An agent's window is a lens, not the store. Neomonic is the store: typed memos under topics under contexts, recalled by the keyphrases the agent already holds.
Every memo is one typed fact with a key. The agent keeps the keys hot in its window and pulls the payload only when a question needs it. That is the whole discipline, and it is what keeps a long-running agent from forgetting.
One fact per memo, typed by what it is: a person, a place, a time, an action, a thing. Payloads go to the store, not the prompt.
memory.add caroline, moving, mv-denver, moved to Denver in MarchLoading a context loads its keyphrase cache: a few hundred bytes the agent carries between turns instead of the memos themselves.
memory.cachekeys carolineA question is matched against the keys first, the full-text index second. The hit comes back as the memo, with its type and its time.
memory.modelkeywords caroline, who helped with the moveBuilt as the memory module of the 0verload tool federation: one C++ binary, no runtime, no cloud, the on-disk store yours to copy, version and inspect.
A context is one person, project or agent. Topics are its chapters. Memos are the facts, each with a key, a type and a timestamp.
Every memo anchors to the most specific date it carries, so "last spring" and "before the promotion" are questions the store can answer.
A trained word net reads each memo and keeps the words that carry it: names, places, times, actions, things. Those words, paired, are the keys the index runs on.
The word net trains on any OpenCL GPU, NVIDIA, AMD or Apple silicon, with nothing to install, and serves on a plain CPU anywhere. One model file either way.
Every save of every enrolled file is a version. Memory that can be rolled back is memory you can let an agent write to.
Every verb is a tool over the Model Context Protocol, so Claude Code, Cursor or any MCP client gets persistent memory in one config line.
BEAM, LoCoMo and LongMemEval, run in mem0's own open-source benchmark harness with only the memory search swapped for Neomonic's. GPT-5 answers and GPT-5 judges. Each figure is the mean of repeated runs, compared against mem0's published numbers.
Runs vary by up to 1.5 points, so smaller gaps count as level. The full results, the method, and every question with its answer and verdict →
Register the server once. The agent then recalls before it assumes it is starting fresh, and saves durable facts as it works, so they outlive the window.
// claude_desktop_config.json / .mcp.json { "mcpServers": { "neomonic": { "command": "0neo", "args": ["mcp"] } } } // or over HTTP, served by the resident "url": "http://127.0.0.1:9966/mcp"