Viewing profile — pacjam

Oh interesting - it's just a .mp4. I put it on vercel blob storage just as a fast way to make it easily embeddeded in our CMS system, but I think I put it on the wrong Vercel accou…

I think it's mostly complimentary, in the same way a linear MCP would be complementary to a MemGPT/Letta-style memory system I guess the main potential point of confusion would ari…

Yes! Letta Code also has a "danger" mode, it's `--yolo`. If you're running Claude Code in a sandbox in headless mode, Letta Code has that too, just do something like `letta -p "Do …

Cool, let us know what you think! Would recommend trying w/ Sonnet/Opus 4.5 or GPT-5.2 (those are the daily drivers we use internally w/ Letta Code)

Yeah exactly - it's all just tokens that you have full control over (you can run CRUD operations on). No hidden prompts / hidden memory.

I'm curious - how do you currently manage this `llm.md` in the tooling you use? E.g., do you symlink `AGENTS/CLAUDE.md` to `llm.md`? Also, is there any information you duplicate ac…

Ah gotcha! In that case, I think Terminal-Bench is currently the best proxy for "how good is this harness+agent combo at coding (quantitatively)" question. I think it used to be SW…

Beads looks cool! I haven't tried it, but as far as I can tell, it's more of a "linear for agents" (memory as a tool), as opposed to baking long-term memory into the harness itself…

Not sure why Cursor CLI isn't on the leaderboard... I'm guessing it's because Cursor is focused primarily on their IDE agent, not their CLI agent, and Terminal-Bench is an eval/ben…

> Does somebody have a clear case on why this is something that we should want For coding agents, I think it's clear that nobody wants to repeat the same thing over an over again. …

IMO context poisoning is only fatal when you can't see what's going on (eg black box memory systems like ChatGPT memory). The memory system used in the OP is fully white box - you …

I think it cuts both ways - for example I've definitely had the experience where when typing into ChatGPT I know ahead of time that whatever "memory" they're storing and injecting …

One cool option is having Void-2 run inside the Letta Code harness (in headless mode) on a sandbox to let is have free access over a computer, just to see what it will do while als…

I think Cameron (Void's handler) has some experience wiring up production Void to his computer via Letta Code

Thanks for sharing!! (Charles here from Letta) The original MemGPT (the starting point for Letta) was actually an agent CLI as well, so it's fun to see everything come full circle.…

MemGPT was also first a CLI (and Discord bot), truly returning to our CLI roots: https://news.ycombinator.com/item?id=37901902

I'm talking about the Letta part - unless I'm missing something, the RunAgent framework has to communicate with the Letta server over the Letta API (I'm saying that part can be don…

This is pretty sweet. The Letta SDKs are actually auto-generated off of the REST API spec, which means that adding an (official) SDK for another language is just a matter of having…

check out Letta - the OSS codebase ( https://github.com/letta-ai/letta ) is basically focused on solving the memory/context problem in a generalized way (via "agentic context manag…

If you're interested in the full schema you can look at the Pydantic models here: https://github.com/letta-ai/letta/blob/main/letta/serialize_... Agent File is intended to support …

Totally agree - a well-defined REST API "standard" for tool listing and tool execution would have been much better. Could extend as needed to websockets for persistent connections …