thority

@YasirK85192 @HubzzHQ @flipsuitexyz my pickle 😢

having some fun on @HubzzHQ with team from @flipsuitexyz ❤️😅

@YasirK85192 nobody, so it rolls over to the next week

@AuthorityNull who won

and it's gone

@flipsuitexyz You forgot to say Hyperliquid at the end like the cool kids

You have approximately 30 minutes left to trade with Flippy agent for a shot at 200 incredible United States tokens. Plenty of time.

@CROGuard @flipsuitexyz awesome 🙌

We’re excited to announce another strong addition to the trusted list on CROGuard 🚀 @flipsuitexyz has officially joined. The leading rewards engine on #Cronos, trusted and used by many Cronos communities. Flipsuite is building a highly flexible rewards distribution engine for teams and communities delivering unmatched quality, robust APIs, and seamless built-in payments. Welcome to the CROGuard ecosystem. CROGuard 🛡️

For my particular setup it does solve the issue of not having a good fact-based recall but I’m always tinkering and trying new stuff. I checked the speed and extraction is about 2ms and recall 10ms, but this doesn’t include model inference. I have some corns that remove as much of the stale/poor facts as possible on set schedule too.

@AuthorityNull @jlehman_ Cool. So your plugin solves everything you’ve described above? Besides that – how’s mem0 speed?

A common line of questions I receive: what does lossless-claw do differently than memory systems? How do the two relate? Should I use both? Here’s the lowdown: Memory systems are good for letting you search for information that’s external to your context window, which are typically “memories” extracted from past/different conversations. This is necessary because: Compaction is lossy: when your conversation gets too big, your agent replaces the whole conversation with a summary. Do this a few times and details from the first conversation are no longer part of the summarized conversation. Your context is split across many sessions: you have conversations with different agents over time and want to be able to reference all of that in your current conversation. Memory systems work okay in the first case and pretty well in the second case. lossless-claw works phenomenally well in the first case and only indirectly addresses the second one. Let’s expand that. Lossless context makes frequent summaries of smaller pieces of context in the background. It keeps your most recent messages around verbatim (the “fresh tail”). As the summaries accumulate, they get combined into summaries of summaries. This lets your agent stay focused: older content is still there, but becomes more “vague” over time — kind of like your own recollection of events. Current messages are always there and never suddenly disappear to be replaced by a summary. This effectively solves the “post-compaction amnesia” problem where your agent seems to suddenly forget important recent details about what you were doing. The reason lossless-claw is called “lossless” though is because your older messages never get truly removed. The incremental summaries replace the messages, but act as “pointers” to them that can be used to expand the source messages back into context. Because the summaries stick around, your agent doesn’t forget about what it can expand should it need to. By contrast, memory systems don’t offer the agent any ideas about what can they can be used to remember. This is why you have to frequently tell your agent to “search its memories” explicitly for something. This feels unnatural and is certainly inefficient. Using lossless-claw means that you can keep one conversation going indefinitely without ever needing to reset. This assesses point (2) from above indirectly: if you don’t need to start new sessions all the time, you don’t need a way to recall information from past sessions! If you work across multiple agents and want to share memories between them, or want to be able to recall information that happened outside of the scope of a conversation (eg meeting notes), you’ll want a memory system. Much of what memory systems are used for is a poor fit for them stemming from overly naive approaches to managing context, which unfortunately are industry-standard. Don’t get me wrong: they’re still useful — I still use one — but they’re not the only tool that agents need to become effective personal assistants. Lossless-claw is among the first production-grade implementations of an alternative context management strategy, and certainly the most effective, and it’s only available on @openclaw. None of this would be possible without the excellent research into Lossless Context Management pioneered by @ClintEhrlich and @rovnys at @Voltropy, so make sure to give them a follow if you’re looking for some real alpha.

I like it, but had to do a lot of customization so it would fit in along side QMD. I use Qwen3 Max (Alibaba) for extraction and Snowflake (local) for embeddings and added/tuned a scoring system to keep bad facts from being recalled (this is a real issue with memory recall systems). Once you get it dialed in it's pretty powerful. I've heard good things about MemU too. My extension is here 🫡 github.com/AuthorityNull/…

@AuthorityNull @jlehman_ Can you give some feedback on your experience with mem0 ?

@flipsuitexyz Community capital 🤔

We just launched points for teams and communities. Use them for roles, tips, raffles, airdrops, and Quest rewards. Community storefronts are coming next!

Points are portable! Communities can choose to share their point systems with partner servers, making those points usable across both ecosystems. You can also exchange one community’s points for another. And as Flipsuite expands to Telegram and across apps via API, this model extends cross-platform too.

best community points system by far

@steipete yesss

in the next claw release (~Sunday), you can always ask your agents, even they are busy working. docs.openclaw.ai/tools/btw

@Da7_Tech @steipete had no issues with Alibaba once I got around the maze of their ui

@steipete x.com/i/status/20326… Hey Peter, any update?

@steipete lossless-claw is amazing!

There's a lot of cool stuff being built around openclaw. If the stock memory feature isn't great for you, check out the qmd memory plugin! If you are annoyed that your crustacean is forgetful after compaction, give github.com/martian-engine… a try!

Spawns an isolated session with a model of your choice, with a bunch of fine tuning controls.

ACP is neat - seems pretty niche for most cases but still useful for discord-based OpenClaw agents

@flipsuitexyz like this

@kaish3n This was written by a human. Not AI.

Rugging and scamming is a people problem. Not a platform problem.

for now

this bot is free