Загрузка видео...

Не удалось загрузить видео

На главную

The Linux tree command... but on steroids? 🤯 🌲 lstr — A minimalist directory tree viewer with an optional TUI mode 💯 Git status, icons, smart sorting & .gitignore support 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #cli #linux #terminal #productivity #devtools

orhundev's profile picture

Orhun Parmaksız 👾

7,153 subscribers

13,048 просмотров • 5 месяцев назад •via X (Twitter)

#rustlang#ratatui
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Omg I can finally organize my downloads folder 😍 🌰 Hazelnut — A file organizer TUI inspired by Hazel ⚡ Watch folders, define rules (move/rename/archive/run) & let the daemon handle everything. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #automation #productivity #files #cli #linux #terminal
0:23

Omg I can finally organize my downloads folder 😍 🌰 Hazelnut — A file organizer TUI inspired by Hazel ⚡ Watch folders, define rules (move/rename/archive/run) & let the daemon handle everything. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #automation #productivity #files #cli #linux #terminal

Orhun Parmaksız 👾

19,735 просмотров • 5 месяцев назад

Wanna quickly edit files in the terminal? Say less 🤝 🌀 lazyide — A lightweight TUI IDE inspired by lazygit 💯 View, edit, navigate & copy/paste instantly. 🎨 Supports file tree, tabbed editor, LSP & themes! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #ide #editor #terminal #lsp #devtools
0:23

Wanna quickly edit files in the terminal? Say less 🤝 🌀 lazyide — A lightweight TUI IDE inspired by lazygit 💯 View, edit, navigate & copy/paste instantly. 🎨 Supports file tree, tabbed editor, LSP & themes! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #ide #editor #terminal #lsp #devtools

Orhun Parmaksız 👾

11,309 просмотров • 5 месяцев назад

The legendary Dos Navigator (1991) is back 🥹 📂 rdn — Rust Dos Navigator terminal file manager 💯 Two-panel layout, DOS accurate colors, built-in viewer & even Tetris 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #dos #file #manager #devtools #terminal
1:22

The legendary Dos Navigator (1991) is back 🥹 📂 rdn — Rust Dos Navigator terminal file manager 💯 Two-panel layout, DOS accurate colors, built-in viewer & even Tetris 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #dos #file #manager #devtools #terminal

Orhun Parmaksız 👾

10,995 просмотров • 4 месяцев назад

Wow this will make code review easy! 🔥 🧩 oyo — A special diff viewer with step-through mode. 👀 Watch the diff evolve step by step. 💯 Supports syntax highlighting, git blame, smooth animations & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #git #diff #codereview #terminal #devtools
0:23

Wow this will make code review easy! 🔥 🧩 oyo — A special diff viewer with step-through mode. 👀 Watch the diff evolve step by step. 💯 Supports syntax highlighting, git blame, smooth animations & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #git #diff #codereview #terminal #devtools

Orhun Parmaksız 👾

17,915 просмотров • 6 месяцев назад

This might be the TUI of the year ⭐ 🎬 gitlogue — A cinematic Git commit replay tool for the terminal. ⚡ Watch commits unfold with typing animations, syntax highlighting and a live-updating file tree. 🤯 Watch your repo code itself. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #git #commits #replay #terminal #screensaver
2:40

This might be the TUI of the year ⭐ 🎬 gitlogue — A cinematic Git commit replay tool for the terminal. ⚡ Watch commits unfold with typing animations, syntax highlighting and a live-updating file tree. 🤯 Watch your repo code itself. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #git #commits #replay #terminal #screensaver

Orhun Parmaksız 👾

32,130 просмотров • 8 месяцев назад

New configuration manager in town! 🚨🐁 🌀 dotstate — A modern & secure dotfile manager TUI 💯 Sync configs via GitHub, manage profiles, auto-handle symlinks and keep backups. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: ➡️ Website: #rustlang #ratatui #tui #dotfiles #terminal #devtools #productivity #opensource
0:37

New configuration manager in town! 🚨🐁 🌀 dotstate — A modern & secure dotfile manager TUI 💯 Sync configs via GitHub, manage profiles, auto-handle symlinks and keep backups. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: ➡️ Website: #rustlang #ratatui #tui #dotfiles #terminal #devtools #productivity #opensource

Orhun Parmaksız 👾

11,924 просмотров • 6 месяцев назад

Bash just got a huge upgrade! 🤯 🪽 flyline — A modern replacement for Bash's command-line editor 💯 IntelliSense-style suggestions, fuzzy history, mouse support, animated prompts, AI-assisted commands & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #bash #terminal #shell #cli #opensource
0:56

Bash just got a huge upgrade! 🤯 🪽 flyline — A modern replacement for Bash's command-line editor 💯 IntelliSense-style suggestions, fuzzy history, mouse support, animated prompts, AI-assisted commands & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #bash #terminal #shell #cli #opensource

Orhun Parmaksız 👾

81,557 просмотров • 26 дней назад

Ever felt lost in a Markdown file? It's not happening again! 🌳 treemd — An interactive Markdown navigator with a collapsible heading tree. 💯 Read Markdown like code! 🧭 Dual-pane interface with vim-style navigation, live search & synchronized scrolling. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #markdown #reader #cli #terminal
0:26

Ever felt lost in a Markdown file? It's not happening again! 🌳 treemd — An interactive Markdown navigator with a collapsible heading tree. 💯 Read Markdown like code! 🧭 Dual-pane interface with vim-style navigation, live search & synchronized scrolling. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #markdown #reader #cli #terminal

Orhun Parmaksız 👾

56,216 просмотров • 8 месяцев назад

Finally, I can see what's draining my battery easily 🔥 🔋 jolt — A battery & energy monitor TUI 💯 See battery health, system power draw & energy-hungry processes ⚙️ Runs on MacOS & Linux 📊 Supports history graphs, themes, bg daemon. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #terminal #battery #power #monitor
0:20

Finally, I can see what's draining my battery easily 🔥 🔋 jolt — A battery & energy monitor TUI 💯 See battery health, system power draw & energy-hungry processes ⚙️ Runs on MacOS & Linux 📊 Supports history graphs, themes, bg daemon. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #terminal #battery #power #monitor

Orhun Parmaksız 👾

27,666 просмотров • 5 месяцев назад

Wow, this is a gem 💯 🕵️ proxelar — Intercept HTTP traffic from the terminal 🔥 MITM proxy with TUI, web UI & Lua scripting ⚡ Inspect, modify, mock requests in real time with full HTTPS interception 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #networking #proxy #security #http #terminal
0:43

Wow, this is a gem 💯 🕵️ proxelar — Intercept HTTP traffic from the terminal 🔥 MITM proxy with TUI, web UI & Lua scripting ⚡ Inspect, modify, mock requests in real time with full HTTPS interception 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #networking #proxy #security #http #terminal

Orhun Parmaksız 👾

21,299 просмотров • 3 месяцев назад

Ayo this looks/sounds fire 🔥🤖 🎧 concertus — A plug-and-play TUI music player for local libraries. 🌊 Supports MP3, FLAC, OGG, WAV & more with waveform visualization. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #music #audioplayer #player #terminal
0:33

Ayo this looks/sounds fire 🔥🤖 🎧 concertus — A plug-and-play TUI music player for local libraries. 🌊 Supports MP3, FLAC, OGG, WAV & more with waveform visualization. 🦀 Written in Rust & built with Ratatui ⭐ GitHub: #rustlang #ratatui #tui #music #audioplayer #player #terminal

Orhun Parmaksız 👾

33,395 просмотров • 7 месяцев назад

I'm super excited to announce my latest project! 📢 🎸 Tuitar — A guitar training tool & DIY kit 🎛️ ⚡ Runs in the terminal or standalone on ESP32. 🎵 Real-time tuning, fretboard tracking, signal analysis & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: (Tuitar) #rustlang #ratatui #tui #guitar #embedded #terminal #diy #esp32 #hardware #opensource
0:49

I'm super excited to announce my latest project! 📢 🎸 Tuitar — A guitar training tool & DIY kit 🎛️ ⚡ Runs in the terminal or standalone on ESP32. 🎵 Real-time tuning, fretboard tracking, signal analysis & more! 🦀 Written in Rust & built with Ratatui ⭐ GitHub: (Tuitar) #rustlang #ratatui #tui #guitar #embedded #terminal #diy #esp32 #hardware #opensource

Orhun Parmaksız 👾

21,484 просмотров • 7 месяцев назад

SPECEXAI 🚨: Grok Build, xAI's new coding desktop app, is being prepared for release on macOS, Windows, and Linux! > It will support planning mode, Plugins, Skills, and MCPs. > Will be able to work with the Git tree, spawn dev servers, and work with a built-in browser. SOON!? 👀
0:27

SPECEXAI 🚨: Grok Build, xAI's new coding desktop app, is being prepared for release on macOS, Windows, and Linux! > It will support planning mode, Plugins, Skills, and MCPs. > Will be able to work with the Git tree, spawn dev servers, and work with a built-in browser. SOON!? 👀

🚨 AI News | TestingCatalog

332,110 просмотров • 2 месяцев назад

Ghostty on both macOS and Linux now support marking a terminal as read-only. In this mode, you can still search, scroll, and select text, but no input is sent to the running program. If you have something scary you really don't want to mess up, this is perfect! You can toggle this with the command palette, a keybinding (bind "toggle_readonly"), the context menu, or the main menu.
0:20

Ghostty on both macOS and Linux now support marking a terminal as read-only. In this mode, you can still search, scroll, and select text, but no input is sent to the running program. If you have something scary you really don't want to mess up, this is perfect! You can toggle this with the command palette, a keybinding (bind "toggle_readonly"), the context menu, or the main menu.

Mitchell Hashimoto

89,086 просмотров • 7 месяцев назад

TheSimsTree Update 💚 🌍 New world dropdown with icons from The Sims 4! 📍 Select your Sim’s location in a few clicks. 🔎 Built-in search - start typing, and we’ll suggest the right city. 👩🏼‍🦰 Avatar update: tap an avatar to open a full gallery in a carousel. ⚙️ Fixes & improvements: ✅ Fixed pet last name requirement. ✅ Custom traits now display correctly on public trees. ✅ Expanded trait lists & added tooltips in tree styling. 📖 Full guide now in the left menu. ⭐️ The dropdown menu feature is currently in early access for Pro users and only includes cities from The Sims 4, but we plan to add locations from previous Sims games as well. Thanks for your support! 💚 #thesimstree #thesimstreeupd #thesims
0:22

TheSimsTree Update 💚 🌍 New world dropdown with icons from The Sims 4! 📍 Select your Sim’s location in a few clicks. 🔎 Built-in search - start typing, and we’ll suggest the right city. 👩🏼‍🦰 Avatar update: tap an avatar to open a full gallery in a carousel. ⚙️ Fixes & improvements: ✅ Fixed pet last name requirement. ✅ Custom traits now display correctly on public trees. ✅ Expanded trait lists & added tooltips in tree styling. 📖 Full guide now in the left menu. ⭐️ The dropdown menu feature is currently in early access for Pro users and only includes cities from The Sims 4, but we plan to add locations from previous Sims games as well. Thanks for your support! 💚 #thesimstree #thesimstreeupd #thesims

TheSimsTree

16,435 просмотров • 1 год назад

Deborah has been scammed!!! While scrolling on Youtube, Deborah saw an advert, Go from beginner to master in coding in just 2 months. It has been her life long dream to become a developer. She paid $150 to learn web 3 development. Fast forward 6 months later, Deborah cannot write a simple smart contract Trust me you don't want to be like Deborah KRNL Labs is your solution. "From Setup to Success: KRNL’s CLI Makes Web3 Dev a Breeze 🔧" 🔗 First, what's the CLI? ➻ It's almost like a magic wand for your computer that lets you deploy, manage, and install KRNL's(KRNL Labs )tools 🛠 by typing commands. Your terminal is all of what is needed. There is not any fancy software that is required. ➻ Brew install krnl-cli goes after type brew tap krnl-labs/krnl. Homebrew gets KRNL on your Mac using this setup. For Windows or Linux users, check the guide about alternatives. Coding is just like downloading a new game instead. ➻ See if it works via running krnl help. This shows every command you can utilize like a toolbox cheat sheet. Brew upgrade krnl-cli updates the CLI you use. Updating your phone is similar to that. It gives access to all of the latest features. After installing, restart your terminal to avoid errors like “forge not found.” This ensures smooth communication. That folder 📁 thus created holds smart contracts with configurations, and other necessities. It is in the same way as receiving a pre-built LEGO set. The set may help you start your project. ➻ Then, deploy your Token Authority (TA) and smart contract 📝. The CLI guides you through registering them on the KRNL's registry, making your dApp part of their ecosystem. Think of it as registering your game online so others can play it. Dev testrun ⚒ ➻ For example, deploy your TA with krnl deploy-ta --network sepolia --private-key . This sets up a secure identity for your kernels. Then, deploy your main contract with krnl deploy-contract --network sepolia --private-key . Finally, register everything with krnl register --network sepolia --private-key --ta-address --contract-address . It's like setting up a shop online, but for blockchain. #GalxeStarboard #KRNL
0:32

Deborah has been scammed!!! While scrolling on Youtube, Deborah saw an advert, Go from beginner to master in coding in just 2 months. It has been her life long dream to become a developer. She paid $150 to learn web 3 development. Fast forward 6 months later, Deborah cannot write a simple smart contract Trust me you don't want to be like Deborah KRNL Labs is your solution. "From Setup to Success: KRNL’s CLI Makes Web3 Dev a Breeze 🔧" 🔗 First, what's the CLI? ➻ It's almost like a magic wand for your computer that lets you deploy, manage, and install KRNL's(KRNL Labs )tools 🛠 by typing commands. Your terminal is all of what is needed. There is not any fancy software that is required. ➻ Brew install krnl-cli goes after type brew tap krnl-labs/krnl. Homebrew gets KRNL on your Mac using this setup. For Windows or Linux users, check the guide about alternatives. Coding is just like downloading a new game instead. ➻ See if it works via running krnl help. This shows every command you can utilize like a toolbox cheat sheet. Brew upgrade krnl-cli updates the CLI you use. Updating your phone is similar to that. It gives access to all of the latest features. After installing, restart your terminal to avoid errors like “forge not found.” This ensures smooth communication. That folder 📁 thus created holds smart contracts with configurations, and other necessities. It is in the same way as receiving a pre-built LEGO set. The set may help you start your project. ➻ Then, deploy your Token Authority (TA) and smart contract 📝. The CLI guides you through registering them on the KRNL's registry, making your dApp part of their ecosystem. Think of it as registering your game online so others can play it. Dev testrun ⚒ ➻ For example, deploy your TA with krnl deploy-ta --network sepolia --private-key . This sets up a secure identity for your kernels. Then, deploy your main contract with krnl deploy-contract --network sepolia --private-key . Finally, register everything with krnl register --network sepolia --private-key --ta-address --contract-address . It's like setting up a shop online, but for blockchain. #GalxeStarboard #KRNL

Deekruz🦋|🅰️|₿|

25,993 просмотров • 11 месяцев назад

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.
0:49

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.

Grok News

69,692 просмотров • 1 день назад

if you are using someone else's garbage saas ai design review product, stop... all of if it is waste of time and i'll give you something better for free that runs with whatever analysis tools you want. altium-cruncher 2026.6.7 public release kicad-cruncher 2026.6.7 public release altium-cruncher is cli tool built on the altium-monkey library. (kicad-cruncher is built on kicad-monkey) here we show the "design_review" (dr) command dr converts an altium project into a simple graph-spatial-topological format specifical design for llm's - json netlist with links with detail indexes into the schematic SVG elements/groups - enriched pcb SVG heavily decorated with links back to the the json graph - all schematic notes in json form - SVG schematic/pcb elements are heirachically grouped w/ tags for the llm to build its own internal map of subcircuits with linkage to copper artwork subsections. - full part parameter linkage - an .md with a guide for codex/claude on how to step through the eviscerated project. - bonus: schdoc and pcbdoc in a raw json serialized format (what altium uses internally but doesnt give you from teh gui). this format is the literal json form of the altium format essentially all of the resolved schematic graph, physical topology, layer stack information and metadata to do make best use of current frontier and local llm techbology it actually was an accidental discovery. better than a netlist. no vendor lock-in. gives you some help without pretending its 100% . no need to waste tokens on full image processing,etc. this dataset works better, is simpler, and compatible with local llms. can help save some time and give you another set of eyes before a release. works on win/mac/linux gratis!
1:27

if you are using someone else's garbage saas ai design review product, stop... all of if it is waste of time and i'll give you something better for free that runs with whatever analysis tools you want. altium-cruncher 2026.6.7 public release kicad-cruncher 2026.6.7 public release altium-cruncher is cli tool built on the altium-monkey library. (kicad-cruncher is built on kicad-monkey) here we show the "design_review" (dr) command dr converts an altium project into a simple graph-spatial-topological format specifical design for llm's - json netlist with links with detail indexes into the schematic SVG elements/groups - enriched pcb SVG heavily decorated with links back to the the json graph - all schematic notes in json form - SVG schematic/pcb elements are heirachically grouped w/ tags for the llm to build its own internal map of subcircuits with linkage to copper artwork subsections. - full part parameter linkage - an .md with a guide for codex/claude on how to step through the eviscerated project. - bonus: schdoc and pcbdoc in a raw json serialized format (what altium uses internally but doesnt give you from teh gui). this format is the literal json form of the altium format essentially all of the resolved schematic graph, physical topology, layer stack information and metadata to do make best use of current frontier and local llm techbology it actually was an accidental discovery. better than a netlist. no vendor lock-in. gives you some help without pretending its 100% . no need to waste tokens on full image processing,etc. this dataset works better, is simpler, and compatible with local llms. can help save some time and give you another set of eyes before a release. works on win/mac/linux gratis!

Eli Hughes

16,263 просмотров • 1 месяц назад

I’ve been using quite heavily over the past few days, alongside Claude Code on its other platforms. The first thing that caught my attention was the “Research preview” label, which likely indicates that this experience is still in an experimental phase. That said, compared to Claude Desktop in Code mode, the web version feels slightly more advanced. You can select branches, and previous sessions display clear status icons, which is a small but very meaningful UX improvement. My impression: I liked it much more than Claude Desktop, especially the use of branches, which is essential when working with agents outside a local environment. What’s missing: The sandbox is very limited. It only allows installing packages from PyPI (maybe npm as well, but I didn’t test it). CLI tools are essential in these environments. I tried installing GitHub CLI (gh), but it failed due to network restrictions. Even though I had all the required domains enabled in Claude’s settings, this execution sandbox clearly does not respect that configuration. Another important issue: environment variables added through the UI are not automatically picked up by the sandbox runtime. I had to restart the session for it to recognize the GitHub token I had just added. I also tried installing the Vercel CLI, without success. In the end, Claude usually finds a workaround, but it burns a lot of tokens trying different installation strategies or alternative external calls. What I would add: In the development environment settings, it should be possible to: Configure the sandbox’s network access and define which CLI tools and packages come preinstalled I don’t want to waste tokens installing gh, vercel, wrangler, or supabase CLIs over and over again. These are relatively simple changes that would dramatically improve execution quality and efficiency on the web. If you’re interested in trying I hope this feedback is useful. It’s definitely a tool worth paying attention to, especially since it syncs with Claude Mobile, allowing you to start a task on your phone and continue it later on your computer. Hope this feedback helps Boris Cherny Thariq Anthony Morris ツ
0:26

I’ve been using quite heavily over the past few days, alongside Claude Code on its other platforms. The first thing that caught my attention was the “Research preview” label, which likely indicates that this experience is still in an experimental phase. That said, compared to Claude Desktop in Code mode, the web version feels slightly more advanced. You can select branches, and previous sessions display clear status icons, which is a small but very meaningful UX improvement. My impression: I liked it much more than Claude Desktop, especially the use of branches, which is essential when working with agents outside a local environment. What’s missing: The sandbox is very limited. It only allows installing packages from PyPI (maybe npm as well, but I didn’t test it). CLI tools are essential in these environments. I tried installing GitHub CLI (gh), but it failed due to network restrictions. Even though I had all the required domains enabled in Claude’s settings, this execution sandbox clearly does not respect that configuration. Another important issue: environment variables added through the UI are not automatically picked up by the sandbox runtime. I had to restart the session for it to recognize the GitHub token I had just added. I also tried installing the Vercel CLI, without success. In the end, Claude usually finds a workaround, but it burns a lot of tokens trying different installation strategies or alternative external calls. What I would add: In the development environment settings, it should be possible to: Configure the sandbox’s network access and define which CLI tools and packages come preinstalled I don’t want to waste tokens installing gh, vercel, wrangler, or supabase CLIs over and over again. These are relatively simple changes that would dramatically improve execution quality and efficiency on the web. If you’re interested in trying I hope this feedback is useful. It’s definitely a tool worth paying attention to, especially since it syncs with Claude Mobile, allowing you to start a task on your phone and continue it later on your computer. Hope this feedback helps Boris Cherny Thariq Anthony Morris ツ

Daniel San

11,626 просмотров • 6 месяцев назад

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!
0:29

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Ken Liu

73,840 просмотров • 3 месяцев назад