Story Keeper – AI agents with narrative continuity instead of memory
Hi HN! Creator here. I built Story Keeper to solve a problem I kept hitting with AI agents: they remember everything but lose coherence over long conversations. The Core Idea Instead of storing chat history and retrieving chunks (RAG approach), Story Keeper maintains a living narrative: Characters: Who you are (evolving), who the agent is Arc: Where you started → where you're going Themes: What matters to you Context: The thread connecting everything Think of it as the difference between reading meeting notes vs. being in the relationship. Technical Approach ~200 lines of Python. Three…
In plain words
Story Keeper is an AI agent framework that maintains narrative continuity across long conversations by tracking characters, story arcs, themes, and context rather than storing chat history. Built in Python and compatible with any LLM, it keeps agents coherent by treating conversations as evolving stories instead of disconnected messages. It is for developers building AI agents that need to sustain meaningful context over extended interactions, particularly in applications like coaching or ongoing assistance where relationship continuity matters more than factual recall.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! Creator here. I built Story Keeper to solve a problem I kept hitting with AI agents: they remember everything but lose coherence over long conversations. The Core Idea Instead of storing chat history and retrieving chunks (RAG approach), Story Keeper maintains a living narrative: Characters: Who you are (evolving), who the agent is Arc: Where you started → where you're going Themes: What matters to you Context: The thread connecting everything Think of it as the difference between reading meeting notes vs. being in the relationship. Technical Approach ~200 lines of Python. Three primitives: Story State (not message list) Story Evolution (not appending) Story-Grounded Response (not retrieval) Works with any LLM - tested with GPT-4, Claude, Llama 3.1, Mistral. Why This Works Traditional memory is about facts. Story Keeper is about continuity. Example: Health coaching agent Normal: Generic advice each time Story Keeper: "This is the pattern we identified last month. You do better with 'good enough' than perfect." The agent carries forward understanding, not just data. Implementation Part of PACT-AX (open source agent collaboration framework). MIT licensed. Simple integration: pythonfrom pact_ax.primitives.story_keeper import StoryKeeper keeper = StoryKeeper(agent_id="my-agent") response = keeper.process_turn(user_message) Use Cases I'm Exploring Long-term coaching/mentorship Multi-session research assistants Customer support with relationship continuity Educational tutors that understand learning journeys What I'd Love Feedback On Is this solving a real problem or am I overthinking it? Performance concerns at scale? Other approaches people have tried for this? Use cases I'm missing? The full technical writeup is in the repo blog folder. Happy to answer questions!
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 · 18d 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 · 26d ago · cactuscompute.com
Launched alongside, October 2025
the whole month →
- SA
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
- ASAutism Simulator▲779
Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · Oct 2025 · autism-simulator.vercel.app
