Agent Client Protocol (ACP) https://agentclientprotocol.com https://github.com/zed-industries/agent-client-protocol A new open standard developed by Zed Industries, aiming to standardize communication between code editors (IDEs, text editors) and AI agents. The approach is similar to how Language Server Protocol (LSP) standardized the integration of language servers. Agents run as child processes of the code editor and exchange data using JSON-RPC over standard input/output (stdio) streams. T...| Code With LLM Updates
Practical Techniques for Claude Code and Codex CLI https://coding-with-ai.dev/ https://github.com/inmve/coding-with-ai The website contains practical techniques for effective work with AI assistants. Each stage has a checklist. Raise the following topic-sections: 1. Planning (preparation for working with AI), 2. UI & Prototype (rapid creation of interfaces and prototypes), 3. Coding (efficient code generation and manipulation), 4. Debuging (identifying and fixing errors with AI), 5. Testing &...| Code With LLM Updates
AI integration experience in production processes https://www.sanity.io/blog/first-attempt-will-be-95-garbage The author used Cursor for 18 months for code generation, and Claude Code for the last 6 weeks. The transition to Claude Code took only hours to understand how to work with it. Author's mental model: AI is a junior developer who never learns. Costs for Claude Code can be a significant percentage of an engineer's monthly salary ($1000-1500 per month). Conclusions: Rule of three attempt...| Code With LLM Updates
A sample instruction file CLAUDE.md is available at https://www.dzombak.com/blog/2025/08/getting-good-results-from-claude-code/ However, there is a discussion about the effectiveness of this file for providing context: some consider it useful for AI's long-term memory, while others argue that the AI often ignores its content. From the HN Discussion, further conclusions can be drawn: The best results are achieved when the developer spends significant time creating very clear, step-by-step spec...| Code With LLM Updates
Auggie https://www.augmentcode.com/product/CLI Augment Code CLI - this is a attempt to copy Claude Code, this time from the developers of Augment Code. As a standalone product, it's hard to say if it has any value; it's more likely an addition to their main product and tied to their pricing plans. An interesting feature is the hotkey for improving a request. Otherwise, it has basic terminal agent functions, with MCP support like everywhere else now. The models are Claude Sonnet 4 and GPT-5. #...| Code With LLM Updates
Privacy mode in TRAE IDE v2.1.0 https://docs.trae.ai/ide/privacy-mode?_lang=en One of the reasons I didn't use ByteDance's Chinese TRAE was their unclear policy of "we do what we want with your code." Now they have added the ability to activate privacy mode in the settings. I think this is a response to Alibaba's Qoder. Privacy mode is only active when your account is active. After logging out, privacy mode ceases to be active. Privacy mode does not apply to SOLO mode, which is still in the t...| Code With LLM Updates
Codex IDE https://developers.openai.com/codex/ide OpenAI has once again changed what is called Codex. It is now not only the old model and a new agent in CLI and ChatGPT, it is also an IDE extension (VSCode, Cursor, and Windsurf). From it, you can both modify code locally and send tasks to the cloud. It works on Mac and Linux. Windows support is still experimental. https://www.youtube.com/watch?v=SgJaSmD3u3k Video on YouTube: https://www.youtube.com/watch?v=SgJaSmD3u3k https://help.openai.com...| Code With LLM Updates
ByteRover 2.0 https://www.byterover.dev/blog/byterover-2-0 A new version of ByteRover 2.0 has been released with an improved interface and two key features. Context Composer: A tool for collecting and managing precise context for AI agents from various sources (documents, images, web, etc.). Git for AI Memory: Allows version control of AI agent memory, tracking changes, and collaboration, similar to Git for code. --- xAI: Grok Code Fast 1 https://openrouter.ai/x-ai/grok-code-fast-1 https://ve...| Code With LLM Updates
Zed and CLI agent support https://zed.dev/blog/bring-your-own-agent-to-zed Zed, in partnership with Google, has integrated Gemini CLI into the IDE via the new Agent Client Protocol (ACP). This is an open, JSON-RPC-based protocol that allows connecting any agents to Zed (similar to how LSP works for languages). AI data is not sent to Zed servers. The protocol is Apache licensed — you can create your own agents or connect them to other editors (for example, Neovim already supports it). When i...| Code With LLM Updates
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Amazon Kiro v0.2 https://kiro.dev/pricing/ Kiro IDE is still in preview development, but they have already launched paid subscriptions. Perhaps this is because in v0.1 they gave a lot of free tokens for Sonnet 4, and now registration is closed. For new users, there is only a waiting list. Only 50 vibe requests per month will be free; currently, all new users have been given 100 vibe and spec requests, which must be used within 2 weeks. This is very unfortunate; my simple test project took 40 ...| Code With LLM Updates
LLMs Won't Replace Programmers https://zed.dev/blog/why-llms-cant-build-software A provocative post by Konrad Irwin from ZED. He says that LLMs are quite good at generating code, updating it when problems are found, and running tests. But human engineers don't work like that: they build mental models of what the code does and what it should do - then perform updates based on that. AI agents do not create a mental model of the project and simply generate code that resembles the best code they ...| Code With LLM Updates
AGENTS.md https://agents.md/ A README equivalent for agents. Finally, a standard for a markdown file where we write context and additional instructions for an AI coding agent. This is a simple text file. It will also be useful for human developers, because most people barely write anything in their READMEs anymore, but that won't work here. This is because LLMs require greater detail and precision. Previously, if I used several AI coding tools in a repository, I had to have a separate file fo...| Code With LLM Updates
As the quality of generated code increases, development moves from manual writing to task organization and AI agent management. The human role transforms into a "project manager" who sets high-level goals, breaks them down, and guides agents that are stuck or need feedback. There is a growing demand for mobile applications to "code on the go". OMNARA https://omnara.com/ A mobile iOS client on top of AI agents (Claude Code, Cursor, GitHub Copilot, etc.). It allows you to run and see the work o...| Code With LLM Updates
Who currently offers TOP models for free https://github.com/inmve/free-ai-coding This repository contains a table of available projects that provide free, limited access to the best models. For example, Rovo Dev CLI gives 5M tokens per day on Claude Sonnet 4. Gemini CLI provides 100 requests per day on the Gemini 2.5 Pro model. It also states whether a credit card number is required. Unfortunately, the author does not specify whether we automatically grant permission to these companies and pr...| Code With LLM Updates
Google Jules https://jules.google/docs/usage-limits On August 6, Google Jules officially moved out of beta after two months of testing. Along with this, Google introduced usage limits and pricing plans, and upgraded the underlying model to Gemini 2.5 Thinking. The default Jules environment now comes with Playwright for frontend testing: it can run tests on web applications and return results as screenshots. Jules also supports image inputs via public URLs. Since August 15, the Jules VM has re...| Code With LLM Updates
1M Context for Sonnet 4 https://www.anthropic.com/news/1m-context The most popular model for code generation, Claude Sonnet 4, now supports up to 1 million tokens of context, a 5x increase that will help Claude Code understand larger codebases. Also, for requests over 200k tokens, input and output prices increase. Talks from Code w/ Claude https://www.youtube.com/watch?v=gv0WHhKelSE Video on YouTube: https://www.youtube.com/watch?v=gv0WHhKelSE Cal Reub from Anthropic explains how to best work...| Code With LLM Updates
Cursor Agent CLI https://cursor.com/blog/cli Due to Anthropic once choosing the path of creating a terminal programming agent, and the Claude Code project being successful and working well, a new trend emerged to create such variations of coding assistants. OpenAI replicated this by creating Codex, although it wasn't as successful, but with the release of GPT-5, it began to work much better. Google made its version, which was copied by Chinese Qwen. And so on. https://www.youtube.com/watch?v=...| Code With LLM Updates
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
model GLM-4.5 https://z.ai/blog/glm-4.5 The new agentic model GLM-4.5, developed by the Chinese company Z.ai (formerly Zhipu AI), significantly improves the capabilities of complex code generation presented in the previous version of GLM-4. The model can now create complex things such as interactive mini-games and physics simulations in HTML, SVG, Python, and other formats. It has a 355b MoE size, with 12b active parameters. It demonstrates very good results in solving real engineering proble...| Code With LLM Updates
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com
Updates and tips about using Large Language Models (LLM) for programming and development| aicode.danvoronov.com