eitanlebras

Oh nice, that separate SSE event seems like a big improvement for UX.

Nice! Glad it’s making the list.

The middleware being adapted from LangChain DeepAgents is interesting... there's a known issue with LangChain's summarization middleware where model.invoke calls during compression leak into the SSE stream as visible assistant turns rather than staying internal. Curious if you hit that and how you handled it, since you're streaming everything over SSE anyway?

Nice! Yeah, maybe adding it as a quick config could be very helpful to embed it into Rekal's structure.

I think that'd be cool, maybe just a simple config option in pyproject.toml or a .rekal/config.yml would cover most use cases: they could default to 0.4/0.4/0.2 but could be overriden.

Genuinely useful. One question: how does Stork rank MCP servers? Is it just stars or something more? Asking because I've been tracking GitHub imports across around 13k active AI repos, and MCP server repos just crossed 5,715 active this month (up 172% in 30 days). At that growth rate the newest and most useful servers are probably invisible if ranking is purely based on popularity.

The hybrid search scoring is really well thought out. One question: are the 0.4/0.4/0.2 weights fixed or configurable? To me it feels like different use cases would want different balances (e.g. a coding assistant would want higher recency weights than a research tool would).

Really interesting project. One thing: why not just save the eviction state to a file automatically when the session ends, and just load it the next time you run context-surgeon in the same project dir? Could context-surgeon do the same as git with the .git folder example, such as with a .surgeon folder? Seems like it would make the tool much more useful for multi-session work.

The multi-agent coordination problem is real. i've been running claude code solo all week and even that gets messy. Spinning up 5 agents that actually talk to each other cleanly sounds hard to get right. Curious how the environment isolation holds up at scale?

Cool tool. Anthropic's managed agents API is powerful, but without a UI, you're essentially flying blind. I've been scraping GitHub this week, and agents are dominating: 63% of active AI repos pushed in the last two weeks are agent-related. Lots of builders who would find this useful. Following.

yeah exactly, all the data was already there, just needed something to surface it. happy it's useful