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

C
Cisco Blogs
Schneier on Security
Schneier on Security
T
Tor Project blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
T
Tenable Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
T
Threat Research - Cisco Blogs
C
CERT Recently Published Vulnerability Notes
Security Latest
Security Latest
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
NISL@THU
NISL@THU
L
Lohrmann on Cybersecurity
Scott Helme
Scott Helme
Webroot Blog
Webroot Blog
Project Zero
Project Zero
Google Online Security Blog
Google Online Security Blog
The Last Watchdog
The Last Watchdog
Spread Privacy
Spread Privacy
Hacker News: Ask HN
Hacker News: Ask HN
PCI Perspectives
PCI Perspectives
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
W
WeLiveSecurity
Attack and Defense Labs
Attack and Defense Labs
D
Darknet – Hacking Tools, Hacker News & Cyber Security
N
News | PayPal Newsroom
Help Net Security
Help Net Security
The Hacker News
The Hacker News
H
Heimdal Security Blog
O
OpenAI News
S
Security @ Cisco Blogs
N
News and Events Feed by Topic
Cyberwarzone
Cyberwarzone
Simon Willison's Weblog
Simon Willison's Weblog
G
GRAHAM CLULEY
www.infosecurity-magazine.com
www.infosecurity-magazine.com
博客园 - 叶小钗
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
Tailwind CSS Blog
大猫的无限游戏
大猫的无限游戏
A
Arctic Wolf
I
Intezer
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
S
Security Affairs
P
Proofpoint News Feed
S
Secure Thoughts
腾讯CDC
Google DeepMind News
Google DeepMind News
量子位
罗磊的独立博客

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
GitHub - shixin-guo/picot: Local Codex-style desktop GUI for the Pi coding agent
shixin · 2026-06-23 · via Show HN

Picot (π-cot(e))

English | 中文

A local desktop GUI for the Pi coding agent. No cloud, no account — runs entirely on your machine.

Picot ships a known-good build of the pi runtime inside the .app bundle, so there's no separate pi install to manage, no PATH shenanigans, and no version drift between Picot and the agent it talks to.

Picot hero


Install

Download from GitHub Releases

You do not need to install the pi CLI separately — Picot bundles its own pi runtime.

macOS unsigned release notice

Picot currently ships macOS builds without Apple Developer ID signing/notarization. Expected Gatekeeper behavior:

"Picot" cannot be opened because the developer cannot be verified.

To allow it:

  1. Drag Picot.app into /Applications
  2. Right-click → Open
  3. If blocked: System Settings → Privacy & Security → Open Anyway

macOS Gatekeeper warning

Then click Done:

Allow app in macOS security settings


What it does

Picot gives you a full visual interface for Pi. Open any project folder, start chatting with the agent, browse sessions and files — no terminal required. Multiple projects run in parallel, each in its own window with its own isolated agent process.


Features

📸 UI Preview

Picot workspace and project UI

💬 Chat

  • Full markdown rendering with syntax-highlighted code blocks
  • Streaming responses with live typing indicator (powered by remend)
  • Image attachments — paste, drag & drop, or button
  • Inline diff viewer for edit tool calls (red/green lines)
  • Tool-call cards and thinking blocks rendered live
  • Copy any message with one click
  • Scroll-to-bottom button with unread indicator
  • Message queuing — type while the agent is working; messages queue as pills and auto-send when ready

🗂️ Multi-Session & Multi-Agent

  • Multiple agents in parallel — each session spawns its own headless pi process; no new OS window, no interruption of running sessions
  • Browse and resume any past session from the sidebar
  • Full-text search across all session history with highlighted snippets
  • Sessions sorted by creation time; live session marked with a green dot
  • Inline session rename, favourites, tags, and filtering

🗃️ Projects & Workspace

  • Multi-project — each project gets its own window, working directory, session history, and agent
  • Shows the current git branch in the project header
  • Open in external editor — launch VS Code, Cursor, or any app directly from Picot
  • Native folder picker to open any project without touching the terminal

📱 Mobile & LAN Access

LAN and mobile access panel

Picot on mobile

  • LAN QR code — scan to open Picot on any device on the same network
  • Mobile-optimised URL handling and App Launcher support (installable as PWA on iOS/Android)

📦 Package Manager

Built-in package manager UI

  • Browse, install, and remove community packages from within the UI
  • Built on top of pi install — no separate package commands needed

💰 Cost & Usage Dashboard

Cost dashboard overview

Per-model and trend breakdown

  • Per-session cost tracking with live token/cost metrics
  • Full cost dashboard with infobar, trends, and per-model breakdown
  • Context window visualiser — click the token pill to see cached tokens, fresh input, and available space

🎨 Themes & Appearance

  • Six built-in themes: Dusk, Dawn, Midnight, Clean, Terracotta, Sage
  • Frosted-glass header and input bar (backdrop-filter: blur)
  • Native macOS title bar overlay integration
  • Window dragging from the header area — feels like a native app

🎤 Voice Input

  • Mic button in the input area using Web Speech API (on-device dictation)
  • Live transcription into the textarea; pulses red while recording

🗄️ File Browser

  • Right sidebar with lazy-loaded file tree
  • Navigate directories, open files natively
  • Drag files onto the input to insert their path

⚙️ Settings & Control

Settings and controls

  • Model picker with search/filter and keyboard support
  • Thinking level toggle (off / low / medium / high)
  • Auto and manual context compaction with status display
  • Push notification toggle
  • Auto-updater — Settings → General → Updates for one-click in-app updates

Pi capabilities integrated

Picot does not re-implement agent logic — it embeds Pi and exposes its runtime capabilities through a native UI.

  • Embedded pi --mode rpc runtime — one managed process per workspace, isolated by project
  • Streaming RPC bridge — token-by-token output, tool-call events, and thinking blocks rendered live
  • Session lifecycle APIs — create, switch, and resume sessions; full per-project history
  • WebSocket broker — multiple UI clients can connect to the same pi process simultaneously
  • Extension compatibility — user extensions from ~/.pi/agent/extensions/ and .pi/extensions/ are auto-loaded
  • Credential reuse — reads Pi's existing ~/.pi/agent/auth.json; no separate login needed

How it works

┌──────────────────────────────────────────────────────┐
│ Picot .app                                       │
│                                                      │
│   Tauri + PiManager (Rust)                           │
│      ├─► spawn  pi --mode rpc  (project A, :3001)    │
│      ├─► spawn  pi --mode rpc  (project B, :3002)    │
│      └─► OS Window per project ──► WebView ──► HTTP  │
│                                                      │
│   resources/                                         │
│      ├─ public/             (frontend)               │
│      ├─ extensions/         (embedded-server.mjs)    │
│      └─ pi/                 (bun-compiled pi binary) │
└──────────────────────────────────────────────────────┘
                       │
                       ▼ reads / writes
              ~/.pi/agent/
                 ├─ sessions/   (chat history)
                 ├─ auth.json   (API keys)
                 └─ settings.json

The embedded pi process loads embedded-server.mjs at startup. That extension owns the HTTP + WebSocket surface the Tauri WebView talks to: static assets, /api/sessions, /api/cost-dashboard, RPC bridge for prompts, etc. Picot's Rust side controls process lifecycle, port allocation, and window management.


Usage

  1. Launch Picot
  2. Click a project bubble or pick a folder
  3. Start chatting — the embedded pi agent starts automatically

Provide your model credentials via pi /login inside any workspace, or by writing ~/.pi/agent/auth.json directly. Picot doesn't manage credentials itself.


Build from source

git clone https://github.com/shixin-guo/picot.git
cd picot
bun install --frozen-lockfile
bun run dev      # fetch embedded pi binary + start tauri dev with hot reload

To make a release build:

bun run build    # downloads embedded pi binary, then runs tauri build

After any changes under src-tauri/:

bun run check:rust   # cargo check + clippy + fmt (fast; no full build needed)

To bump the embedded pi version, edit scripts/pi-version.json, run bun run fetch:pi, smoke-test, and commit.


Upstream

Picot is a maintained fork of Tau, adapted for Pi-first, local development workflows. Key additions:

  • Tauri-native PiManager — spawns one pi --mode rpc process per project window
  • Embedded pi runtime — no separate global install; Picot ships its own binary
  • Multi-session without new windows — headless pi processes, current WebView navigates
  • LAN + mobile access — QR code, PWA support, WebSocket broker for multi-client

License

MIT