Mwe-MCP – self-hosted memory for AI agents that knows who may know what
Hi HN, for about a year now I've been experimenting with AI agents and building my own home ecosystem; from the start I set out with the idea of an agent that behaves like a member of the family, not as a personal agent, and this made me clash very early first with OpenClaw's builtin memory, then I tested dozens of memory plugins without ever finding one that fit my purpose, so like any good builder I made my own. First on OpenClaw, as a plugin, then the idea matured and since the beginning of this year the memory plugin has evolved into an agent agnostic MCP server. It has been running my…
What it does
Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL. - Fr4nZ82/mwe-mcp
In the maker’s words, at launch
Hi HN, for about a year now I've been experimenting with AI agents and building my own home ecosystem; from the start I set out with the idea of an agent that behaves like a member of the family, not as a personal agent, and this made me clash very early first with OpenClaw's builtin memory, then I tested dozens of memory plugins without ever finding one that fit my purpose, so like any good builder I made my own. First on OpenClaw, as a plugin, then the idea matured and since the beginning of this year the memory plugin has evolved into an agent agnostic MCP server. It has been running my household since spring, 4 people and 3 agents on the same memory. The core idea that sets this project apart is the addition of inline ACLs on the prose of the wiki pages; the inspiration came to me, in all honesty, when social media was full of the redacted documents from the Epstein files; the wikis are written like that, every paragraph, every item of a list, every sensitive piece of data has its own ACL, which is applied already during the autocapture of messages and at the ingest of documents and media. In practice: my partner can tell the assistant something and our kid can't get it out of it, "we're out of milk" belongs to the whole household and not to me; the same page is served differently to each reader, redacted by the engine before any text reaches the agent. Memory is organized into wikis, every user, group and agent has their own wiki and other wikis can emerge autonomously. To reach this goal the server uses various components that use configurable LLMs, from the simple dedup, which you can easily run locally, to the reconciler that works during the REM phase (yes, there's a light dream and a REM dream) and reorders the pages that during the day, for efficiency, may have been written roughly. Engineering wise it's a single Rust binary, MCP endpoint (Streamable HTTP, with OAuth) and admin dashboard on the same port. Recall is just as important: an initial RAG pass finds the entry doors into the various wikis, then the "navigator" follows the links of each page that fit the purpose of the search, to get the whole context of the data being looked up or the topic being discussed; this funnel navigation itself creates the context, ready to hand to the connected agent, and since it follows text written as prose it also surfaces stray memories, that is, memories nobody asked for but that can be important in the context being discussed, for example a user who once specified a food intolerance, when the agent is asked for a recipe for the group that user belongs to. The prose isn't there for beauty or for humans to read, the prose links the facts, so that no fact is disconnected from the rest but everything is part of one huge narrative, which is however made extremely efficient by the metadata. These are the peculiarities, for the rest I took the best of what I found in the other existing memories and integrated it. Now I've realized that this memory system, initially born for a family, can be great for a team too and, with some future adjustments, even for small and medium businesses. Honest limits: the internal LLM needs a reasonably capable model (small local ones route poorly, it's documented), and Windows support is best-effort for now. The repo is mostly vibe-coded, I'm aware of it, but I've been a developer since the last millennium and I would never have managed to finish it in a reasonable time; anyway it's in production and I've been using it for months, fixing the problems as they come out. License: AGPL, self-hosting is free forever; the sustainability model is a commercial license for closed SaaS cases. Now I'm simply looking for people who can put it to the test, maybe someone who has a team or wants to try it with their family, but it also works for a single user with several agents. Built for my family, released for yours. https://github.com/Fr4nZ82/mwe-mcp
Does a similar job
all alternatives →
- MAMcp-Agent – Build effective agents with Model Context Protocol2025 · github.com · ▲80
Hey HN, I spent my xmas break building an agent framework called mcp-agent [1](https://github.com/lastmile-ai/mcp-agent) for Model Context Protocol [2]. It makes it easy to build AI apps with MCP servers, and implements every pattern from the popular Building Effective Agents blog [3] as well as OpenAI’s Swarm [4]. I’m sharing it early to get community feedback on where to take it from here, and to ask for contributions. For those who aren’t familiar with MCP, I think of it as a standardized interface to let AI communicate with software via tool calls, resources and…
MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS525d ago · github.com · ▲70An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory
Remote OpenClawJul 2026 · codexmarketplaces.com · ▲8113,000+ MCP servers, skills & plugins for AI coding agents
- IMI made an open-source memory layer for agentsMay 2026 · agentrecall.cloud · ▲8
Store memories, auto-extract entities and relationships, search semantically. MCP server + REST API + SDKs. Self-hostable, cloud option, MIT license.
systemprompt - AI Agent InfrastructureFeb 2026 · github.com · ▲11Love OpenClaw? Now ship it to production. Built in Rust.
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 · 18d 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 · 28d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
18 Words▲1,160Play 18 Words, the free daily word puzzle. The official home is 18words.com. Tap Play now to open today
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
