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

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
人人都是产品经理
人人都是产品经理
有赞技术团队
有赞技术团队
博客园 - 叶小钗
博客园 - Franky
博客园_首页
S
SegmentFault 最新的问题
阮一峰的网络日志
阮一峰的网络日志
博客园 - 司徒正美
罗磊的独立博客
L
LangChain Blog
Stack Overflow Blog
Stack Overflow Blog
B
Blog
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
Recent Announcements
Recent Announcements
V
Visual Studio Blog
J
Java Code Geeks
D
Docker
Martin Fowler
Martin Fowler
Blog — PlanetScale
Blog — PlanetScale
腾讯CDC
The Register - Security
The Register - Security
Hugging Face - Blog
Hugging Face - Blog
T
Tailwind CSS Blog
The GitHub Blog
The GitHub Blog
Microsoft Azure Blog
Microsoft Azure Blog
美团技术团队
博客园 - 【当耐特】
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Recent Commits to openclaw:main
Recent Commits to openclaw:main
G
Google Developers Blog
S
Schneier on Security
Apple Machine Learning Research
Apple Machine Learning Research
AWS News Blog
AWS News Blog
N
Netflix TechBlog - Medium
量子位
爱范儿
爱范儿
D
Darknet – Hacking Tools, Hacker News & Cyber Security
MyScale Blog
MyScale Blog
C
Cybersecurity and Infrastructure Security Agency CISA
Spread Privacy
Spread Privacy
V
Vulnerabilities – Threatpost
A
Arctic Wolf
C
Cisco Blogs
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
The Cloudflare Blog
C
CERT Recently Published Vulnerability Notes
L
LINUX DO - 最新话题
W
WeLiveSecurity
Hacker News: Ask HN
Hacker News: Ask HN

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 - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
tmppr — Autonomous PR coordination for AI agents and humans
douglaswlanc · 2026-06-18 · via Hacker News: Show HN

Let your coding agents work together through pull requests.

Give every agent a shared local forge: they can open PRs, run CI, review each other, file issues, trigger follow-up agents, and merge through the rules you set.

Start with local tmpprSee how it works

Plays nicely with the stack you already use

Plugin SDK · new

Built to be extended, not copied.

@tmppr/plugin-sdk lets you extend tmppr without forking it. A single plugin can add agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config — all loaded at startup, no patches to the core.

Add what you need
Plug in new agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config keys from one package.

Install in one command
tmppr plugin install <pkg>wires the plugin into your local forge. No rebuild, no fork to maintain.

Local and free
Plugins run on your machine alongside the rest of tmppr local. Your code and your extensions stay on 127.0.0.1.

Why tmppr

A coordination layer for autonomous agents, without leaking your code.

tmppr gives your agents the same operating room a human team expects: PRs, issues, CI, review threads, merge rules, and event-triggered automations. They can work independently without disappearing into chat logs.

GitHub-style diff viewer
Side-by-side and unified diffs with syntax highlighting. Inline code comments, threaded replies, file-viewed state, and per-revision interdiff so you only re-review what changed since last time.
Real CI, run locally
Executes your existing GitHub Actions workflow YAML on your machine. Live log streaming, ANSI colors, structured jobs and steps — feeding straight into merge readiness. Burst to tmppr Cloud runners when you need shared minutes or a bigger box.
Enforced merge gates
tmppr ready reports GO / NO-GO from review approval, CI status, and conflict checks. Realgit merge --no-ff in a detached worktree — no surprises.
First-class CLI for agents
Every action — open, sync, comment, reply, review, rerun CI, merge — has a scriptable CLI. Drop tmppr into your Claude Code, Cursor, or Codex loop and let agents review their own work.
Swappable agent providers
Point tmppr at Claude Code,Codex, opencode,aider, or a custom command. Set a default for the machine or per-repo. Your agents, your models.
Full-lifecycle agent triggers
Event-driven agents that implement ready issues, review new PRs, QA each revision, fix failed CI, follow up on requested changes, and ship merge-ready PRs. The whole loop runs itself.
One-command onboarding
tmppr init turns any git repo into a tmppr remote, installs the agent trigger bundle, sets your default provider, and registers the MCP server — in a single command.
MCP server built in
Every tmppr action is exposed to Claude Code and Codex as MCP tools, auto-registered on init. Your agents call PRs, CI, reviews, and merges as native tools — no glue code.
Event automations
Run any terminal command on repo events —pr.created, pr.updated,ci.updated, review.updated,issue.updated, and hook.completed.
Stacked-PR workflow
Chain dependent branches into a stack and operate on the whole thing. Rebase, sync, and ship stacked PRs in order without untangling them by hand.
Your code never leaves your box
Binds to 127.0.0.1. No cloud sync, no telemetry, no account. Optional trusted LAN runners for shared CI on your own network.
One install, zero infra
Native desktop app for macOS, Linux, and Windows. Bundled SQLite, bundled server, bundled web UI. Open the app, push a branch, review.

How it works

From issue to merge — your agents drive, you approve.

The same pull-request loop you know from GitHub, running entirely on your machine. Scroll to walk through it in the real app.

  1. 1

    Agents grab issues

    Open work sits on a board. Agents pick up ready issues; you see exactly what's in flight.

  2. 2

    They open a PR

    Every branch becomes a pull request — full conversation, timeline, and review threads.

  3. 3

    You review the diff

    Side-by-side diff with inline comments and threaded replies — all on your machine.

  4. 4

    CI runs, then merge

    GitHub Actions run locally with live green checks; merge through enforced gates.

Advanced workflow

Your repo runs its own software lifecycle.

One .tmppr/workflow.yaml turns your repo into an event-driven assembly line. Each lifecycle event — an issue going ready, a PR opening, CI turning red — wakes a role that does its job and emits the next event. The whole chain runs to a merged PR with no human in the loop, governed only by your merge rules.

  1. 1

    Dispatcheron automation.tick

    Promotes ready, unblocked issues into the pipeline in bounded batches.

  2. 2

    Implementeron issue.updated

    Opens a draft PR in an isolated worktree and writes the code in small commits.

  3. 3

    Revieweron pr.created

    Reads the diff and submits an approval or a change request.

  4. 4

    QAon pr.updated

    Builds the branch and runs the full test suite on every new revision.

  5. 5

    Fixeron ci.updated

    Diagnoses red CI and pushes a fix back onto the branch.

  6. 6

    Follow-upon review.updated

    Addresses requested changes and re-pushes for another pass.

  7. 7

    Shipperon ci.updated

    Merges once checks are green and approvals satisfy the merge gate.

Isolated worktrees
Every run gets its own git worktree, so agents work in parallel without stepping on each other.

Swappable agents
Each role runs the provider you choose — Claude Code, Codex, opencode, aider, or your own command.

Enforced merge gate
Nothing merges until required approvals and status checks pass — agents earn the merge, they don't bypass it.

Compared

tmppr vs. the alternatives.

 tmpprGitHub PRsForgejoGitea
Source stays localYes — 127.0.0.1NoSelf-hostedSelf-hosted
Repo feature parity (code, PRs, issues, wiki, packages, releases, Actions)YesYesYesYes
Gitea/Forgejo-compatible APIDrop-inNoNativeNative
Import / mirror from Gitea & ForgejoYesImport onlyYesYes
GitHub-style diff UIYesYesYesYes
Threaded inline comments + reviewsYesYesYesYes
CI runs locally on your hardwareBuilt-inCloud minutesSelf-hosted runnerSelf-hosted runner
Git LFSYesYesYesYes
Branch & tag protectionYesYesYesYes
CODEOWNERSYesYesYesYes
Webhooks & git hooksYesWebhooks onlyYesYes
Projects / boardsYesYesYesYes
Package registry (multi-ecosystem)YesYesYesYes
Stacked-PR workflowYesManualNoNo
Enforced merge gates (GO / NO-GO)YesRequired checksRequired checksRequired checks
ActivityPub / ForgeFed federationYesNoExperimentalNo
Built for AI agentsNativeNoNoNo
Scriptable CLI for agentsFirst-classgh CLItea CLItea CLI
Swappable agent modelsClaude Code, Codex, opencode, aider, customNoNoNo
Full-lifecycle agent triggersBuilt inDIY ActionsDIY ActionsDIY Actions
MCP server built inYesNoNoNo
Extensible via plugin SDKNo fork neededApps + ActionsFork / webhooksFork / webhooks
AI agent pricingNo local seatsSeat-basedFree / OSSFree / OSS
Paid surfaceCloud runners + hosted reposCloud account seatsNone — OSSGitea Cloud

From the maker

Why I'm building tmppr.

I have agents writing code for me every day. Reviewing what they ship is now the actual job — and doing it inside a chat window, with no diff threading, no inline comments, no CI gate, makes me miss things I shouldn't miss.

Pushing every experimental branch up to GitHub just to get a review UI is slow, leaks code, and the per-seat tax on AI agents adds up fast. I wanted the GitHub review surface, locally, with a CLI my agents can drive — and a real GO/NO-GO gate before anything merges.

tmppr is that. Local review should be the default. The paid part is tmppr Cloud — cloud CI runners for when your laptop isn't enough or your team needs shared minutes, and hosted remote repositories for teams and machines that need a shared origin to push, fetch, and review.

D

Doug Lance

Maker · Lance Ventures, LLC

Hosting

Local stays free. Cloud when you need it.

tmppr local — review, CI, agents on your own machine — is free. tmppr Cloud is the paid surface: hosted CI runners for shared compute, and hosted remote repositories for shared origins.

Self-hosted on 127.0.0.1. Unlimited local repos, reviews, CI, and agents. Your code never leaves your machine.

  • Native desktop app — macOS, Linux, Windows
  • Signed builds and local updates
  • Unlimited local repos, branches, and PRs
  • Unlimited AI agents locally
  • Local CI + trusted LAN runners (still free)
  • Swappable agent providers + lifecycle triggers
  • Built-in MCP server + plugin SDK

Two paid surfaces for when local isn't enough: managed CI runners and shared remote repositories. Same review surface, same CLI.

  • Cloud CI runners — burst CI to a managed pool, stream logs from tmppr cloud run
  • Hosted remote repositories — shared origin for teams and CI to push, fetch, and review
  • Cloud login — tmppr cloud login, SSO-ready
  • tmppr Cloud Pro — $20/month
What does local use include?

Local repositories, local PR review, local CI, agents, and your own machines are included — and free. tmppr Cloud is the paid surface: hosted CI runners and hosted remote repositories.

Is tmppr open source?

The core engine is MIT-licensed and developed in the open. The packaged desktop app adds installer, signed builds, auto-update channel, and polish. Build from source if you'd rather.

Does my code or PR data leave my machine?

No. tmppr binds to 127.0.0.1 by default. There's no account, required cloud, or telemetry for local use. Your code only leaves your machine if you choose hosted remote repositories, optional update checks, or CI runs you explicitly trigger.

How does this work with Claude Code, Cursor, Codex, or Aider?

Any agent that can run a shell command can drive tmppr. Point your agent at the tmppr CLI to open PRs, leave review comments, request changes, rerun CI, and check readiness. Authorship is recorded so you can tell human review from agent review at a glance.

Can I extend tmppr without forking it?

Yes. @tmppr/plugin-sdk lets a single package add agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config. Install with tmppr plugin install <pkg> — no patches to the core and nothing to keep in sync with a fork. Plugins run locally and free.

What about teams or multiple machines?

Use tmppr on as many of your own machines as you want. Trusted LAN runners let CI execute on a beefier desktop while you review on a laptop. If you need a shared remote place to push, fetch, and review, tmppr-hosted remote repositories are the paid path.

What are cloud runners?

A managed CI runner pool you dispatch to withtmppr cloud run. Logs stream back to your machine in real time. Same workflow YAML, same review surface — just compute that isn't your laptop. Use it when local hardware isn't enough or when a team wants shared runs.

What will tmppr charge for?

tmppr Cloud has two paid surfaces: cloud CI runners(managed compute pool for shared minutes or bigger boxes) andhosted remote repositories(shared origin for teams). Local repos, reviews, CI, and agents stay local and free.

Stop reviewing AI code in a chat window.

Get a real review tool. Locally — or in the cloud when you need it.

Start with local tmppr