. Stord shows you exactly who did what — then stord undo brings it all back.

stord — agent flight recorder

Terminal demo: stord log shows a Claude Code agent reading .env and a Codex agent deleting build/, then stord undo restores the deleted files and stord agents lists every identity.

The problem

Agents act with production access and no seatbelt.

Coding agents run with skip-permissions flags. Ops agents hold credentials broader than any employee’s. When one overwrites a config, wipes a directory, or leaks a file, there’s no record of what happened and no way back.

Identity tools know who the agent is. Gateways know what it called. Nobody knows what happened to your data — or can undo it.

63%of orgs can’t stop their AI agents when something goes wrong

33%have no audit trail of agent activity at all

45:1machine identities now outnumber humans

What Stord does

A governance layer between agents and your files.

Start with the open-source CLI today — audit and undo on your own machine, zero dependencies. The cloud layer adds enforced permissions and tamper-evident, fleet-wide audit. That’s what the waitlist is for.

01 · AUDITAvailable now

Flight recorder

An append-only journal of every read, write, and delete — attributed to the exact agent, session, and user. stord log shows the timeline; stord agents shows who touched what.

02 · REVERSEAvailable now

The undo button

Every write is snapshotted before it runs. Reverse a single operation with stord undo or roll the whole tree back with stord restore — even after rm -rf. Your real git history is never touched.

03 · PERMISSIONOn the roadmap

Scoped agent credentials

Least-privilege keys per agent, not per team. Path-scoped permissions like write: /build/**, enforced — plus tamper-evident, off-host audit and a fleet dashboard. Join the waitlist →

Free & open source

Install it in one line.

One Node file, zero dependencies, MIT licensed. Works with Claude Code out of the box, and with Codex, Hermes, OpenClaw, or any custom agent via hooks.


$ stord enable
$ claude --dangerously-skip-permissions
$ stord log  
$ stord undo last  

Cloud — early access

Run your fleet. Keep the receipts.

The CLI is yours today. The cloud layer — enforced per-agent permissions, tamper-evident off-host audit, and a dashboard across every agent and machine — is onboarding early teams now. Join for early access and founding-user pricing.

No spam — launch updates only.