Another take I've seen is https://agentrepo.com/, which is light-weighted hosted git that's easy for agents to use (no accounts, no API keys, public repos are free). There are large parts of the GitHub experience I'm no longer using (mostly driving from Claude), so I think this is an interesting take.
I’m used to having good observability for systems and workflows, but now that I generally start development with Claude Code vs my IDE, I lost a layer of visibility into how my code is produced.Subtle (https://github.com/itsderek23/subtle) is a free, open-source app for analyzing Claude Code logs that runs entirely on your local machine. It lets you:* See overall Claude Code usage over time...
> Did you hit token limits?
While i used TikToken to limit the message history (and keep below the token limit), generally I found that I didn't get better completions by putting a lot of data into the context. Usually the completions got more confusing. I put a limited amount of info into the context and have generally stayed below the token limit.
> Are you storing message/ chat histories between sessions
Right now, yes. It's pretty important to store everything (each request / response) to debug issues with prompt, context, and the agent call loop.
* Is this really for more intensive model inference applications that need a cluster? It feels like for a lot of my models, a cluster is overkill.
* A lot of the ML deployment (Cortex, SageMaker, etc) don't see to rely on first pushing changes to version control, then deploying from there. Is there any reason for this? I can't come up for a reason why this shouldn't be the default. For example, this is how Heroku works for web apps (and this is a web app at the end of the day).
My background is as a software engineer at SMBs and startups, which typically lack a data scientist. Because I love numbers, charts, etc. I do a lot of amateur data science. I enjoy the analysis, but I despise the data preprocessing: it's common for an SMB to store data across 10+ cloud apps (Salesforce, Google Ads, Hubspot, Mixpanel, etc) but it's uncommon for them to store this data in a data...