-
zed
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
The simplest mainstream options for tools:
1) Claude Desktop which includes Claude Code for Anthropic: https://claude.com/product/claude-code (alternatively the terminal based version; either way get the subscription)
2) Codex for OpenAI: https://developers.openai.com/codex/app (same as above, subscription preferred instead of paying per token)
3) OpenCode for a variety of models: https://opencode.ai/ (they also have a subscription, but this in particular also makes it really easy to connect to OpenRouter)
4) KiloCode is essentially the above, but for VSC derived editors: https://kilo.ai/ (I personally liked RooCode more, but that got retired)
More niche tooling options:
1) Zed is pretty good, though I saw some issues with their LSP Edits and found that connecting them to OpenCode through ACP worked better, still a cool editor: https://zed.dev/
2) If you have to pay for tokens and can't get subscriptions, look at DeepSeek as a provider (V4 Pro with Max reasoning): https://api-docs.deepseek.com/quick_start/pricing
3) I'm also writing a launcher to make running Claude Code with 3rd party providers earlier, early days still: https://ccode.kronis.dev/
Note: for anyone on Windows, if you install the terminal versions of the tools (Claude Code, Codex, OpenCode, ...), you probably want them inside of WSL so there's less confusion with file paths etc. that some models have.
In regards to actually using the tech:
- version control and maybe worktrees -
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
The simplest mainstream options for tools:
1) Claude Desktop which includes Claude Code for Anthropic: https://claude.com/product/claude-code (alternatively the terminal based version; either way get the subscription)
2) Codex for OpenAI: https://developers.openai.com/codex/app (same as above, subscription preferred instead of paying per token)
3) OpenCode for a variety of models: https://opencode.ai/ (they also have a subscription, but this in particular also makes it really easy to connect to OpenRouter)
4) KiloCode is essentially the above, but for VSC derived editors: https://kilo.ai/ (I personally liked RooCode more, but that got retired)
More niche tooling options:
1) Zed is pretty good, though I saw some issues with their LSP Edits and found that connecting them to OpenCode through ACP worked better, still a cool editor: https://zed.dev/
2) If you have to pay for tokens and can't get subscriptions, look at DeepSeek as a provider (V4 Pro with Max reasoning): https://api-docs.deepseek.com/quick_start/pricing
3) I'm also writing a launcher to make running Claude Code with 3rd party providers earlier, early days still: https://ccode.kronis.dev/
Note: for anyone on Windows, if you install the terminal versions of the tools (Claude Code, Codex, OpenCode, ...), you probably want them inside of WSL so there's less confusion with file paths etc. that some models have.
In regards to actually using the tech:
- version control and maybe worktrees -
-
-
- chunker - app to get smart slices from text and organize them in hierarchical LLM/Obsidian wiki. There were two features implemented using sddw and 15 subtags:
-- https://github.com/sermakarevich/chunker/blob/master/.sddw/c...
-- https://github.com/sermakarevich/chunker/blob/master/.sddw/m...
- ccw (claude code workflow - plugin to compile generic claude code workflows based on sdd approach) - https://github.com/sermakarevich/ccw/blob/main/.sddw/claude_...
Btw you can use ccw to compile your custom version of sddw to ith spec that fits your needs
-
modern-software-dev-assignments
Assignments for CS146S: The Modern Software Dev (Stanford University Fall 2025)
Stanford University offered the course "CS146S: The Modern Software Developer" in Fall 2025. Check it out if interested. https://themodernsoftware.dev/
-
https://github.com/portpowered/you-agent-factory/commits/mai...
The general premise when you get to full automation generally is you go full industral engineering:
-
I am using Spec Driven Development approach implemented as a Claude Code plugin since Feb for all mid + size tasks. The idea is to write detailed specs first using agent help doing research and interviewing, decompose the task into smaller subtasks, write detailed spec for each task, implement each task separately. You can restart the session after every step in еру workflow and after each subtask implementation since all requirements are materialized in specі. This helps to keep session context focused on a single task at time, improve adherence, reduce cost and allow to implement bigger tasks that are hard to implement with pure plan + code.
Discussion on hn: https://news.ycombinator.com/item?id=48231575
Repo: https://github.com/sermakarevich/sddw
Slides: https://docs.google.com/presentation/d/1SjKXF7hkoqyiN9-3tBGY...
-
kilocode
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.
The simplest mainstream options for tools:
1) Claude Desktop which includes Claude Code for Anthropic: https://claude.com/product/claude-code (alternatively the terminal based version; either way get the subscription)
2) Codex for OpenAI: https://developers.openai.com/codex/app (same as above, subscription preferred instead of paying per token)
3) OpenCode for a variety of models: https://opencode.ai/ (they also have a subscription, but this in particular also makes it really easy to connect to OpenRouter)
4) KiloCode is essentially the above, but for VSC derived editors: https://kilo.ai/ (I personally liked RooCode more, but that got retired)
More niche tooling options:
1) Zed is pretty good, though I saw some issues with their LSP Edits and found that connecting them to OpenCode through ACP worked better, still a cool editor: https://zed.dev/
2) If you have to pay for tokens and can't get subscriptions, look at DeepSeek as a provider (V4 Pro with Max reasoning): https://api-docs.deepseek.com/quick_start/pricing
3) I'm also writing a launcher to make running Claude Code with 3rd party providers earlier, early days still: https://ccode.kronis.dev/
Note: for anyone on Windows, if you install the terminal versions of the tools (Claude Code, Codex, OpenCode, ...), you probably want them inside of WSL so there's less confusion with file paths etc. that some models have.
In regards to actually using the tech:
- version control and maybe worktrees -
virgin project:
1/ spec driven dev (https://github.com/github/spec-kit)
2/ then degrade to multiple sessions (no worktrees) debugging various problems until its done
-
-
I've spent 2 weeks (2-4h per day) to make D language[1] version of Sciter SDK [2]
Choice of AI "tooling" was by accident - typed something like "how to define copy constructor in D for custom structure" in Microsoft's Copilot in Edge browser that gives context for AI.
The answer was good enough for me and so I went with it further.
[1] D language HQ : https://dlang.org/
-
llm-flashcards
Visual knowledge bank for understanding large language models, with 180 concept cards from tokenization to deployment.
Don't want to jeopardize this awesome chat about tools but for AI workshops I think these visual cards I came across could be an amazing way to handout. They cover all LLM concepts and explained visually. Found very useful to revise LLM concepts before AI research scientist/AI engineer interviews.
https://github.com/llmsresearch/llm-flashcards
-
I use Claude Code, Codex, Pi all for varying levels of work.
I like reviewing agent messages, some specs/plans, and then conducting local code reviews with Plannotator [1].
For skills, i really only like using the interrogate skill from cursor's lauren [2]. I use with claude and codex models.
[1] https://plannotator.ai
[2] https://github.com/cursor/plugins/blob/main/pstack/skills/in...
-
plannotator
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
I use Claude Code, Codex, Pi all for varying levels of work.
I like reviewing agent messages, some specs/plans, and then conducting local code reviews with Plannotator [1].
For skills, i really only like using the interrogate skill from cursor's lauren [2]. I use with claude and codex models.
[1] https://plannotator.ai
[2] https://github.com/cursor/plugins/blob/main/pstack/skills/in...
-
Picosa
Picosa – a Pi Container Sandbox to run secure, offline AI agents. Because I do, in fact, care about your privacy.
I've dabbled a bit in GitHub Copilot using Claude Opus and Sonnet models via work, but I couldn't shake the thought that we weren't allowed to use this on any of our clients' codebases. Having been a fan of Ollama, I wanted to try something truly local.
First I tried OpenCode but they unexpectedly make external requests (!) even when using Ollama (I noticed when Ollama wasn't properly connected and I still got a title generated).
So I settled for Pi, but I strongly disliked the idea that the agent could, at any point, decide to delete files or exfiltrate .env secrets. So I created Picosa (https://github.com/GreenpantsDeveloper/Picosa), containerizing and sandboxing Pi, with firewall rules such that it could only ever reach the local network (for Ollama), scoped by just the current working directory, and nothing else. Combined with Qwen3.6:35b, it works surprisingly well, and I could ask it to improve itself when run on its own repository.
-
-
-
-
-
-
My current workflow is to make the agent plan before it edits: repo status → indexed search → symbol refs → impact → tests → plan → verify. I've built a local-first tool around that because I found agents waste too much context crawling files and guessing blast radius. The useful part is not search alone; it is getting files, symbols, likely impact, validation commands, confidence/caveats, and boundaries before the edit.
The repo is https://github.com/shivyadavus/open-kioku if anyone would like to try it. Love any feedback.
-
Sahil’s ME skill pack seems to be this: https://github.com/slavingia/skills
-
- chunker - app to get smart slices from text and organize them in hierarchical LLM/Obsidian wiki. There were two features implemented using sddw and 15 subtags:
-- https://github.com/sermakarevich/chunker/blob/master/.sddw/c...
-- https://github.com/sermakarevich/chunker/blob/master/.sddw/m...
- ccw (claude code workflow - plugin to compile generic claude code workflows based on sdd approach) - https://github.com/sermakarevich/ccw/blob/main/.sddw/claude_...
Btw you can use ccw to compile your custom version of sddw to ith spec that fits your needs
-
I'm currently using herde[1] to handle/supervise multiple agents (with some patches I need to try to upstream) along with Nono[2] for sandboxing. This sandboxing approach avoids use of a microVM, which lets me use tooling I already have installed inside the sandbox. The downside is getting all the policies correct as it seems every project needs some new type of access, though Nono does try to make policy writing easy.
I've been considering switching my approach to using a microVM through microsandbox[3]. The pro of this approach is you can essentially skip the policies and rely on the security of the VM boundary. The negative is that now you've lost all your installed tools, so you need to either provision at runtime or build something (like an image) beforehand to match your dev environment.
I still don't know which is less maintenance. And while I think herde is pretty well thought out, I do think about something that works outside the terminal may be nicer.
[1] https://github.com/ogulcancelik/herdr
[2] https://github.com/always-further/nono
[3] https://github.com/superradcompany/microsandbox
-
I'm currently using herde[1] to handle/supervise multiple agents (with some patches I need to try to upstream) along with Nono[2] for sandboxing. This sandboxing approach avoids use of a microVM, which lets me use tooling I already have installed inside the sandbox. The downside is getting all the policies correct as it seems every project needs some new type of access, though Nono does try to make policy writing easy.
I've been considering switching my approach to using a microVM through microsandbox[3]. The pro of this approach is you can essentially skip the policies and rely on the security of the VM boundary. The negative is that now you've lost all your installed tools, so you need to either provision at runtime or build something (like an image) beforehand to match your dev environment.
I still don't know which is less maintenance. And while I think herde is pretty well thought out, I do think about something that works outside the terminal may be nicer.
[1] https://github.com/ogulcancelik/herdr
[2] https://github.com/always-further/nono
[3] https://github.com/superradcompany/microsandbox
-
I'm currently using herde[1] to handle/supervise multiple agents (with some patches I need to try to upstream) along with Nono[2] for sandboxing. This sandboxing approach avoids use of a microVM, which lets me use tooling I already have installed inside the sandbox. The downside is getting all the policies correct as it seems every project needs some new type of access, though Nono does try to make policy writing easy.
I've been considering switching my approach to using a microVM through microsandbox[3]. The pro of this approach is you can essentially skip the policies and rely on the security of the VM boundary. The negative is that now you've lost all your installed tools, so you need to either provision at runtime or build something (like an image) beforehand to match your dev environment.
I still don't know which is less maintenance. And while I think herde is pretty well thought out, I do think about something that works outside the terminal may be nicer.
[1] https://github.com/ogulcancelik/herdr
[2] https://github.com/always-further/nono
[3] https://github.com/superradcompany/microsandbox
-
spec-driven-development
Spec-driven development guide: maturity levels, Spec Kit comparison, PRD-to-app demo (by Anioko)
There are many good answers here. I created microcodegen that can help scaffold the entire architecture for you to get started. Here is it https://github.com/Anioko/spec-driven-development
