letta

> When are we going to build a safe version of this? I built something similar to Clawdbot for my own use, but with a narrower feature set and obviously more focus on security. I'm now evaluating Letta Bot [0], a Clawdbot fork by Letta with a seemingly much saner development philosophy, and will probably migrate my own agent over. For now I would describe this as "safer" rather than "safe," but something to keep an eye on. I was already using Letta's main open source offering [1] for my agent's memory, and I can already highly recommend that. [0] https://github.com/letta-ai/lettabot [1] https://github.com/letta-ai/letta

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 management"). if you're more interested in papers, we also worked on MemGPT and more recently sleep-time compute (https://arxiv.org/abs/2504.13171)

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 "one thread" agents, ie agents that have an indefinite conversation/event history, even if the underlying in-context message history is limited. That's why there's a distinction between just "messages" and "in-context messages" (a subset of messages).

...also MemGPT (now called Letta) https://github.com/letta-ai/letta

On a side note: working over longer contexts also reminds me of MemGPT(https://github.com/cpacker/MemGPT) I think a similar concept can be applied to Mamba architecture models too.

If you have a chance try it out via the Discord bot or with the GitHub repo! Or even just check out the short demo GIFs we released (at https://github.com/cpacker/memgpt) to get an idea of the MemGPT inputs/outputs. The high-level memory read/writes are quite intuitive and you may be surprised at how closely it matches what you were suggesting to your friend.

Hey all, MemGPT authors here! Happy to answer any questions about the implementation. If you want to try it out yourself, we have a Discord bot up-and-running on the MemGPT Discord server (https://discord.gg/9GEQrxmVyE) where you can see the memory editing in action - as you chat with the bot, you'll see MemGPT edit its memory to update its profile about you (and itself). Everything's open source, so can also try running MemGPT locally using the code here: https://github.com/cpacker/MemGPT. In the repo we also have a document-focused example where you can chat with MemGPT about the LlamaIndex API docs.

This is similar to how our external context is implemented under the hood - you might be interested in our perpetual chat bot example in the GitHub repo (https://github.com/cpacker/MemGPT), the message traces in the demo GIF should give you an idea of how things work at a glance.

If you want to try the MemGPT Discord chatbot, join the Discord server (linked above), then check out the #memgpt channel to start messaging the bot. If you want to run the chatbot or API docs examples locally, you can follow the instructions here: https://github.com/cpacker/MemGPT/tree/main#quick-setup.

Thanks for checking out our work! Yeah, great point, this is even more critical in those scenarios when you have very limited memory. You can play around with different context sizes using the code on GitHub: https://github.com/cpacker/MemGPT/blob/main/memgpt/constants...

Hey all, I’m the lead author on this work. Thanks to the OP for posting, and for all the interest and feedback. To clarify a few points: the goal of this work is to investigate the extent to which an LLM can manage memory and different memory hierarchies, applying lessons from operating systems to extend effective context lengths. All of our code is open sourced at https://github.com/cpacker/MemGPT so you can try it out yourselves!