Search
1000 results for “cli_ar”
-
[Перевод] Как кодинг-агенты используют инструменты, память и контекст репозитория, чтобы писать код лучше
Это перевод хорошей статьи про базу того, как устроены кодинг-ассистенты и что для них важно: что такое харнесс и харнесс-инжиниринг , в чем разница просто агентной обвязки и кодинговой, что такое компактизация и почему та же самая модель в консольке ощущается мощнее, чем просто в веб-чате. Сильного хардкора и больших откровений в ней нет, но это отличный материал для старта изучения архитектуры кодинг-ассистентов и лучшего понимания, как оно работает внутри.
https://habr.com/ru/articles/1021168/
#harness #харнесс #кодингхарнесс #кодинг #кодинг_ассистенты #aiassisted_development #harness_engineering #claude_code #codex #coding_cli
-
[Перевод] Как кодинг-агенты используют инструменты, память и контекст репозитория, чтобы писать код лучше
Это перевод хорошей статьи про базу того, как устроены кодинг-ассистенты и что для них важно: что такое харнесс и харнесс-инжиниринг , в чем разница просто агентной обвязки и кодинговой, что такое компактизация и почему та же самая модель в консольке ощущается мощнее, чем просто в веб-чате. Сильного хардкора и больших откровений в ней нет, но это отличный материал для старта изучения архитектуры кодинг-ассистентов и лучшего понимания, как оно работает внутри.
https://habr.com/ru/articles/1021168/
#harness #харнесс #кодингхарнесс #кодинг #кодинг_ассистенты #aiassisted_development #harness_engineering #claude_code #codex #coding_cli
-
🤖 b0p is coming soon 😀 #agentique #aiagent #AutonomousAgents #GenAI #LLM #MCP #ArtificialIntelligence #terminal #cli #opensource
-
🤖 b0p is coming soon 😀 #agentique #aiagent #AutonomousAgents #GenAI #LLM #MCP #ArtificialIntelligence #terminal #cli #opensource
-
Data centers are creating ‘heat islands’ and warming the land around them by up to 16 degrees | CNN
The vast data centers that power artificial intelligence guzzle huge amounts of energy but they also have another alarming impact, according to new research. They are creating “heat islands,” warming the land around them by up to 16 degrees Fahrenheit, and making life hotter for more than 340 million people.
-
Data centers are creating ‘heat islands’ and warming the land around them by up to 16 degrees | CNN
The vast data centers that power artificial intelligence guzzle huge amounts of energy but they also have another alarming impact, according to new research. They are creating “heat islands,” warming the land around them by up to 16 degrees Fahrenheit, and making life hotter for more than 340 million people.
-
To my #jfrog bubble: Given #artifactory with a remote (cached) repository. I can see the contents of the remote repo using curl commands, even using jf rt curl commands. But if I try to jf rt search for something, it doesn't return results. For jf rt dl you have to set JFROG_CLI_TRANSITIVE_DOWNLOAD=true. Is there something similar for jf rt search? Or do I have to code up a recursive curl based search?
-
Google Workspace CLI公開、Gmail、Googleドライブ、カレンダー、Chatなどをコマンドラインから操作可能に ―エージェントスキルやMCPサーバーも装備
https://gihyo.jp/article/2026/03/google-workspace-cli?utm_source=feed#gihyo #技術評論社 #gihyo_jp #Google_Workspace_CLI #Rust #Google_Workspace
-
@amalia12 wäre wünschenswert, ja, aber bisher werden Hopepunk und Climate Fiction noch zu stark ignoriert, als dass ich denken würde, dass das demnächst eine größere Sache wird ...
Ich empfehle #Arborealität von Rebecca Campbell - das ist beides, Cli-Fi und Hopepunk ^^
-
@amalia12 wäre wünschenswert, ja, aber bisher werden Hopepunk und Climate Fiction noch zu stark ignoriert, als dass ich denken würde, dass das demnächst eine größere Sache wird ...
Ich empfehle #Arborealität von Rebecca Campbell - das ist beides, Cli-Fi und Hopepunk ^^
-
@amalia12 wäre wünschenswert, ja, aber bisher werden Hopepunk und Climate Fiction noch zu stark ignoriert, als dass ich denken würde, dass das demnächst eine größere Sache wird ...
Ich empfehle #Arborealität von Rebecca Campbell - das ist beides, Cli-Fi und Hopepunk ^^
-
@amalia12 wäre wünschenswert, ja, aber bisher werden Hopepunk und Climate Fiction noch zu stark ignoriert, als dass ich denken würde, dass das demnächst eine größere Sache wird ...
Ich empfehle #Arborealität von Rebecca Campbell - das ist beides, Cli-Fi und Hopepunk ^^
-
@amalia12 wäre wünschenswert, ja, aber bisher werden Hopepunk und Climate Fiction noch zu stark ignoriert, als dass ich denken würde, dass das demnächst eine größere Sache wird ...
Ich empfehle #Arborealität von Rebecca Campbell - das ist beides, Cli-Fi und Hopepunk ^^
-
I am playing for the first time with microcontrollers (#arduino #Raspberry_pi pico).
And I am so confused by the amount of things that are hidden from me...
(when installing deps, writing a program, compiling a program, flashing the program, getting the serial output)When looking online how to things without the arduino-ide, I don't find much.... (i am now using the arduino-cli + a makefile but still a lot of magic in that cli)
Like, sure, I am a microcontroller noob, but not a complete computer noob: where is the tutorial for this kind of audience ? 🙂
Note: I might be so noob that I don't know how/where to find those resources. That's also a strong possibility 😅
-
I am playing for the first time with microcontrollers (#arduino #Raspberry_pi pico).
And I am so confused by the amount of things that are hidden from me...
(when installing deps, writing a program, compiling a program, flashing the program, getting the serial output)When looking online how to things without the arduino-ide, I don't find much.... (i am now using the arduino-cli + a makefile but still a lot of magic in that cli)
Like, sure, I am a microcontroller noob, but not a complete computer noob: where is the tutorial for this kind of audience ? 🙂
Note: I might be so noob that I don't know how/where to find those resources. That's also a strong possibility 😅
-
I am playing for the first time with microcontrollers (#arduino #Raspberry_pi pico).
And I am so confused by the amount of things that are hidden from me...
(when installing deps, writing a program, compiling a program, flashing the program, getting the serial output)When looking online how to things without the arduino-ide, I don't find much.... (i am now using the arduino-cli + a makefile but still a lot of magic in that cli)
Like, sure, I am a microcontroller noob, but not a complete computer noob: where is the tutorial for this kind of audience ? 🙂
Note: I might be so noob that I don't know how/where to find those resources. That's also a strong possibility 😅
-
Really happy with the internal architecture of Fowl's activity visualization: a series of "Message" objects that deterministically build the status state.
Thus I can easily have a "record" and "replay" option https://github.com/magic-wormhole/fowl/blob/main/src/fowl/cli.py#L462 which greatly helps when fiddling with the console visualizations (record one test-case, replay it until the output looks nice).
-
From Obsidian to SiYuan: Why Your Homelab Needs a Database, Not Just Notes 📚💻
As a system analyst, I’ve always been obsessed with structuring chaos. For years, Obsidian was my go-to "Second Brain." It’s powerful, but as my Homelab expanded, I realized I didn't just need notes — I needed a living documentation engine that I could access via web from any device in my network.
I’ve tested the whole spectrum: Docmost, Trillium, and AFFiNE.
- AFFiNE is beautiful (Notion + Miro vibes), but its "infinite canvas" often leads to visual chaos. It's great for sketching a network topology, but terrible when you need to find a specific CLI command via Ctrl+F.
- SiYuan changed the game for me. It’s currently at the heart of my local stack.
Why SiYuan is the "Final Boss" of Self-Hosted Note-taking:
1. Block-Level Granularity (JSON Power): 🧩
Unlike standard Markdown, SiYuan assigns a unique ID to every single paragraph and list item. This allows for transclusion—you can pull a specific VPN setup instruction into five different guides, and when you update the original, it updates everywhere.
2. The SQL Killer-Feature: ⚡
This is where it turns into a professional CMDB (Configuration Management Database). I don't manually track my 50+ Docker containers in a table. I just add custom attributes to my service notes:custom-ip: 192.168.1.10custom-port: 8080
Then, I use a native SQL query on my Dashboard to automatically generate a real-time "Service Matrix." If I change a port in a note, the master table updates itself. No more IP conflicts.
3. Performance & Sovereignty: 🛡️
- Resource Efficiency: While AFFiNE is a bit of a resource hog, SiYuan is incredibly light, idling at just 31MB in my Docker container.
- No Vendor-Lock: Even though it uses.sy(JSON) files for its advanced logic, the export to Markdown is flawless and can be automated via Kernel API.
The Verdict:
If you have 3-4 services, stick to Obsidian. But if you’re running a Proxmox cluster with complex networking, you need a tool that speaks SQL.
Don't let your documentation become legacy hardware. Give it a database-driven brain.
What about you? Are you a "pure Markdown" purist, or have you embraced the power of block-based databases like SiYuan or Notion? How do you track your Homelab inventory?
#SelfHosted #Homelab #SiYuan #Obsidian #KnowledgeManagement #SQL #SysAdmin #Documentation #TechStack #Privacy #OpenSource -
From Obsidian to SiYuan: Why Your Homelab Needs a Database, Not Just Notes 📚💻
As a system analyst, I’ve always been obsessed with structuring chaos. For years, Obsidian was my go-to "Second Brain." It’s powerful, but as my Homelab expanded, I realized I didn't just need notes — I needed a living documentation engine that I could access via web from any device in my network.
I’ve tested the whole spectrum: Docmost, Trillium, and AFFiNE.
- AFFiNE is beautiful (Notion + Miro vibes), but its "infinite canvas" often leads to visual chaos. It's great for sketching a network topology, but terrible when you need to find a specific CLI command via Ctrl+F.
- SiYuan changed the game for me. It’s currently at the heart of my local stack.
Why SiYuan is the "Final Boss" of Self-Hosted Note-taking:
1. Block-Level Granularity (JSON Power): 🧩
Unlike standard Markdown, SiYuan assigns a unique ID to every single paragraph and list item. This allows for transclusion—you can pull a specific VPN setup instruction into five different guides, and when you update the original, it updates everywhere.
2. The SQL Killer-Feature: ⚡
This is where it turns into a professional CMDB (Configuration Management Database). I don't manually track my 50+ Docker containers in a table. I just add custom attributes to my service notes:custom-ip: 192.168.1.10custom-port: 8080
Then, I use a native SQL query on my Dashboard to automatically generate a real-time "Service Matrix." If I change a port in a note, the master table updates itself. No more IP conflicts.
3. Performance & Sovereignty: 🛡️
- Resource Efficiency: While AFFiNE is a bit of a resource hog, SiYuan is incredibly light, idling at just 31MB in my Docker container.
- No Vendor-Lock: Even though it uses.sy(JSON) files for its advanced logic, the export to Markdown is flawless and can be automated via Kernel API.
The Verdict:
If you have 3-4 services, stick to Obsidian. But if you’re running a Proxmox cluster with complex networking, you need a tool that speaks SQL.
Don't let your documentation become legacy hardware. Give it a database-driven brain.
What about you? Are you a "pure Markdown" purist, or have you embraced the power of block-based databases like SiYuan or Notion? How do you track your Homelab inventory?
#SelfHosted #Homelab #SiYuan #Obsidian #KnowledgeManagement #SQL #SysAdmin #Documentation #TechStack #Privacy #OpenSource -
----------------
🛠️ Tool
===================Opening: Antigravity Awesome Skills (Release 5.4.0) is a large-scale GitHub repository that aggregates 857+ agentic "skills"—small markdown files that encode task-specific instructions and workflows intended for multiple AI coding assistants. Supported agents listed include Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode, and AdaL CLI.
Key Features:
• Cross-agent compatibility: skills are authored to be usable across diverse assistant runtimes and IDE/CLI integrations.
• Curated bundles: starter packs and role-focused bundles (referenced as docs/BUNDLES.md) group relevant skills for specific developer personas.
• Workflow-oriented: packaged workflows aim to make an AI assistant operate as a full-stack digital agency, covering tasks from code generation to deployment-oriented concepts.Technical Implementation (conceptual):
• Skills are stored as markdown artifacts that include invocation patterns, input/output expectations, and role-play prompts to guide agent behavior.
• Integration points reference official provider capabilities (Anthropic, OpenAI, Google, Microsoft) so that skills can map to provider-specific APIs and CLIs when invoked by an agent front-end.Use Cases:
• Standardizing coding assistant responses across teams by distributing a shared skillset.
• Rapid composition of multi-step developer tasks (scaffolding, refactors, test generation, CI/CD conceptual flows) using prebuilt workflows.
• Onboarding AI assistants to organization-specific protocols or syntax via reusable skill files.Limitations:
• Repository is a collection of declarative skill files rather than a single runnable binary; actual behavior depends on the consuming agent and its integration.
• Runtime compatibility and feature parity depend on upstream agent capabilities and provider APIs; not every skill will map identically across all assistants.
• Versioning and maintenance of 857+ items require governance to avoid drift between skill intent and agent semantics.References:
• Noted components: V5.4.0, docs/BUNDLES.md, and explicit support for Claude Code, Gemini CLI, Codex CLI, Copilot, Cursor, OpenCode, and AdaL.🔹 tool #agentic_skills #antigravity #claude_code #gemini_cli
🔗 Source: https://github.com/sickn33/antigravity-awesome-skills
-
Patagonia wildfires
Wildfires are common in Patagonia during the summer months, but the current fires have breached Los Alerces National Park, a UNESCO World Heritage site famed for its #alerce trees, which can live more than 3,600 years, making them the world's second-longest-living tree species.
Argentina's 2026 budget slashed funding for the National Fire Management Service by 71% in real terms compared with the previous year.
-
Patagonia wildfires
Wildfires are common in Patagonia during the summer months, but the current fires have breached Los Alerces National Park, a UNESCO World Heritage site famed for its #alerce trees, which can live more than 3,600 years, making them the world's second-longest-living tree species.
Argentina's 2026 budget slashed funding for the National Fire Management Service by 71% in real terms compared with the previous year.
-
Patagonia wildfires
Wildfires are common in Patagonia during the summer months, but the current fires have breached Los Alerces National Park, a UNESCO World Heritage site famed for its #alerce trees, which can live more than 3,600 years, making them the world's second-longest-living tree species.
Argentina's 2026 budget slashed funding for the National Fire Management Service by 71% in real terms compared with the previous year.
-
Patagonia wildfires
Wildfires are common in Patagonia during the summer months, but the current fires have breached Los Alerces National Park, a UNESCO World Heritage site famed for its #alerce trees, which can live more than 3,600 years, making them the world's second-longest-living tree species.
Argentina's 2026 budget slashed funding for the National Fire Management Service by 71% in real terms compared with the previous year.
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
"Codex CLI is our cross-platform local software agent, designed to produce high-quality, reliable software changes while operating safely and efficiently on your machine. We’ve learned a tremendous amount about how to build a world-class software agent since we first launched the CLI in April. To unpack those insights, this is the first post in an ongoing series where we’ll explore various aspects of how Codex works, as well as hard-earned lessons. (For an even more granular view on how the Codex CLI is built, check out our open source repository at https://github.com/openai/codex. Many of the finer details of our design decisions are memorialized in GitHub issues and pull requests if you’d like to learn more.)
To kick off, we’ll focus on the agent loop, which is the core logic in Codex CLI that is responsible for orchestrating the interaction between the user, the model, and the tools the model invokes to perform meaningful software work. We hope this post gives you a good view into the role our agent (or “harness”) plays in making use of an LLM.
Before we dive in, a quick note on terminology: at OpenAI, “Codex” encompasses a suite of software agent offerings, including Codex CLI, Codex Cloud, and the Codex VS Code extension. This post focuses on the Codex harness, which provides the core agent loop and execution logic that underlies all Codex experiences and is surfaced through the Codex CLI. For ease here, we’ll use the terms “Codex” and “Codex CLI” interchangeably."
https://openai.com/index/unrolling-the-codex-agent-loop/
#AI #GenerativeAI #LLMs #OpenAI #CodexCLI #Codex #AIAgents #AgenticAI #Programming #SoftwareDevelopment
-
links: GitHub – justin025/onthespot: A GUI music downloader for Apple Music, Bandcamp, Deezer, Qobuz, Spotify, Tidal, and More
https://github.com/justin025/onthespot
#arr #music #openSourceAn easy to use music downloader written in Python. OnTheSpot has support for various music services and, unlike similar projects, downloaded files and metadata are sourced directly from the service of your choosing. The app includes a GUI, CLI, and Web UI frontend.