Eros
Episodic memory for the autonomous AI agents
What it does
AI Agents are stuck in a "Permanent Present." Every time you ask an agent to perform a recurring task— it starts the execution from scratch. This makes agents slow, expensive, and unpredictable. The Solution: The Episodic Plan Cache is the memory layer that gives AI agents a "Reflexive Memory." Instead of generating a new execution graph for every request, it indexes successful past outcomes. When a similar intent is detected, it hydrates a proven plan in milliseconds instead of re-generates.
Does a similar job
all alternatives →
Agent Memory SystemMay 2026 · ravbyte-ai.github.io · ▲9Open Source Context Infrastructure for AI Agents
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
