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

Jina AI
Jina AI
宝玉的分享
宝玉的分享
Last Week in AI
Last Week in AI
Help Net Security
Help Net Security
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
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
GbyAI
GbyAI
博客园_首页
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
MongoDB | Blog
MongoDB | Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
L
LINUX DO - 最新话题
PCI Perspectives
PCI Perspectives
博客园 - 三生石上(FineUI控件)
V2EX - 技术
V2EX - 技术
Spread Privacy
Spread Privacy
T
Tor Project blog
量子位
阮一峰的网络日志
阮一峰的网络日志
S
SegmentFault 最新的问题
小众软件
小众软件
博客园 - 叶小钗
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Blog — PlanetScale
Blog — PlanetScale
H
Help Net Security
Y
Y Combinator Blog
N
News | PayPal Newsroom
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
T
Tenable Blog
Scott Helme
Scott Helme
G
GRAHAM CLULEY
大猫的无限游戏
大猫的无限游戏
aimingoo的专栏
aimingoo的专栏
IT之家
IT之家
Schneier on Security
Schneier on Security
F
Fortinet All Blogs
Martin Fowler
Martin Fowler
T
Threat Research - Cisco Blogs
博客园 - 司徒正美
Application and Cybersecurity Blog
Application and Cybersecurity Blog
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
Attack and Defense Labs
Attack and Defense Labs
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
The Last Watchdog
The Last Watchdog
L
LangChain Blog
C
Check Point Blog
Google Online Security Blog
Google Online Security Blog
V
Visual Studio Blog
Latest news
Latest news

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%
GitHub - combinatrix-ai/agenv: nvm / pyenv for AI coding agents
h_mirin · 2026-04-28 · via Hacker News: Show HN

Environment manager for AI coding agents — like nvm or pyenv, but for agent accounts, config, and saved runtime args.

agenv installs codex, claude, and gemini into isolated profiles and lets you pick which profile runs by default, globally or per project. Each profile has its own agent binary and its own agent home directory, so auth, MCP servers, permissions, and history never bleed across profiles.

Image

Install

npm install -g @combinatrix/agenv

Common Workflows

Tip

agenv (no args) opens the TUI shown below, which covers daily use cases.

$ agenv
agenv — Agent Environment Manager
╭───────────────────────────────────────────────────────────────────────────────────────╮
│     Name            Agent             Args            Env             Default         │
│ 1 > claude-home     claude@2.1.119    —               —               claude          │
│ 2   codex-home      codex@0.125.0     --full-auto     —                               │
│ 3   codex-work †    codex@0.125.0     —               OPENAI_API_KEY  codex, default  │
│ 4   gemini-family   gemini@0.39.1     —               —               gemini          │
│     + Create new profile                                                              │
╰───────────────────────────────────────────────────────────────────────────────────────╯
† Project config at /path/to/project/.agenv.json overrides here — press d for detail
1-9 run; n new; e edit; x remove; d detail; q quit

Install and run

agenv install claude     # installs claude into a profile named "claude"
agenv run                # launches it (single installed profile → auto-selected)

Separate work and personal accounts

agenv install claude work
agenv install claude personal

agenv run work
agenv run personal

Set a global / local default

agenv install gemini work
agenv default global work
agenv run  # → work
cd some/repo
agenv run  # → work

agenv install gemini personal
agenv default local personal     # writes ./.agenv.json
agenv run  # → personal
cd another/repo
agenv run  # → work

Configure args and env on a profile

agenv edit global work --env HTTPS_PROXY=http://proxy:8080  # set env var
agenv edit global work -- --model gpt-5                     # set saved args
agenv edit local work --env-file .env                       # bulk-load from .env

When both local and global set values for the same profile:

  • env: project entries override global entries with the same key; non-overlapping keys from both are kept
  • args: project args fully replace global args (no merging)
agenv edit global work --env APP_FLAG=g --env DEBUG=1 -- --model gpt-5
agenv edit local  work --env APP_FLAG=l -- --temperature 0.9
agenv run work  # → env: APP_FLAG=l, DEBUG=1; args: --temperature 0.9

Env and args can also come from the shell, agenv run --env, runtime --, --yolo, and auto-injected ones. For the full precedence order, see env precedence and args composition in docs/profiles.md.

Use multiple agents

agenv install codex
agenv install gemini gemini-private
agenv install gemini gemini-work

agenv default global codex                       # overall default
agenv default global gemini-private --for gemini  # default for `agenv run gemini`

cd some/repo
agenv default local gemini-work --for gemini      # project-local override

agenv run         # → codex
agenv run gemini  # → gemini-work
cd another/repo
agenv run gemini  # → gemini-private

Update or pin an agent version

agenv run checks the registry before launching and offers to update outdated agents interactively. Pin a profile to skip those prompts, or pass --no-update-check (or set AGENV_NO_UPDATE_CHECK=1) to skip the check entirely.

agenv install codex work --pin 0.1.2     # install pinned to version 0.1.2
agenv update work --pin 0.1.5            # move the pin to version 0.1.5
agenv update work                        # update to latest version and remove the pin

Clone, remove

agenv clone work work-experimental       # copy install + saved args/env into a new isolated profile
agenv remove work-experimental           # delete the profile directory

Updating agenv itself

When a newer agenv release is published, agenv prints a one-line notice on stderr before each command. Update with whichever package manager you used to install agenv (e.g. npm install -g @combinatrix/agenv@latest). Suppress the notice with AGENV_NO_SELF_UPDATE_CHECK=1.

Supported Agents

Agent Package --yolo adds
codex @openai/codex --full-auto
claude @anthropic-ai/claude-code --dangerously-skip-permissions
gemini @google/gemini-cli --yolo

Each agent has its own flag for bypassing approval / permission prompts. Pass --yolo to agenv run (or agenv install) and agenv appends the right flag for that agent — so you don't have to remember which one is which.

CLI Reference

agenv install <agent> [profile] [options] [-- <saved_args...>]
agenv update  <profile> [--pin <v>]
agenv remove  <profile>
agenv clone   <source> <target>
agenv default <local|global> <profile> [--for <agent>]
agenv edit    <local|global> <profile> [options] [-- <saved_args...>]
agenv list    [--json]
agenv show    [profile] [--json] [--reveal]
agenv run     [selector] [--profile <p> | --agent <a>] [--tui] [--yolo] [--env KEY=VALUE] [--dry-run] [--debug] [--no-update-check] [-- <agent_args...>]

Aliases: i (install), up (update), rm (remove), ls (list).

Run agenv <command> --help for details on each command. The full reference lives in the CLI docs.

Selector Resolution

agenv run picks a profile based on its argument:

Command Resolves to
agenv run default profile
agenv run <agent> agent-specific default
agenv run <profile> named profile
agenv run --profile <profile> explicit profile
agenv run --agent <agent> explicit agent default

Tiebreakers:

  • agenv run (no selector): if no defaultProfile is set, use the sole installed profile when exactly one exists.
  • agenv run <agent>: try agentDefaults.<agent>, then defaultProfile (only if it points to a profile of that agent), then the sole installed profile of that agent. Otherwise error.

Defaults are read from the nearest .agenv.json walking up from the cwd, falling back to $AGENV_HOME/.agenv.json.

Inspect a Profile

agenv show work
agenv show work --json
agenv show work --reveal

agenv show redacts env values for secret-shaped keys. Use --reveal to print them.

Diagnose

agenv ls                          # the `default` column shows what `agenv run` and `agenv run <agent>` resolve to here
agenv run --dry-run               # print resolved profile, args, env without launching
agenv run --debug                 # debug mode: resolution trace + error stack traces + update-check warnings
AGENV_DEBUG=1 agenv run work      # equivalent to --debug

Storage

~/.agenv/
├── .agenv.json
└── agents/
    ├── work/
    │   ├── agent/
    │   ├── config/
    │   └── profile.json
    └── personal/
        ├── agent/
        ├── config/
        └── profile.json

Override the root with $AGENV_HOME.

Example .agenv.json

{
  "defaultProfile": "work",
  "agentDefaults": {
    "codex": "work"
  },
  "profiles": {
    "work": {
      "args": "--model gpt-5",
      "env": {
        "DEBUG": "1"
      }
    }
  }
}

More Details