if you are looking for a customizable agent harness that provides everything except a tui (cli, acp, embeddable python package) i built and use this for a handful of projects where i needed a vendor-agnostic replacement for claude agent sdk: https://github.com/zackham/aloop
The most durable way to reason about agents is to just think about humans. We have thousands of years of prior art on coordinating instantiations of stochastic intelligence. Context, tools, goals, validation, specialization, distribution of labor, coordination... If jobs are bundles of tasks and areas of accountability, maybe it's more effective right now to unbundle and reorganize some of these things. If constraints underperform autonomy, maybe you have to adjust where you operate on that spectrum, and account for it in goal definition and validation. These are not new problems.
When I come across a paper/article/insight that connects to one or more things I'm working on, I generate 20-30 minute podcasts that do deep research, connect it back to my work, and target an angle I'm interested in. I can message my agent over Telegram and say "check this out [link] curious who else is working on this problem and if there's anything actionable we can glean from it in relation to [projectX], generate a podcast". It's been surprisingly good, and in my commutes I've found these more compelling to listen to than my normal rotation of stuff.
agreed. the long-running tasks i handle with immediate-background and continually edit message with updates, along with fork-and-reconcile semantics so you don't have to queue messages. also having a supergroup with separate topics for different sessions works really well.
the separate topics approach along with allowing other processes to enqueue messages into the session stream solves state pretty tidily, see "the session as decision-maker" in the linked report
pi is great and made popular some things that are really valuable, that hopefully spread to more projects (arbitrary forking with /tree, system prompt transparency and control). i was hoping to use it on a few projects but needed something to embed, and it didn't quite fit the bill. ended up building https://github.com/zackham/aloop which i am using in coordination with https://stepwise.run/ - reach if you're interested, both under active dev and deployed in systems doing real work.
Hey - OP here. I've been working on Ride with GPS since 2006 (!) and the game we've built is the most fun I've had in a long time. We're launching in PDX and if that is a success, we'll double down on it and roll it out to a bunch more cities. I want to do everything I can to stack the deck in our favor since I believe in this project.
I put together this landing page start to finish yesterday (thanks claude/grok), and am hoping it's effective in generating some initial interest. Looking for any feedback you have, small/large, however blunt, to dial it in and make it work for us.
We are the world's best library of bike routes, and we enable cyclists to go on better rides, more often. We have a website and mobile apps that allow people to discover the best riding in their area, and get turn by turn navigation using either our mobile apps or the bike computer of their choosing. Come join us in taking Ride with GPS to the next level!
Senior Software Engineer - iOS Development: We have a technically interesting, battery efficient app that offers a full-featured bike computer (ride recording, & route navigation), a route planning tool, as well as ride management, analysis, and more. We're looking for a talented iOS engineer to help us take what we've done to the next level.
I'll add to the sibling comment and say I've been writing software for money for 25+ years, have a CS degree, and have found immense leverage with these tools. I put in the time on hobby projects over the past couple years to figure out how best to integrate it all into my work, and now I'm in a place where it's saving me significant amounts of time every time I produce code, and I'm getting the quality of results the project demands. I use gemini-2.5-pro, claude-4-sonnet, and o3 for different purposes, and have a variety of techniques to avoid pitfalls and get the results I'm looking for. There are a lot of ways to unsatisfactory results, but it's possible to get usable results that save time. I've shared my enthusiasm and seen other devs dabble, get poor results, and go back to their practiced methods of writing software–so I'm not surprised to see so many skeptics and naysayers. It isn't easy or obvious how to make this stuff work for you in larger codebases and for meatier problems. That doesn't mean it's impossible, and it doesn't mean it's not worth it to climb the learning curve. As the models and tools get better, it's getting a lot easier, so I suspect we'll see the number of people denying the utility of LLM-generated code to shrink. Personally, I'd rather be reaping the benefits as early as possible, because I can get more stuff done faster and more pleasantly.
If you're using org-mode and thinking about customizing it a bit more, and/or would like it to serve you in a way that is a bit more aligned with GTD, this reference from Bernt Hansen is without peer and just an incredible contribution: https://doc.norang.ca/org-mode.html
reply