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

罗磊的独立博客
L
LangChain Blog
aimingoo的专栏
aimingoo的专栏
IT之家
IT之家
B
Blog
博客园_首页
博客园 - 司徒正美
有赞技术团队
有赞技术团队
博客园 - 聂微东
I
InfoQ
美团技术团队
GbyAI
GbyAI
阮一峰的网络日志
阮一峰的网络日志
H
Help Net Security
大猫的无限游戏
大猫的无限游戏
MyScale Blog
MyScale Blog
WordPress大学
WordPress大学
The GitHub Blog
The GitHub Blog
A
About on SuperTechFans
人人都是产品经理
人人都是产品经理
Microsoft Azure Blog
Microsoft Azure Blog
Engineering at Meta
Engineering at Meta
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
The Cloudflare Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - softcane/cc-session-recover: Recover Claude Code...
pradeep1177 · 2026-06-15 · via Hacker News: Show HN

Your long Claude Code task survives quota stops — and continues by itself after the reset, with no prompt from you.

When quota or a rate limit kills a session mid-task, Claude normally just stops until you come back and tell it to continue. This workflow removes that. Claude keeps a recovery note (HANDOFF.md) as it works, retries on a slow schedule while quota is blocked, and the first attempt after the reset picks the task up exactly where it stopped.

Every part of this has been verified against a genuine quota stop, end to end.

Install

npx cc-session-recover init /path/to/project

(Or from a clone: bash scripts/install-into-project.sh /path/to/project. Pass --no-hooks with either to install the files without activating anything.)

Approve the hooks once when Claude Code asks on the next start. That's the whole setup.

Use

cd /path/to/project
claude

Give Claude your task, normally. Nothing extra to type — the injected standing instructions make Claude keep the recovery note and set its own retry schedule. Leave the terminal open and walk away.

If quota dies mid-task, work resumes automatically after the reset.

Why This Approach Is Stronger

  • It avoids tmux, screen, and terminal-injection hacks. Headless claude -p --resume is used only by the optional closed-terminal watcher, targeting the exact recorded session.
  • It gives you two recovery paths. With the terminal open, the heartbeat resumes inside the active Claude Code session. With the terminal closed, the watcher resumes the saved session id.
  • HANDOFF.md keeps the next step in the repo, with project state, recent progress, and the exact next action.
  • The heartbeat runs inside the active Claude Code session, so the original context stays alive while quota is blocked.

Limits

  • It does not bypass quota. It only waits for the reset.
  • The basic flow needs the terminal to stay open. A closed-terminal recovery mode exists; see the docs.
  • Worst case is never lost work: the recovery note is always on disk, and "Read HANDOFF.md and continue" restores any session by hand.

Docs

  • Simple flow — how it works, told as a story (notebook, alarm, watchman).
  • FAQ — reliability, hook approval, what still needs a human.
  • Full details — closed-terminal watcher, precise reset-time resume, all limits.