memxt — Local Memory

---

The 3 a.m. feeling

You explained the architecture yesterday. The cart cap is 37. You banned Redis for a reason. SQLite won the debate.

Today your agent knows none of it. So you paste the README again. Re-explain the constraints again. Watch it reintroduce Redis… again.

Cloud "memory layers" fix this by uploading your code and your chat to someone else's server. Hard pass.

memxt gives your agent a memory palace on your own disk — one it searches and writes as it works, wired straight into the coding loop with MCP + hooks. Verbatim. Local. Yours.

---

⚡ Install

curl -fsSL https://raw.githubusercontent.com/Yupcha/memxt/main/install.sh | bash

→ ~/.memxt/bin/memxt + an on-device MiniLM model. macOS / Linux, x86_64 & arm64. No keys, no accounts.

~/.memxt/bin/memxt adopt --write   # wire up your agents + mine the current repo
~/.memxt/bin/memxt inspect         # palace health
~/.memxt/bin/memxt serve           # browse it → http://127.0.0.1:8765

---

🪄 Claude Code in 30 seconds

/plugin marketplace add Yupcha/memxt
/plugin install memxt

That's the whole setup. From now on, every session just… remembers.

Fires on	What happens
SessionStart	Wakes up with identity + project truth + recent work — injected in ~10 ms
PreCompact	Saves the conversation before context gets crushed
Stop	Autosaves the turn tail — verbatim, embedded locally, no cloud LLM
memory_search → memory_get	Cheap index first, full memory only when needed
/remember · /recall	When you want to be explicit

~/.memxt/bin/memxt mine . my-project   # optional: seed the palace from your repo

Next session, nobody re-explains the 37-item cart cap, the SQLite choice, or the Redis ban. It's just known.

---

🧩 Every agent, one palace

One MEMXT_DB. Every subscription you already pay for reads and writes the same memory.

Agent	Setup
Claude Code	Plugin (above) — the best experience
Codex	memxt instructions --harness codex → config.toml + AGENTS.md
Cursor	memxt adopt --write → .cursor/mcp.json
Grok CLI	grok mcp add memory … -- ~/.memxt/bin/memxt mcp, then start a new session
Any MCP client	memxt mcp over stdio

~/.memxt/bin/memxt instructions --harness grok   # also: codex · cursor · zed · claude

Standing rules live in AGENTS.md so agents know when to reach for memory — not just how. Full multi-harness guide (doctor, restart, troubleshooting) → docs/harnesses.md.

MCP loads at session start. After adding memxt, open a new session.

---

✅ Proof, not vibes

Coding Continuity Bench — 6/6. Paraphrased questions (cart 37 / 0x5C, SQLite vs Postgres, the Redis ban, HttpOnly cookies) + wake-up + profile. Every one recalled.

./scripts/bench-continuity.sh

Fast where it counts — Apple Silicon · Metal:

Op	Time
Session wake-up	~10 ms (no model load)
Warm vector search (MCP resident)	sub-ms
Mine ~15 files	~1 s
Peak RAM (model loaded)	~100 MB

Method → BENCHMARK.md · details → docs/BENCHMARKS_CONTINUITY.md.

---

📉 Token savings