Collabmem – a memory system for long-term collaboration with AI
Hello HN! I built collabmem, a simple memory system for long-term collaboration between humans and AI assistants. And it's easy to install, just ask Claude Code: Install the long-term collaboration memory system by cloning https://github.com/visionscaper/collabmem to a temporary location and following the instructions in it. To collaborate with AI over weeks, months, or even years, there needs to be a shared conceptual understanding of: - History (episodic memory): what has been done, why, and what was decided and learned along the way. - Reality (world model): what the…
In plain words
Collabmem is a memory system that enables long-term collaboration between humans and AI assistants by maintaining shared episodic memory and world models across extended projects. It stores the history of work completed, decisions made, and lessons learned, along with project context, current status, and guidelines. The system is designed for users who want to sustain productive AI partnerships over weeks, months, or years by giving AI assistants persistent understanding of their project's background and constraints.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hello HN! I built collabmem, a simple memory system for long-term collaboration between humans and AI assistants. And it's easy to install, just ask Claude Code: Install the long-term collaboration memory system by cloning https://github.com/visionscaper/collabmem to a temporary location and following the instructions in it. To collaborate with AI over weeks, months, or even years, there needs to be a shared conceptual understanding of: - History (episodic memory): what has been done, why, and what was decided and learned along the way. - Reality (world model): what the project is about and in what context, the current state of the work, how it should be done, and what the guidelines, preferences, and constraints are. Without this conceptual knowledge and context built up over time, the AI can't work effectively; it can't respond well or make good choices when writing code, producing a design, or doing anything non-trivial. I don't think the future is just about making AI agents run autonomously for ever-longer stretches. Long-term human-AI collaboration is pivotal: it's how the AI builds up the project history and world model it needs to be effective, and it's how we humans keep track of what's being done. AI will certainly work more autonomously over time, but even then, we need ways for humans to see what was done and why. That's what collabmem enables. It builds up episodic memory and a world model over time. A compact index of every memory entry is always loaded in the AI's context window, giving the model a global awareness of everything in memory; it can associate across entries and knows where to look when it needs the details. The system uses three sentinel tokens — readmem, updatemem, maintainmem — as the primary way to interact with memory. Drop one into your message and the AI reads memory, proposes updates, or runs maintenance. You approve; nothing is written silently. Underneath, the design is deliberately simple. The memory is plain-text files you can inspect, git-track, and share; so teams, or even entire organizations, can build up shared knowledge with AI through distributed collaboration. No databases, no vector stores, no infrastructure; just files and a methodology the AI follows. It works with any AI assistant that can read and write files, though so far it's optimised for Claude Code. I'm looking for developers, researchers, or anyone running long-term projects with AI to try it and share feedback. Thank you! Written in collaboration with Claude Opus 4.6 (1M)
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, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app