🧠 Microscope Memory
A living, self-organizing cognitive memory engine for AI agents.
Not a database. Not a vector store. A system that learns, dreams, and remembers — written in 62,938 lines of pure Rust.
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A living, self-organizing cognitive memory engine for AI agents.
Not a database. Not a vector store. A system that learns, dreams, and remembers — written in 62,938 lines of pure Rust.
Hierarchical memory engine for AI agents. 9-level zoom (D0-D8), 13-layer consciousness architecture, sub-microsecond queries. Pure binary, mmap, SIMD. Spine Bridge REST API + MCP server. Zero JSON.
Microscope Memory is a cognitive memory engine that models how a biological brain remembers, forgets, and learns. It runs a 12-layer cognitive architecture across 9 hierarchical depths (D0–D8) with 1.28 million blocks — all backed by pure binary (mmap, SIMD, zero JSON).
Think of it as the hippocampus + neocortex + amygdala rolled into a single 3 MB Rust binary.
Traditional AI systems treat memory as a database — fetch, store, query. But real intelligence is not about retrieval accuracy. It is about:
This engine was built to experiment with those biological principles at scale — and to make them available to any AI agent that needs a real memory, not a lookup table.
Built by Máté R. — a researcher who started as a factory worker (6 days/week, rotating shifts) and taught himself to code 2 years ago. His work on wave-quantum is hardware-validated on real superconducting QPUs (IBM Fez, Marrakesh, Kingston — 156Q Heron r2, Pearson 0.99+). The same rigor of falsification, pre-registration, and statistical validation is applied here.
# Native build (release — approx. 2.5 min on a modern CPU)
git clone https://github.com/silentnoisehun/microscope-memory.git
cd microscope-memory
cargo build --release
# Quick test
./target/release/microscope-mem store "hello world" -l session -i 5
./target/release/microscope-mem recall "hello"
cargo build --target wasm32-unknown-unknown --release \
--features wasm --no-default-features
wasm-pack build --target web --release \
-- --features wasm --no-default-features
docker build -t microscope-memory .
docker run -p 8080:8080 microscope-memory
The system computes a gradient at every cycle to decide where and how to grow:
gradient = w₁·relevance + w₂·resonance + w₃·evidence
+ w₄·hebbian + w₅·prediction + w₆·emotion + w₇·execution
effective_gradient = positive_gradient × (1 − absence_shadow)
The shadow term prevents growth toward areas with weak evidence, without blocking exploration entirely.
The seven-component cognitive gradient drives every learning decision. Bottom-up causality: node → path → organism → field → phase. Top-down: phase → field → growth rule → path → node.
All figures are measured on release builds (in-process A/B runs, warm-up discarded):
Honest boundaries: The end-to-end CLI is dominated by process startup (~17 ms floor), so user-visible
findimproves modestly. In-loop paths (bridge, MCP, benchmarks) improve by ~10×.
e0cea99, 12-core Ryzen 5 7535HS)These are single-observation measurements from BENCHMARKS.md — recorded on one machine, not a distribution. The query set was not retained, so recall numbers cannot be re-derived.
See BENCHMARKS.md for full methodology, χ² goodness-of-fit (95% confidence), and the 2Q parity analysis (95% χ²red).
# Memory Operations
microscope-mem recall " query " # Top-5 recall
microscope-mem store " text " -l session -i 5
microscope-mem find " pattern "
microscope-mem stats
microscope-mem verify
# Cognitive Morphogenesis
microscope-mem morphogenesis status
microscope-mem morphogenesis run
microscope-mem morphogenesis adversarial
microscope-mem morphogenesis deep-adversarial
# Absentia (Silence Layer)
microscope-mem absentia status
microscope-mem absentia scan
microscope-mem absentia anti-hebbian
microscope-mem absentia causal-laundering
# Intent Pipeline
microscope-mem intent generate
microscope-mem intent genome
# Other Cognitive Commands
microscope-mem hebbian
microscope-mem resonance
microscope-mem patterns
microscope-mem hottest 5
microscope-mem dream
microscope-mem autonomous
Microscope Memory ships with a native MCP server built on the rmcp
crate. Two transports are available:
The stdio server implements the full JSON-RPC 2.0 framing by hand (protocol
version 2024-11-05) with 47 tools covering store, recall, spatial look,
MQL query, session log, Hebbian learning, emotional field, dream
consolidation, and more.
The Streamable HTTP server uses rmcp's StreamableHttpService and speaks
protocol version 2026-07-28 (compatible with 2025-11-25 and 2024-11-05).
It exposes the core tools — memory_status, memory_store, memory_recall,
memory_find, memory_look, memory_mql_query, memory_session_log,
memory_ping, memory_build, and memory_speak (text-to-speech via system SAPI).
[server].api_key is set in config.toml, every
request must carry it via the x-api-key or Authorization: Bearer <key>
header.[server].cors_origin is set, cross-origin
requests whose Origin header doesn't match are rejected (DNS-rebinding
protection).Mcp-Session-Id header handling via
LocalSessionManager (stateful + stateless modes).{
"mcpServers": {
"microscope": {
"command": "/path/to/microscope-mem",
"args": ["mcp"]
}
}
}
# Start the server (requires --features mcp_http)
cargo build --release --features mcp_http
./target/release/microscope-mem mcp-http --host 127.0.0.1 --port 8080
# With API key (set in config.toml under [server])
curl -H "x-api-key: your-key" http://localhost:8080/mcp
# MCP client .mcp.json (Streamable HTTP)
# For Cursor, Claude Code, etc.:
{
"mcpServers": {
"microscope-http": {
"type": "http",
"url": "http://localhost:8080/mcp",
"headers": {
"x-api-key": "your-key"
}
}
}
}
# Start the HTTP bridge
microscope-mem --serve-http --port 8080
# API endpoints
curl http://localhost:8080/recall?query=hello
curl -X POST http://localhost:8080/store -d '{"text":"hello","layer":"session"}'
import { MicroscopeWasm, HopeCli } from './microscope_memory.js';
const mem = new MicroscopeWasm();
await mem.loadBinary(meta, headers, data);
const results = mem.recall("quantum computing", 5);
cargo test # All tests (451 lib + 88 integration)
cargo test --lib # Library tests only
cargo test --test integration
microscope-mem morphogenesis adversarial # Basic (8/8 PASS)
microscope-mem morphogenesis deep-adversarial # Deep (7/7 PASS, 5 warnings)
microscope-mem morphogenesis presence-absence-test
cargo test -p microscope-hooks # 16 hook tests
I'm an independent researcher working at the intersection of quantum information theory and neuromorphic AI. My work is:
# Native
cargo build --release
# With semantic embeddings (BERT/ONNX)
cargo build --release --features "native,embeddings"
# With Streamable HTTP MCP server
cargo build --release --features mcp_http
# WASM
cargo build --target wasm32-unknown-unknown --release \
--features wasm --no-default-features
Note: Without the
embeddingsfeature, semantic recall falls back to a mock provider. The build succeeds but will refuse to return meaningless results — verifydata/embeddings.binexists before measuring. Available providers:mock(hash-derived, default),candle(BERT),onnx. Seescripts/eval_real.shfor reproducing published retrieval numbers.
MIT — see LICENSE.
Hierarchical memory engine for AI agents. 9-level zoom (D0-D8), 13-layer consciousness architecture, sub-microsecond queries. Pure binary, mmap, SIMD. Spine Bridge REST API + MCP server. Zero JSON.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Microscope Memory 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 Hierarchical memory engine for AI agents. 9-level zoom (D0-D8), 13-layer consciousness architecture, sub-microsecond queries. Pure binary, mmap, SIMD. Spine Bridge REST API + MCP server. Zero JSON.