meme-sniper

This is a measurement instrument, not a trading bot, and the distinction is the whole design. Phase one is meant to produce a number, not a strategy. It is recording now and has no results yet, which is the correct state for it to be in.

Why record before modelling

On 21 July 2026, pump.fun shipped a mechanism called BOOST that reinjects previously dead liquidity as post-migration buybacks and burns. Graduation rates moved from around 0.2% to somewhere between 4.7% and 6.7%, roughly eightfold.

Every published threshold, heuristic and model for this market predates that change and is calibrated against a mechanism that no longer exists. You can still find them, and they will still fit beautifully to historical data drawn from a regime that is gone.

So the first job is not to build a model. It is to measure what the market looks like now, from scratch, and treat every inherited constant as suspect until re-measured. That is an unglamorous decision and it is the one I would defend hardest, because the alternative is fitting confidently to the wrong world.

A funnel shaped by what is free

Free-tier API quotas are the binding constraint, so the architecture is four tiers with the budget spent only on survivors.

Tier	Population	Cost	What happens
0 Firehose	every launch, 36k to 65k a day	free	record raw, no filtering
1 Metadata	5 to 15%	free	resolve the metadata URI to socials
2 Enrichment	1 to 3%	rate-limited	deployer history, holder concentration
3 Tracked	~0.1%	RPC polling	curve velocity, score, paper trade

The shape is not arbitrary. Tier 1 carries the strongest published signal in the space, and it costs one HTTP GET: across 832,941 launches, tokens advertising a Telegram graduated at 1.485% against 0.166%, and tokens carrying all three social channels at 1.919% against 0.110%. Roughly nine times and seventeen times respectively, for free, on the cheapest tier in the funnel.

There is also a clear statement of where an edge cannot come from. Bundle snipers own the first two blocks after a launch and no free-tier setup will ever beat them there. What is potentially winnable is a selection edge on a thirty second to five minute horizon, using how few trades it took to reach a given liquidity level as a proxy for large-ticket conviction rather than bot churn. Knowing which race you are not entering is worth as much as knowing which one you are.

Reading the curve rather than the documentation

The bonding-curve constants were measured against live frames instead of taken from docs. Virtual SOL opens at exactly 30.0, virtual tokens at 1,073,000,000, and their product holds as an invariant across every launch observed, with a worst-case residual of 1.2e-16, which is floating-point noise.

That precision buys something concrete. Create frames report state after the developer’s own pre-buy, so subtracting the opening constant from the reported virtual SOL gives you exactly how much the deployer bought of their own token, at time zero, with no RPC call and no cost. One of the most direct rug signals available is sitting in a field that looks like a constant until you check.

Those constants are pinned in tests against real captured frames. If pump.fun changes a curve parameter, the test suite fails, rather than the features quietly becoming wrong while everything continues to look fine.

What the stream does not tell you

The empirical notes are the part of this repository I would show first, because every entry is something that would have poisoned the dataset silently.

One stream carries two venues. A second launchpad shares the subscription with a different payload shape, so classification branches on the pool field rather than on anything that looks like a naming convention.

There is no timestamp. The stream does not carry one, so arrival time is our clock, not the chain’s. Any real timing feature has to resolve block time from the signature, and treating receipt time as truth would bake network latency into the model.

Instant-bond bundles exist. One token had its creation and its migration twenty-four milliseconds apart: a create plus a full curve buy in a single bundle. It was never buyable by anyone and it is not organic demand, but to a naive model it is the most successful launch in the dataset. Left in, it teaches the model that graduating fast is good. It is detected and excluded.

Graduation rate is a cohort question. Dividing migrations by launches over the same window is wrong, because most migrations observed belong to tokens launched before the recorder connected. Only cohort-based rates get reported.

The creator is not always the signer. The on-chain creator field disagrees with the transaction signer in ten to twenty-five percent of samples, because proxies and bundlers sign on someone else’s behalf. Any deployer-history feature has to decide which identity it keys on, and the disagreement is itself a candidate signal.

Serial spam is the dominant behaviour. In one seventy-five second window a single creator launched five tokens under one symbol, and two mints shared an identical name, symbol and metadata URI seconds apart. A duplicate creator-plus- URI pair is a free spam filter.

The kill criterion

Written down before collection began: if three weeks of paper trading comes out negative once a realistic two percent round-trip cost is applied, the conclusion is that no edge exists at this latency tier, and the project stops or changes approach.

It is in the repository, agreed in advance, so the result cannot be graded on vibes afterwards. That matters more than usual here. The base rate before the protocol change was that roughly 0.2% of tokens graduated, and one study found 98.6% of launches carry pump-and-dump signatures. This is a domain that will happily show you a pattern in noise and let you fund it.

No real money is involved at any point. Paper trading only, no hot wallet, free API tiers throughout.

Where it is

Live on a small EC2 instance since 5 August 2026, running under systemd with Litestream replicating the database off the box, plus a periodic local pull. The deploy runbook covers the free-tier account expiry that would otherwise silently end the collection.

Tier 0 and tier 1 are running. Tiers 2 and 3, the scorer, the paper-trading ledger and the analysis are not built yet, and there is no point building them against a fortnight of data.

The value of this thing compounds with wall-clock time and nothing else. Right now the honest status is that it has been collecting for a week and a half, the viability question is open, and the answer arrives when there is enough data to answer it rather than when I would like to have it.