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

S
Schneier on Security
F
Fortinet All Blogs
博客园_首页
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
D
DataBreaches.Net
aimingoo的专栏
aimingoo的专栏
爱范儿
爱范儿
B
Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
阮一峰的网络日志
阮一峰的网络日志
P
Proofpoint News Feed
D
Docker
Engineering at Meta
Engineering at Meta
大猫的无限游戏
大猫的无限游戏
The Cloudflare Blog
罗磊的独立博客
云风的 BLOG
云风的 BLOG
Microsoft Azure Blog
Microsoft Azure Blog
T
The Exploit Database - CXSecurity.com
博客园 - 三生石上(FineUI控件)
量子位
The Last Watchdog
The Last Watchdog
MyScale Blog
MyScale 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
T
The Blog of Author Tim Ferriss
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
小众软件
小众软件
Cloudbric
Cloudbric
博客园 - 司徒正美
H
Help Net Security
人人都是产品经理
人人都是产品经理
Application and Cybersecurity Blog
Application and Cybersecurity Blog
L
LangChain Blog
Latest news
Latest news
M
MIT News - Artificial intelligence
T
Threat Research - Cisco Blogs
博客园 - Franky
S
Security Affairs
W
WeLiveSecurity
F
Full Disclosure
Know Your Adversary
Know Your Adversary
Google DeepMind News
Google DeepMind News
The Hacker News
The Hacker News
Cyberwarzone
Cyberwarzone
美团技术团队
PCI Perspectives
PCI Perspectives
C
Check Point Blog
Spread Privacy
Spread Privacy

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 - chojs23/lazyagent: TUI for watching all your AI coding agents(claude, codex and opencode)
neozz · 2026-04-23 · via Hacker News: Show HN

lazyagent

lazyagent is a terminal TUI app for watching what ai agents are doing. You can inspect projects, sessions, agents, subagents, tools, prompts and outputs in one place.

The TUI is built for day to day observability. You can see which session belongs to which project, which agent or subagent is active, what tool ran, and what happened next.

It also helps you check whether each agent is doing the work that fits its role, so it is easier to spot when a run goes off track.

lazyagent

You can also check token usage breakdowns for each session, so you can see how many tokens were spent on the model, how many were saved by cache reuse, and how many were spent on cache creation.

Features

  • Multi-runtime support -- Support Claude, Codex, and OpenCode sessions
  • Subagent hierarchy -- See which agents spawned which subagents, displayed as a visual tree.
  • Event stream with filtering -- Filter events by type (tool, user, session, system, code) or by agent. Full-text search across event payloads.
  • Syntax and diff highlighting -- Code blocks and diffs in event payloads are syntax-highlighted for readability.

lazyagent is still early in development, some breaking changes may happen.

Installation

NPM

npm install -g @chojs23/lazyagent

Or run without installing:

npx @chojs23/lazyagent

Homebrew

Install from the Homebrew tap with:

brew tap chojs23/homebrew-tap
brew install --cask lazyagent

Go install

go install github.com/chojs23/lazyagent/cmd/lazyagent@latest

Nix flake

These commands build the repository through its flake. The binary version comes from the repo VERSION file, while the exact source you install depends on the ref you choose.

Run directly:

nix run github:chojs23/lazyagent

Install into your profile:

nix profile install github:chojs23/lazyagent

Pin a specific release tag if you want that exact release through Nix:

nix run github:chojs23/lazyagent/v0.2.0
nix profile install github:chojs23/lazyagent/v0.2.0

The default github:chojs23/lazyagent form follows the default branch, so use a tag ref when you want a fixed release.

Release install script

Install the latest release asset into ~/.local/bin:

curl -fsSL https://raw.githubusercontent.com/chojs23/lazyagent/main/scripts/install.sh | sh

Install a specific release into a custom directory:

curl -fsSL https://raw.githubusercontent.com/chojs23/lazyagent/main/scripts/install.sh | \
  sh -s -- --version v0.2.0 --bin-dir /usr/local/bin

Installer options:

  • --version <tag> or VERSION=<tag> to install a specific release
  • --bin-dir <dir> or BIN_DIR=<dir> to choose the install directory

Build from source

go build -o ./bin/lazyagent ./cmd/lazyagent

Claude, Codex, and OpenCode setup

lazyagent is usually used through runtime hooks and plugins.

Claude

lazyagent init claude

This updates:

~/.claude/settings.json

It registers lazyagent ingest --runtime claude for these Claude hook events:

  • PreToolUse
  • PostToolUse
  • SessionStart
  • SessionEnd
  • Stop
  • SubagentStop
  • Notification
  • UserPromptSubmit

Existing non lazyagent hooks are preserved.

Codex

lazyagent init codex

This updates:

~/.codex/config.toml
~/.codex/hooks.json

It enables features.codex_hooks = true and registers lazyagent ingest --runtime codex --quiet for supported Codex hook events.

OpenCode

lazyagent init opencode

This writes the OpenCode plugin to:

~/.config/opencode/plugins/lazyagent.ts

Set an environment variable for the plugin if you want:

  • LAZYAGENT_BIN to point at a specific lazyagent binary

Build and test

Build the Go binary:

go build -o ./bin/lazyagent ./cmd/lazyagent

Run the Go test suite:

go test ./...

If you need to work on the maintained OpenCode plugin source directly:

cd plugins/opencode
npm install
npm run build

The shipping plugin is embedded into the Go binary, so keep the maintained source and embedded copy in sync when you change it.

TUI layout

The interface is divided into five panes.

  1. Projects -- Lists all projects with their root sessions. Each session shows a runtime indicator: [C] for Claude, [X] for Codex, [O] for OpenCode. Active sessions display an animated spinner.
  2. Session summary -- Shows metadata for the selected session: runtime, project path, session ID, start time, last event time, and event/agent counts.
  3. Agents / subagents -- Displays the agent tree for the selected session. Active agents show a spinner.
  4. Events -- List of events for the selected session. Each row shows the event type, tool name, agent ID, and timestamp.
  5. Event detail -- Full inspection of the selected event. Shows status indicators, metadata fields, and the event payload.

Keybindings

Main keys:

  • tab, shift+tab move between panes
  • 1, 2, 3, 4, 5 jump to a specific pane
  • j, k move through lists
  • g, G jump to top or bottom
  • ctrl+u, ctrl+d move by half a page
  • enter, space select the current item
  • / opens search
  • t, shift+t cycles event type filters
  • b opens the token/tool usage overlay for the selected session
  • a clears the current agent filter when the agent pane is focused
  • d deletes the selected project or session from the projects pane
  • D clears events for the selected session tree
  • F toggles auto follow in the events pane
  • r refreshes data
  • ? toggles help
  • q quits
  • Hold shift while dragging to select and copy text

When a non panic internal app error happens, the TUI shows a small toast in the bottom right for about 5 seconds while also writing the error to lazyagent.log.

Detail pane keys:

  • J toggles raw JSON
  • e expands long content blocks

Usage

Run the lazyagent:

lazyagent

Project grouping is automatic. lazyagent first tries to match sessions by working directory such as cwd or project_dir, then falls back to transcript path information when needed. That means Claude, Codex, and OpenCode sessions from the same worktree are usually grouped under the same project in the TUI.

Filtering and search

  • Type filter -- Press t to cycle through: All, User, Message, Code, System, Tool, Session.
  • Agent filter -- Select an agent in the agents pane to show only that agent's events. Press a to clear the filter and show all agents again.
  • Text search -- Press / and type a pattern to search event payloads.

Token usage overlay

Press b on a selected session to open the token usage overlay.

The overlay is designed as a compact session audit sheet instead of a raw dashboard. It keeps the main TUI visible underneath and groups the data into a few ranked sections:

  • Session -- Runtime, session label, and project context for the selected run.

  • Overview -- Cost, model calls, direct input, total input, output, and cache numbers.

  • Signals -- Derived hints such as cache share, output ratio, top model, top tool, and top command.

  • Model Ledger -- Ranked per-model usage with share, calls, total input, and output.

  • Execution Mix -- Ranked tools and commands used in the session.

  • Model Calls -- Counted model usage events for the selected runtime.

  • Direct Input -- Non-cache input tokens only.

  • Total Input -- Direct Input + Cache Read + Cache Write.

  • Cache Read -- Input tokens served from cache reuse.

  • Cache Write -- Tokens spent creating cacheable prompt state.

  • Model total in -- The per-model version of Total Input, so it includes direct input plus cache tokens.

  • Tool Usage -- Which tools were called in the session and how many times each tool ran.

  • Shell Commands -- Which shell commands were detected from Bash or shell tool invocations and how many times each command appeared.

Event types

lazyagent tracks the following event types depending on the runtime.

Type Subtypes Description
User UserPromptSubmit User sent a prompt
Message -- AI response output
Code -- Code-changing actions
System Stop, SubagentStop, StopFailure, Notification, SessionStatus, PermissionReply, TodoUpdate, CommandExecuted, FileEdited, and others Agent stop, status, permission, todo, command, and other system events
Tool PreToolUse, PostToolUse, PostToolUseFailure Tool execution start, success, or failure
Session SessionStart, SessionEnd, SessionUpdated, SessionDiff Session lifecycle

When a PreToolUse or PostToolUse event involves the Agent tool, lazyagent automatically creates a subagent entry and links subsequent events to it.

Commands

lazyagent init <claude|opencode|codex>

Install or refresh runtime hooks and plugins.

Examples:

lazyagent init claude
lazyagent init codex
lazyagent init opencode

lazyagent ingest

Read runtime event payloads from stdin and store them in the database.

This command is normally called by hooks and plugins, not manually.

Examples:

lazyagent ingest --runtime claude
lazyagent ingest --runtime opencode
lazyagent ingest --runtime codex --quiet

lazyagent health

Check whether the SQLite database can be opened.

lazyagent health

lazyagent version

Show build and release metadata.

lazyagent version
lazyagent version --json
lazyagent --version

DB and log information

By default, lazyagent stores data under:

~/.lazyagent

Default database path(SQLite):

~/.lazyagent/observe.db

Default log path:

~/.lazyagent/lazyagent.log

Supported environment variables:

  • LAZYAGENT_DATA_DIR
    • overrides the base data directory
  • LAZYAGENT_DB_PATH
    • overrides the database path
    • when set, its parent directory also becomes the active data directory for logs

The TUI refresh interval defaults to 1 second.

Contribution

Bug reports, feature requests, and pull requests are all welcome.

Please see CONTRIBUTING.md for contribution guidance.

License

MIT