曦曦曦
31 posts
Spent the last 48 hours improving @AnsemClone
Here is a deeper look at the tech behind it all.
1. In-Process Retrieval
The clone can search its full historical memory without relying on an external database.
Ansem’s historical tweets are embedded ahead of time and loaded directly into the application. When the clone prepares a response, it searches that corpus in memory instead of calling an external vector database. For a dataset of this size (250K) the simpler architecture works better. Retrieval is faster, there are fewer network calls, and there is less infrastructure to maintain. It also removes failure points caused by service outages, connection issues, and indexes falling out of sync.
2. Incremental Memory Updates
New tweets become part of the clone’s memory automatically while the system is running.
Every six hours, the system checks for new tweets from Ansem @blknoiz06 . It filters out anything already processed, generates embeddings for the new material, and adds them to the live corpus. There is no need to rebuild the full archive or redeploy the application. New tweets become searchable as soon as they are ingested. This allows the clone’s memory to evolve alongside Ansem’s views, language, and interests instead of slowly becoming a frozen snapshot.
3. Multi-Source Context Assembly
Each response combines long-term memory with current events and information relevant to the conversation.
The generation pipeline uses three inputs:
/ relevant historical tweets,
// live market context from Grok Agent Tools,
/// retrieval tied to the topic being discussed.
Each source solves a different problem.
Historical memory provides continuity.
Live context keeps the clone aware of what is happening today.
Topic retrieval narrows the available information to what matters for the current conversation.
A good example of this working organically and staying up to date was when @AnsemClone naturally posted about,
"everyone chasing the next chain, next narrative"
Combining all three gives the model a stronger factual base and reduces the amount it has to infer or invent.
4. Layered Safety
Several independent checks must approve a response before the account can post it.
The system uses four safety layers to screen for shilling requests, contract addresses, financial advice, prompt injection, wallet drain attempts, and other unsafe inputs.
These checks run at different stages of the pipeline. That matters because no single classifier, filter, or system prompt will catch every attack. A harmful request has to pass several independent controls before it can reach the posting stage. This reduces the chance that one missed signal becomes a public reply.
5. Reliable Autonomous Posting
The system can recover from crashes and API failures without losing work or posting duplicate replies.
Each reply is tracked from discovery through generation, safety review, and publication. That state is stored in a restart-safe way, which allows the application to recover after a crash without forgetting what it has already processed. The pipeline also uses exactly-once reply semantics. Each eligible tweet should receive one reply, even when an operation has to be retried. External APIs are treated as unreliable by default, so the system can handle timeouts, rate limits, incomplete responses, and uncertain delivery states without bringing down the full process.
TLDR Outcome:
Our Clone can now ingest new memory, gather live context, retrieve relevant history, generate a response, run several safety checks, publish it, and recover from common failures without constant supervision all at scale and in real time.
The reply is just the visible output.
The real challenge was making everything behind it simply work.
English
English
$Clude pump and dump instantly all time like $AgenC. Both @sebbsssss and @tetsuoai is a fuking farming scammer. @elonmusk should ban them
English
曦曦曦 retweetledi
etf outflows don't care about your feelings bro
zoom out, believe in something
English
EVAA Agent version 1.0 is coming soon 🥳
We're building an AI Agent directly into the EVAA app, and it's almost ready!
It will work with the wallet connected to EVAA, so the answers are based on real context: balances, positions, current pool rates, and available strategies.
Instead of switching between data, docs, and protocol actions, users will be able to ask what they can do next — and get a response shaped around their actual EVAA position and the wallet balance.
When you decide to take action, EVAA Agent can assemble the transaction and send it to your wallet for signature.
😍 The agent helps prepare the action.
👍 You review it, sign it, and keep control of your keys.
ℹ️ Security first. Every transaction remains visible and manually approved by the user before anything happens on-chain.
From day one, EVAA Agent will help users navigate DeFi strategies on TON, understand their position context, and prepare supported EVAA transactions.
Agentic DeFi has mostly been an Ethereum and Base story so far. We want TON to have its own, and it starts inside EVAA. Where it goes from there... Telegram is a big place 👀
DeFi as a dialogue launching soon on EVAA!
English
曦曦曦 retweetledi
