@jpschroeder Curious what features of which harnesses you find the most enjoyable or effective? Stated another way, "why not just use Cursor's harness?". Or is standardagents just about democratizing the combo of harness and models that suits each person best?
@nbaschez I mean, *should* it tell you what you should consider? Maybe only if you're unhappy with what you asked it for originally? It's wild how philosophical this all gets, fast.
It's wild, @cursor_ai with Composer 2.5 is now the optimal solution for all? of my tasks. One model, one harness, fast, efficient, reliable. Somehow achieves the impossible highest marks on best-speed + best-IQ + best-cost.
@Leohuynh57 Pro plans on all three is the way. Add Ultra for your fave. Yes, Composer 2.5 is fast, cheaper, and good. Beats Sonnet in all dimensions which is high praise by me.
@ericzakariasson So fast, best economics, retires Sonnet for me, need to throw more planning activities at it to understand its reasoning better but just, best all-around model there is for coding.
I'm finding it more enjoyable in having faster back and forth in the "early" parts of a session so that the model can rip through the rest once it understands preferences and patterns of the task at hand
@ericzakariasson I guess I am finding thanks to AI that I'm managing many diverging ideas and several times per week looking to "close the loop" on open explorations that quickly get lost
heya @ericzakariasson lobbing this in your direction:
Any thoughts on how Cursor might improve "findability" of past agent chats/sessions or introduce more forms of organization systems around them? Is anyone talking about this in the community or building their own solutions?
@ericzakariasson Ah, I should try that more. Does it find them and link to them successfully for you in most cases? Is there a decay factor to conversations that are, say 6+ months old? Feels like the UI *wants* me to forget about the past, maybe it's just assuming those topics are less important
@ericzakariasson Search has a tendency to rank project/codebase symbols, skills, etc. higher over "these tokens were important in a prior conversation." Feels wrong/broken, curious if intentional or just, is mine a rare use case?
@ericzakariasson - I use multiple agent interfaces, stack ranked: Cursor (BEST), Claude Code, Codex, Antigravity
- Cursor has the best grouping/filtering so far but has an opportunity to really pull ahead by being most model-agnostic
- CC has branch status awareness/iconography baked in
Exploring AI tools? Sign up for Cursor, the best agent harness in town for coding, and get 50% off your first month. Try all the frontier models and see which works best for you!
Link below:
"Update this repository to use uv, FastAPI, SQLModel, and Typer. Install the necessary library-skills so that you are implementing everything as the library intended. Map out the plan for how to refactor in steps. Then implement each step, one by one."
If you are building a vibe-coded app and you want it to be something that, if it takes off and you need to hire proper devs to manage it, I strongly recommend "the FAST Stack". Here's a prompt I ran in Codex that did a surprisingly great job... (1/2)
Install the library skills bundled with your dependencies (like FastAPI) for your coding agent 🤖
In Python or Node.js, both versions support both ecosystems ✨
https://t.co/QlmEF6FPe0