Post

How do y'all avoid having seven+ terminal windows open with agent conversations that are probably over? but maybe you might want to pick back up a few days from now? seems a shame to throw away all that exploration & context, right?

austin (eeek!/ackkk! 👻)

@thebadcode.com

11 Sept

we chunk and summarize everyone’s agent transcripts, compute text embeddings, and do RAG over the result. it works insanely well

wariziles

@riziles.bsky.social

11 Sept

This, but just use agentsview.io to do it for you instead of building it yourself. Shout out to @wesmckinney.com

agentsview.ioSee what your AI coding agents did, and what it cost.The local-first system of record for AI coding sessions, with search, activity, cost, quality, and recall.

austin (eeek!/ackkk! 👻)

@thebadcode.com

we deliberately wanted something that worked without needing to scrape the local session logs but this is also cool 👍

11/9/26, 7:17 pm0 reposts8 likes

wariziles

@riziles.bsky.social

11 Sept

How do you do it without?

austin (eeek!/ackkk! 👻)

@thebadcode.com

11 Sept

we forked agentgateway.dev to robustly persist all inference request/response bodies to s3 as gzipped jsonl batches

agentgateway.devagentgatewayThe open-source gateway for AI traffic — LLM, MCP, A2A, and HTTP in one data plane.

austin (eeek!/ackkk! 👻)

@thebadcode.com

11 Sept

session reconstruction from the raw inference call logs happens out of band

Nice!

session reconstruction must be hairy right? i use a hook that emits turn-by-turn tracing, but the drawback there is I need to install it on the client