I Built an AI Memory Agent That Forgets on Purpose — Then Spent Two Days Proving It Actually Works A developer built Synapse, an AI memory agent with intentional forgetting, for the Global AI Hackathon Series with Qwen Cloud. The system uses decay math, contradiction detection, and consolidation to outperform naive vector storage, and was benchmarked against the naive approach to prove its effectiveness. Every "AI memory agent" I looked at before starting this does the same trick: embed every message, dump it in a vector database, retrieve the top-k most similar chunks at query time. That's not memory. That's a search index. It never forgets anything, it treats "nice weather today" with the same weight as "I'm allergic to penicillin," and it gets slower and dumber the longer it runs because retrieval gets noisier with every near-duplicate you never clean up. For the Global AI Hackathon Series with Qwen Cloud Track 1: MemoryAgent , the brief asked for three specific things: efficient storage and retrieval, timely forgetting of outdated information , and recalling critical memories within a limited context window. That middle one is the one almost nobody builds, because naive vector storage has no concept of "outdated." So I built it — real decay math, real consolidation, real contradiction detection — and then benchmarked it against the naive approach to prove it actually works, instead of just claiming it does. This is the story of building that, on Qwen Cloud, in about two days, including the parts that broke. Every memory Synapse stores gets a salience score that changes over time: salience t = importance score recall boost recall count exp -lambda hours since last recall recall boost n = 1 + log 1 + n lambda = ln 2 / half life hours Two things matter here. First, importance score isn't a keyword heuristic — it's a real structured-output call to Qwen at write time, scoring the memory on explicit signals "remember this" , decision-relevance is this the kind of fact that should change future behavior? , and specificity. Second, the half-life isn't a single global constant. Episodic details — what you mentioned on a random Tuesday — decay in about 72 hours unless reinforced. Semantic facts — stable preferences, "I'm vegetarian" — decay over 30 days. That asymmetry is the whole point: the system should forget what you talked about, not what you told it matters. On top of decay, a background "sleep pass" does two more things a naive vector store can't: Every LLM call in this project — chat replies, importance scoring, memory extraction, contradiction judgment, cluster summarization, and even the benchmark's own LLM-as-judge scoring — goes to a real Qwen Cloud endpoint. No mocked responses, anywhere, including in the benchmark. That was a hard rule I set for myself: if a mechanism didn't work for real, I'd cut the claim rather than fake the output. Getting there wasn't instant. Qwen Cloud's OpenAI-compatible endpoint is workspace-specific — not the generic host you'd expect, but a ws-