Free · Open · Local-first · Keypair-signed Adventure awaits ✦ v0.6.0 · local context layer · sovereignty stack

What you know
has always been yours.
Your Palace of Co‑Intelligence The context
layer.

Every session, the context resets. The decision you worked through, the thread worth following, the 2am insight, gone. Your AI starts fresh. loci doesn't. Every conversation, kept close. Locally, privately, permanently yours. A memory-mapped workspace for AI agents, MCP rooms, and local LLMs. Works in your IDE, on your desktop, with any local or remote LLM. The palace grows as you build inside it. Local-first. MCP-native. Keypair-signed. Zero cloud dependency. Sovereignty stack integration: Nostr, Nym, Ollama, Goose. Your memory, your schema, your terms.

◆ ELI-5
Your AI finally remembers you.

A regular user who chats with AI tools and wants their work to stick. Local index, full-text search, private. No config. No cloud. No re-explaining yourself from scratch every session.

Feels like: your AI finally knows who you are.
Build your palace in 10m →
⚔ Wizardopen beta
Open your AI desktop app, paste one line.

A technically curious builder, gamer, or power user. Run a single curl one-liner to wire loci into Claude Desktop (or your favourite MCP-aware client). Optional Tauri palace app for the full RPG view. Works with local or remote LLMs.

Feels like: building a dungeon your AI lives in.
See the one-liner →
◈ LLMAGEopen beta
Clone the repo. Read the spec. Own the stack.

A developer or researcher who wants full control over the context layer. git clone + inspect the MCP server, config, and primitives. Ollama local inference (nomic-embed-text, zero API keys) and MCP plugin for Goose, Continue.dev, and Claude Code are both shipped. Nostr keypair identity in progress, see the roadmap.

Feels like: the infrastructure, finally yours.
Read the spec →

The apps you use don't store your knowledge.
They store it for you.

Notion holds your notes. ChatGPT holds your context. Apple holds your memory. They're all landlords, your thinking lives in their architecture, retrievable at their pleasure, gone when you leave. The knowledge you build with AI is yours. It just doesn't live where you live. Yet.

loci inverts this. The index runs in your browser. The search lives on your machine. The palace belongs to the person who builds it.


Your Hero AI Companion

The palace turns your AI from a tool into something that stays with you. Reads your rooms. Knows your crystals. Every session starts exactly where the last ended, no re-explaining, no rebuilding from scratch. Your AI grows wiser as the palace does.

Rooms

A room is a named context space, Dev, Design, Research. Each has a soul file your AI reads before it speaks. The room holds what happened here before: the decisions, the patterns, the things that should never need explaining again.

The Soul Layer

Every room has a CLAUDE.md, the briefing file your AI reads at the start of every session. Two sentences or twenty. It answers: what is this room for, and what must never be forgotten here? Write it once. Let it grow.

THE KNOWLEDGE
Crystals

A crystal is a fact established once, never re-derived. The decision you keep explaining from scratch every session. Write it in the room's soul file, it becomes part of the palace. Your AI never asks again.

The Garden

The garden holds open questions growing across sessions. Not tasks, not features, genuine inquiries you're moving toward slowly, across many sessions. A garden plant is something you tend. The garden remembers.

The Hatchery

New projects are fragile. The hatchery is the palace's incubator, a room without pressure, for ideas that aren't ready to be named. Prototype. Explore. Fail fast in the dark. When something matures, graduate it to the palace proper.

THE ARCHITECTURE
Agent Architecture

Local LLMs, MCP-native rooms, remote agents. The palace exposes your rooms as tools your IDE can call. Every room becomes a live context source for any agent in your stack. The palace serves every conjuration.

Team Palace

Shared rooms. Shared crystals. When a teammate opens the Design room they inherit the same accumulated context, not just your notes, but the living memory of every session held there. Co-intelligence that travels between minds.

The Chronicle

Every session logged. Every decision preserved. The chronicle is the palace's long memory, not just what you know now, but how you came to know it. Navigate back through your thinking. The palace remembers what you forget.

Search everything Memory Loci context_persistence

Full-text search across all your AI chat history. Find that conversation from six months ago in seconds. Every conversation anchored in spatial memory. Navigate your knowledge like rooms in a palace, each locus a persistent node of thought. Persistent context across sessions. Retrieval is O(log n). Semantic indexing optional.

Organize by topic MCP-Native Rooms mcp_integration

Automatically group conversations by topic, project, or date. Your ideas stay connected, even across different AI tools. Each room is a fully configured MCP workspace. Dev room, Design room, Research room, each with its own tools, memory, and agent context. First-class MCP server support. Compose rooms as namespaced tool collections. Expose or isolate contexts as needed.

Works with any AI Agent Architecture zero_vendor_lock

Claude, ChatGPT, Gemini, local models, loci works alongside all of them. Switch tools without losing your history. Runs local LLMs, connects remote agents, orchestrates multi-step workflows. The palace serves every conjuration. Provider-agnostic. Swap LLM backends via config. Local-first, cloud-optional. Your data stays yours.

Never re-explain yourself The Garden namespace_isolation

loci remembers what you already figured out. Link back to past insights instead of rebuilding context from scratch every session. A living room for growing ideas. Seeds become concepts, concepts become loci. The garden grows quietly between sessions, return to find it richer than you left it. Rooms are namespaced scopes. Dev context stays in Dev. Research stays in Research. Explicit boundary control per session.

Private by default The Hatchery snapshot_export

Everything runs in your browser. Your conversations never touch a server. No account, no telemetry, no cloud. Your memory, yours. Where new projects incubate. Prototype, experiment, fail fast in an isolated room. When an idea matures, promote it to the palace proper. Export context as portable JSON. Version-controlled. Diff-able across time. Composable into larger pipelines.

Crystal Extraction

The palace distils your best thinking into crystals, reusable, quotable, linkable knowledge nodes. Extract once, reference everywhere.


Build your palace.
Keep it close.
loci desktop · Tauri v2

loci for Desktop is your palace on your machine. The Tauri app boots into your ~/.loci/ directory, rooms configured, crystals loaded, agents connected. It lives in your system tray. When you open your IDE, loci is already there. Not a browser tab. Not a cloud sync. A local memory hub that runs while you work. Native Tauri v2 shell wrapping the loci WebView frontend. Gives the renderer OS-level file system access. Manages ~/.loci/ bootstrap on first run. Exposes MCP server via local HTTP. System tray entry point for ⌘K search overlay.

The onboarding runs like a dungeon. Each step is a room. Enter the Palace, configure your rooms, summon your first LLM, expose the MCP server. Complete the setup and your palace is live. The quest doesn't end, it continues with every session. Every room you add is a new wing. Every crystal you extract is loot.

~/.loci/ ├── config.json # tier, providers, sync settings ├── index/ │ ├── search.json # MiniSearch index (serialised) │ └── metadata.db # SQLite: metadata + tags ├── rooms/ │ ├── dev/ │ │ └── CLAUDE.md # room soul file │ ├── design/ │ └── research/ ├── loci/ # crystallised .locus nodes └── logs/ └── session.log

Wizard palace · v0.6.0 · Tauri v2 · open beta, for testing, not production Tauri v2 · Rust backend · arm64 + x86_64 · Build from source: github.com/huximaxi/loci

Runs local. No account. No cloud. Runs local. No account. No cloud. Runs local. No account. No cloud.


We built loci because the best AI conversations kept vanishing. A breakthrough insight at 2am, searched for a week later, gone. Re-explaining the same context to the same AI, session after session. Your thinking was happening, just nowhere permanent. loci is the fix: a local memory layer that makes your AI conversations actually yours, fully searchable, never leaving your device.

The memory palace is one of the oldest techniques for thought: a place for everything, everything in its place. loci applies this to co-intelligence. A room is a persistent workspace, Dev, Design, Research, not a single conversation. Conversations happen inside rooms, accumulating context over time. What crystallises from that work becomes a locus: a fixed point in the palace, a node your memory navigates back to. The palace grows as you build inside it. Your thinking becomes architecture.

Palace map, rooms of the co-intelligence system THE GARDEN growing ideas GREAT HALL ✦ THE PALACE ✦ DEV ROOM forge & build DESIGN ROOM vision & craft RESEARCH archive & recall THE HATCHERY seeds incubate LOCI.GARDEN · PALACE FLOOR PLAN · v0.6.0

loci is a context persistence primitive. It solves the stateless session problem for LLM-native workflows, not by adding a cloud layer, but by treating your local machine as the canonical context store. No accounts. No sync. Architecture documented at docs.loci.garden.

Context is state. State must persist.
Local is canonical. Cloud is optional.
Rooms are namespaces. Namespaces are tools.
The index lives with you. Always has.
# config.json, full Wizard/LLMAGE tier
{
  "version": "0.6.0",
  "tier": "wizard", // "eli5" | "wizard" | "llmage"
  "index": {
    "auto_sync": true,
    "sync_interval": "5m",
    "full_text": true,
    "semantic": false
  },
  "llm": {
    "provider": "local", // "local" | "claude" | "openai"
    "endpoint": "http://localhost:11434",
    "model": "llama3"
  },
  "mcp": {
    "expose_rooms": ["dev", "research", "design"],
    "port": 3721
  }
}
# Claude Code / Cursor, add to mcp_servers
{
  "loci": {
    "url": "http://localhost:3721",
    "transport": "http"
  }
}

What you need Prerequisites REQUIREMENTS
  • Any AI tool you already use (Claude, ChatGPT, etc.) A working LLM endpoint, local or remote node >= 18 or python >= 3.10
  • About 20 minutes to set things up 20 minutes + the step-by-step guide MCP-compatible client (Claude Code, Zed, Cursor)
  • A browser (that's it!) A local LLM or Claude API key (for full palace mode) git + config.json (provided)
// 1. open Claude Desktop (or your favourite MCP-aware client)
// 2. run one line in your terminal:

curl -fsSL https://loci.garden/install/wizard.sh | bash

// 3. restart Claude Desktop, loci tools appear in your toolbox
// open beta · macOS · backs up your config before any write

Prefer the GUI? Grab the Tauri palace app below (open beta) or build from source: github.com/huximaxi/loci.

# config.json, minimal setup
{
  "loci_dir": "~/.loci",
  "llm": { "provider": "local", "endpoint": "http://localhost:11434" },
  "mcp": { "expose_rooms": ["dev", "research"] },
  "index": { "semantic": false, "sync_interval": "5m" }
}
Build your palace in 10m → Get the app → Full documentation →

Get in touch Send a Raven Contact

loci is in early development. Questions, ideas, feedback, or just a hello, all welcome. The palace is under construction. Ideas, conjurations, questions, send them through. loci v0.6.0. Feedback, integration questions, architecture discussions.