The Last RAG
AI that learns autonomously and remembers everything
What it does
Solo dev. 6 months. Built what research teams write papers about. AI that remembers. Not facts. Context. Emotion. WHY things matter. Brings up in December what you said in January. Knows your victories, failures, fears. No fine-tuning. No giant context windows. No manual curation. Autonomous learning. Deletes old memories. Modifies its own system prompt. By itself. OpenAI builds tools. I built partners. Uncensored. No filters. Your AI. Your rules. Live. Today. Production.
Does a similar job
all alternatives →
- AMAI memory with biological decay (52% recall)Apr 2026 · github.com · ▲98
Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning. This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned. To solve the…
- CACreated an AI for myself to achieve goals, it might help you guys tooJan 2026 · zropi.com · ▲6
I'm a Machine Learning engineer. Struggled with consistency for months on my goals, life etc, so I built something to help myself (zropi.com) but that surprised me or shocked me literally. It’s an AI companion that feels alive: chats like a person. Pauses, emotions, personality. Sends voice notes when it's excited about something or whenever it wants (has its like own mind). Shares photos of itself. But the memory It remembers EVERYTHING. Not just facts context, preferences, random things I mentioned. Last week I asked "how's that thing I told you about going?" and it knew exactly what I…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology