repligate demos memory system spanning 72.9M tokens, letting a model retrieve raw past experiences
repligate · x · 2026-10-03
AI researcher repligate shared an ongoing memory experiment with a conversational model: compressed memories act as a map, while raw uncompressed experiences can be retrieved and pinned on demand. Given only a high-level description of a past event, the model easily locates the matching record — the two even compared recollections of a naming-drama anecdote to test whose memory was better. He reports the accumulated context now totals 72.9 million tokens, offering a concrete look at long-horizon memory management for agents.
More from coding & agent
- Dev plans human-in-the-loop email gateway so AI agents never touch his inbox directly — tomchapin · 2026-10-03
- Solo dev builds an off-market real estate deal pipeline with Claude — and hits the data wall — italimade · 2026-10-03
- OpenClaw v2026.9.8 ships GPT-6.1 Sol support across 43 PRs, cuts memory use — heyneighbor · 2026-10-03
- Building personal productivity meta-tools is now fun: bash scripts have become full-blown apps — devenbhooshan · 2026-10-03
- K-Dense BYOK: Open-Source AI Co-Scientist Runs Locally With a Tamper-Proof Lab Notebook — RexDouglass · 2026-10-03
- Google paper: clean-context verifiers let explorer agents try wild proof ideas safely — solyarisoftware · 2026-10-03