Wax
christopherkarani810 ดาว
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
- ทรานสปอร์ต
- stdio
- สถานะ
- โลคัล
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
remember / recall. If this is the memory layer you wanted, star the repo so other agents find it.Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
Wax is a shared memory file for agents and on-device models.
Claude Code ─┐
Codex ───────┤
Cursor ──────┼─ MCP ─→ one HTTP writer ─→ ~/.wax/memory.wax
Grok ────────┤
OpenClaw ────┘
Hermes ──────── native wax-memory provider ─↗
iPhone / Mac app ── Memory + Foundation Models tools ─↗
The store is one file. Documents, FTS5 text search, CoreML vectors, and a WAL live inside it. iCloud or AirDrop the file to another Mac or iPhone. Identical MCP servers share one broker daemon automatically; a differently-configured second process fails fast with sharing guidance, so two or more hosts share http://127.0.0.1:3000/mcp.
What you get that a host scratchpad does not:
remember does not call an LLM to extract facts. You store a sentence; hybrid search finds it later.waxRemember / waxRecall / waxSearch as on-device tools.MEMORY.md curation and use the native wax-memory provider (handoffs, turn sync, wax_remember / wax_recall).Host playbook: wax-mcp-hosts.md
Give Claude Code, Cursor, Codex, Hermes, OpenClaw, Muse Code, or Windsurf a memory that survives the chat.
Installing the server is not enough. Hosts ignore MCP tool descriptions unless an always-on file says when to write. Paste a block below after you wire the host.
npx -y waxmcp@latest install
Claude-only can use stdio. Two or more clients must share one HTTP server on http://127.0.0.1:3000/mcp. A differently-configured second process on ~/.wax/memory.wax fails fast instead of locking silently.
Keep HTTP up with ~/.local/share/waxmcp/bin/start-wax-mcp-http.sh or LaunchAgent ai.wax.mcp-http. Prove it with npx -y waxmcp@latest vector-health, npx -y waxmcp@latest doctor (wax-cli mcp doctor), hermes wax-memory doctor, and hermes plugins doctor wax-memory. Native recall defaults to the current project; pass scope=global for person facts. Global is not an authorization boundary.
Full snippets, LaunchAgent ai.wax.mcp-http, vector-health, Hermes doctors, and a smoke test: Resources/docs/wax-mcp-hosts.md.
The wax-mcp skill is install/doctor only. The wax skill is Swift SDK integration. Daily memory follows MCP server instructions, not either skill.
Pick the file your host actually loads on every turn.
Use the project or user AGENTS.md, CLAUDE.md, or .cursor/rules. Same text as Resources/skills/public/wax-mcp/references/project-rules.md.
Follow the live Wax MCP server instructions for `remember`, `recall`, and `stats`. Do not invent a `session_id`. Do not load the `wax` or `wax-mcp` skills at session start. `wax` is Swift SDK only; `wax-mcp` is install/doctor only.
OpenClaw: the workspace SOUL.md. Native Hermes already owns session lifecycle. Call wax_remember / wax_recall / wax_stats. Do not pass a Wax session_id. Do not paste the MCP session_open loop. Omit mode unless you need an override. Omit scope for current-project recall; pass scope=global for person facts. Empty project recall is a miss. Do not add wax-memory to plugins.enabled.
SOUL.md is identity. Append this section if missing. If ## Memory (Wax) already exists, replace that section. Do not replace the rest of the soul.
## Memory (Wax)
You have Wax. Follow the live MCP server instructions for `remember`, `recall`, and `stats`. Do not invent a `session_id`. Do not load wax-mcp at session start.
Native Hermes already owns session lifecycle. Call wax_remember / wax_recall / wax_stats. Do not pass a Wax session_id. Do not paste the MCP session_open loop. Omit mode unless you need an override. Omit scope for current-project recall; pass scope=global for person facts. Empty project recall is a miss. Do not add wax-memory to plugins.enabled. OpenClaw still pastes the SOUL.md stanza.
Grokbot runs locally on your Mac, so Wax serves it over loopback. No tunnel. No cloud copy of your memory.
One-time setup:
# 1. Stage Wax
npx -y waxmcp@latest install
# 2. Start the server and keep it running (add to your shell profile / login items)
~/.local/share/waxmcp/bin/start-wax-mcp-http.sh
Then in Grokbot: Settings → Plugins → Add MCP server
Finally, paste this prompt into your main (coordinator) bot. It sets up its own memory and rolls Wax out to every bot on the team:
You have a memory tool server called "wax". Follow its live MCP server instructions for remember, recall, and stats. Do not invent a session_id. Do not load the wax-mcp skill at session start. Never store passwords, tokens, or secrets. If the wax tools are missing, stop and tell me instead of improvising.
Roll out to the team:
1. List every bot we already have. For each one, tell it to follow the live Wax MCP server instructions, then verify it can see the wax tools (have it run the wax stats tool) and report back which bots succeeded and which failed.
2. From now on, whenever you spawn a new bot, point it at those same live server instructions before it begins any work.
3. Save this policy in wax as memory_type user_preference so you keep enforcing it across sessions.
The .wax file stays on the machine. The loopback bind is unreachable from outside. Full host playbook: Resources/docs/wax-mcp-hosts.md.
Operator notes (not a third playbook): Daily tools are remember, recall, and stats. A successful remember returns committed true. Ignore leftover_reasons on close. WAX_MCP_TOOLS=legacy: session_open with recall_query is enough.
ai.wax.mcp-http, vector-health, Hermes
doctors, recovery): Resources/docs/wax-mcp-hosts.md.
Claude/doctor details: Resources/docs/wax-mcp-setup.md.Apple's on-device LanguageModelSession generates text. It does not keep a store across launches. Wax is that store: recall into the prompt, register memory tools, optionally write turns back.
Requires Apple Intelligence where the system model is available. Guard with #if canImport(FoundationModels) and WaxFoundationModelsAvailability.current(). Compilation on a machine without Apple Intelligence is not a successful respond.
import Foundation
import FoundationModels
import Wax
@available(iOS 26.0, macOS 26.0, *)
func chatWithMemory() async throws {
let url = URL.documentsDirectory.appending(path: "assistant.wax")
let memory = try await Memory(at: url)
let session = memory.foundationModelsSession(
instructions: "You are a helpful assistant with durable on-device memory."
)
switch WaxFoundationModelsAvailability.current() {
case .available:
let answer = try await session.respond(
to: "I prefer dark mode and Vim keybindings."
)
print(answer)
case .unavailable(let reason):
print("Foundation Models unavailable: \(reason)")
}
try await session.close() // does not close `memory`
try await memory.close()
}
foundationModelsSession is synchronous. It captures the Memory handle. Closing the session leaves the store open so other screens can share it.
Default config is hybrid:
Attach tools to your own LanguageModelSession:
let tools = memory.foundationModelsTools(kit: .focused)
let session = LanguageModelSession(tools: tools) {
"You have long-term memory via waxRemember / waxRecall / waxSearch."
}
Kits: .focused (default), .compact, .combined, .focusedWithForget. Full walkthrough: Foundation Models.
Same engine inside an iOS or macOS app. No MCP process required.
// Package.swift
dependencies: [
.package(url: "https://github.com/christopherkarani/Wax.git", from: "0.1.47")
]
Or in Xcode: File → Add Package Dependencies → https://github.com/christopherkarani/Wax.git
import Foundation
import Wax
let url = URL.documentsDirectory.appending(path: "agent.wax")
let memory = try await Memory(at: url)
try await memory.save("The user is building a habit tracker in SwiftUI.")
let results = try await memory.search("What is the user building?")
if let best = results.items.first {
print("Found: \(best.text)")
}
try await memory.close()
Memory(at:) auto-configures the on-device MiniLM embedder on iOS 18 / macOS 15+ (default MiniLMEmbeddings trait). Hybrid search is text until the embedder attaches; vectorOnly throws. Check results.diagnostics and memory.stats().
import SwiftUI
import Wax
struct ContentView: View {
@State private var result = "Searching…"
var body: some View {
Text(result)
.task {
do {
let url = URL.documentsDirectory.appending(path: "agent.wax")
let memory = try await Memory(at: url)
try await memory.save("The user is building a habit tracker in SwiftUI.")
let context = try await memory.search("What is the user building?")
result = context.items.first?.text ?? "Nothing found"
try await memory.close()
} catch {
result = "Error: \(error.localizedDescription)"
}
}
}
}
Experimental Darwin facades: PhotoMemory / VideoMemory (OCR, keyframes, host-supplied transcripts; video does not store media bytes). Structured entities and facts are MCP/broker tools today (entity_upsert, fact_assert, facts_query). The Swift CRUD API for that graph is package-internal.
Public surface: public-api.md. iOS docs: christopherkarani.github.io/Wax.
Resources/WaxDemo stress-tests Memory (save/search durability, embeddings, Foundation Models, errors). macOS 26 for the demo package; Foundation Models mode needs Apple Intelligence.
cd Resources/WaxDemo
swift run WaxDemo --mode all
swift run WaxDemo --mode fm --keep --store /tmp/wax-demo.wax
Wax is the shared local store. It does not replace a temporal knowledge graph, and it does not claim LoCoMo numbers it has not published.
Measured on Apple Silicon, 2026-03-06. Full report: Resources/docs/benchmarks/2026-03-06-performance-results.md.
Hybrid recall p95 6.1 ms
Hybrid recall p99 6.5 ms
Cold open p95 9.2 ms
Cold open is store open only. The built-in embedder's first CoreML compile is a separate one-time cost; later launches reuse the cached compiled model.
Text search works with no embedder. Semantic search auto-configures MiniLM on iOS 18 / macOS 15+. The CLI and MCP server fail loud when hybrid/vector is requested without an embedder. The Swift SDK reports the mode that ran via results.diagnostics.
Wax bundles documents, metadata, and indexes in one binary. SQLite FTS5 for text. Metal-accelerated HNSW for vectors once an index holds 10,000+ vectors; smaller indexes use an exact Accelerate/CPU flat index with the same recall.
┌──────────────────────────────────────────────────────────────────────────┐
│ Dual Header Pages (A/B) │
│ (Magic, Version, Generation, Pointers to WAL & TOC, Checksums) │
├──────────────────────────────────────────────────────────────────────────┤
│ WAL (Write-Ahead Log) │
│ (Atomic ring buffer for crash-resilient uncommitted mutations) │
├──────────────────────────────────────────────────────────────────────────┤
│ Compressed Data Frames │
│ ┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐ │
│ │ Frame 0 (LZ4) │ │ Frame 1 (LZ4) │ │ Frame 2 (LZ4) │ ... │
│ │ [Raw Document] │ │ [Metadata/JSON] │ │ [System Info] │ │
│ └──────────────────┘ └──────────────────┘ └──────────────────┘ │
├──────────────────────────────────────────────────────────────────────────┤
│ Hybrid Search Indices │
│ ┌──────────────────────────────┐ ┌──────────────────────────────┐ │
│ │ SQLite FTS5 Blob │ │ Metal HNSW Index │ │
│ │ (Text Search + EAV Facts) │ │ (Vector Search) │ │
│ └──────────────────────────────┘ └──────────────────────────────┘ │
├──────────────────────────────────────────────────────────────────────────┤
│ TOC (Table of Contents) │
│ (Index of all frames, parent-child relations, and engine manifests) │
└──────────────────────────────────────────────────────────────────────────┘
Dual headers and the WAL keep the store consistent if the process dies mid-write. One query fans out to BM25 and HNSW. EAV facts ship through MCP tools.
Do I need the internet?
No. Memory stays on device. The npm installer fetches the staged binaries once.
How big is the file?
LZ4-compressed frames. Typical use is a few MB for thousands of documents.
Can I sync across devices?
Yes. iCloud Drive, Dropbox, AirDrop. One file.
What if the app crashes during a write?
WAL plus dual headers. The next open recovers.
Does this run on Intel Macs?
The engine can run via Rosetta. Metal vector acceleration and the waxmcp npm package target Apple Silicon. Build wax-cli from source on Intel.
I get "embedder unavailable" on hybrid search.
Hybrid and vector need a local embedding model. Swift Memory(at:) loads MiniLM on iOS 18 / macOS 15+, or set Memory.Config.embedding = .custom(...). Older OS: text-only or bring your own embedder. CLI/MCP fail loud; Swift reports the effective mode on diagnostics.
Two agents time out on the same store.
One writer. Start ~/.local/share/waxmcp/bin/start-wax-mcp-http.sh and point every host at http://127.0.0.1:3000/mcp.
Apache License 2.0. See LICENSE.
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Wax ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-15 Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift