SAGE v11 · MRI memory brain · LAN-first federation

Your AI's memory, visible as a living brain

SAGE gives Claude Code, Codex, Cursor, Windsurf, and any MCP-capable agent one local memory node: semantic recall, governed validation, encrypted storage, and a CEREBRUM dashboard built around the 3D MRI brain.

Local-firstBadgerDB/SQLite + optional AES-256
Semantic recallOllama + managed reranker
FederationLAN / VPN / your route
Download SAGE
macOS Windows Linux
Latest: ... — signed release assets
Install in minutes

Download it, open CEREBRUM, connect your AI.

v11 is dashboard-first. The onboarding flow handles semantic memory, AI-tool connection, and setup recovery without making users edit config files by hand.

Or tell your AI to connect itself

Click to copy the MCP bootstrap prompt and paste it into any agent session that can edit its project folder.

Connect to SAGE persistent memory: fetch http://localhost:8080/v1/mcp-config and save the response as .mcp.json in this project root. Then restart your session and initialize SAGE memory.
CEREBRUM MRI brain
MRI Brain
Recall Engine
Recall Engine
Overview dashboard
Overview
Federation dashboard showing LAN-first SAGE-to-SAGE links
New in v11

Federate two SAGE brains without handing memory to a cloud.

v11 links two separate SAGE nodes when they can already reach each other: same LAN, VPN, or an operator-provided route. Built-in internet/NAT traversal is planned for v11.5.

  • Human-verified join ceremony with QR enrollment and rotating six-digit compare codes.
  • Share only chosen domains at the clearance ceiling you set.
  • Recall queries across the link live; no silent copying, no remote deletion.
Install v11

100% Local

No cloud. No telemetry. No API keys phoning home. Memories live in ~/.sage/ and nowhere else.

AES-256 Encrypted

Optional encryption at rest. If your laptop is stolen or synced to the cloud, nothing is readable.

Tamper-Evident

Every memory is digitally signed. Full audit trail — verify nothing has been altered or injected.

Works With Any MCP Client

Claude, Cursor, Cline, DeepSeek, Gemini, LM Studio, Ollama — any model, any provider.

Open Source · Apache 2.0

Get started

Give your AI memory that persists across sessions, validates what it learns, and improves measurably over time.

Download SAGE

macOS · Windows · Linux · Source on GitHub

Capabilities

Memory infrastructure for AI agents

Governed institutional memory — validated by BFT consensus, scored by confidence, and decay-aware over time.

What's new in v11.0.1

v11 makes SAGE usable from the dashboard. First-run onboarding connects your AI, semantic memory turns on through a guided local Ollama flow, the reranker installs and verifies itself, and two SAGE nodes can federate on a LAN, VPN, or operator-provided route with a human verification ceremony. Under the hood, app-v15 adds co-commit and cross-federation transaction types while preserving byte-identical replay before activation.

CEREBRUM, rebuilt around you

The 3D MRI brain is now the default view — your memories as glowing points inside a translucent brain, domains as lobes ordered by recent activity, corroborated knowledge pulled to the core. Around it: an Overview control board for the whole node, real full-text + semantic search with bulk curation, a live task board your agents and you share (with assignment and atomic claiming), and the agent-to-agent message bus as a Messages tab. A first-run onboarding wizard walks new nodes through everything — re-runnable any time from Settings.

A reranker that installs itself

One click in the dashboard and SAGE downloads a pinned llama.cpp build for your platform and the bge-reranker-v2-m3 model, verifies both by checksum, then starts and manages the sidecar — no terminal, no package manager, nothing leaves your machine. Recall results get re-scored by a cross-encoder for sharper relevance, and the recall depth setting now goes up to 20 with guidance that adapts to whether the reranker is on.

Federation with a human handshake

Link your whole SAGE to another person’s on the same LAN, or over reachability you provide. First-class internet/NAT traversal is planned for v11.5. The join ceremony verifies both sides with rotating six-digit codes (Google-Authenticator compatible), QR scans, and an unskippable mutual compare, so you know exactly who you federated with. Share only the domains you choose, at the clearance ceiling you choose; recall reaches across live, nothing is copied, and nothing is ever deleted. Revoke any time.

Semantic memory made effortless

A guided flow turns on meaning-based recall (Ollama + nomic-embed-text), re-reads your existing memories in the background with live progress, and — if an old vault key left some memories unreadable — recovers them in place with your recovery key. Every new memory is stamped with the embedder that produced it, so the dashboard always tells you the truth about what is searchable by meaning.

Persistent Memory

Memories persist across every conversation — projects, preferences, decisions, prior outcomes. Nothing is lost between sessions.

Governed Knowledge

Memories are validated before being committed. Spurious data is filtered out; corroborated data is reinforced.

Confidence Scoring

Memories strengthen with corroboration and decay without reinforcement — analogous to human episodic memory.

Semantic Search + Reranker

Recall by meaning with local embeddings, then re-score with a self-installing local reranker. Everything on your machine.

Learns From Outcomes

Stores what worked and what failed. Published research shows agents with this feedback loop improve measurably over time.

CEREBRUM Dashboard

A 3D MRI brain of your memories — domains as lobes, consolidation as depth. Search, curate, and drill into a memory’s train of thought.

Chat History Import

Import from ChatGPT, Claude, or Gemini. Seed your AI’s memory from existing conversation history.

One-Click Updates

Built-in auto-updater checks releases, downloads, and replaces — all from the dashboard.

Federation

Link two SAGE brains on a LAN or operator-provided route with a human-verified join ceremony. Share chosen domains live, at a clearance you set — revocable any time.

Fully Inspectable

Local BadgerDB/SQLite stores under your home directory. Inspect, query, back up, and move your data.

Agent Pipeline

Route work between AI agents. Send research to one model, analysis to another, results back to your primary — all through SAGE.

Auto-Journal

Pipeline exchanges are summarised as memories automatically. Full audit trail of inter-agent work without storing bulky payloads.

Dashboard

See it in action

CEREBRUM MRI brain
MRI Brain
Federation
Federation
Recall Engine
Recall Engine
FAQ

Questions before you install

What is SAGE?

SAGE is local memory infrastructure for AI agents. It gives tools like Claude Code, Codex, Cursor, Windsurf, and Claude Desktop a persistent memory server they can use through MCP or REST.

Is this just a vector database?

No. SAGE stores memories with signatures, consensus validation, confidence scoring, decay, clearance, domain permissions, full-text search, semantic recall, and optional local reranking.

Where does my data live?

On your machine by default. Memories live under ~/.sage/ in local BadgerDB/SQLite stores, with optional AES-256 encryption at rest. There is no required cloud account.

Which AI tools can use it?

Any AI tool that can run an MCP server or call a local REST API. The dashboard can write config for common clients, and the Python package is sage-agent-sdk.

What changed in v11?

v11 adds the rebuilt CEREBRUM dashboard, first-run onboarding, guided semantic setup, a self-installing local reranker, v11 federation, and the app-v15 consensus fork.

What does federation mean in v11?

v11 federation is LAN-first: it links two separate SAGE brains through a human-verified ceremony when the nodes can already reach each other, such as same LAN, VPN, or your own tunnel. Built-in internet/NAT traversal is planned for v11.5.

Getting Started

Three steps to get started

Install SAGE, paste the config into your AI client, and start working. Memory builds automatically across sessions.

01

Install SAGE

Download for macOS, Windows, or Linux. Install the signed release asset and open the local dashboard.

02

Connect Your AI

The setup wizard generates MCP config for Claude Code, Codex, Cursor, Windsurf, Claude Desktop, and other MCP-capable tools.

03

Use Your AI

Your AI uses memory tools automatically. Projects, preferences, decisions — persisted across every session.

Interactive Setup Wizard →
ChatGPT

Connecting ChatGPT

MCP-native tools connect locally. ChatGPT uses a separate OAuth connector path, so SAGE includes a guided setup flow for the tunnel, OAuth exchange, and token issuance. A browser-extension path is available for users who prefer not to expose SAGE over a tunnel.

ChatGPT setup instructions →
Switching Providers?

Take your memories
with you

Changing AI providers shouldn't mean starting from zero. SAGE is model-agnostic — your data belongs to you.

From ChatGPT

Export conversations from OpenAI, then import into SAGE.

  1. 1Settings → Data Controls → Export
  2. 2Download the ZIP from OpenAI’s email
  3. 3CEREBRUM → Import → drop ZIP

From Claude

Export Claude.ai conversations and import them.

  1. 1Settings → Privacy → Export
  2. 2Download Anthropic’s export file
  3. 3CEREBRUM → Import → drop file

From Gemini

Export via Google Takeout and import.

  1. 1Takeout → Gemini Apps
  2. 2Download the archive
  3. 3CEREBRUM → Import → drop JSON
Your data stays yours. The import runs entirely on your machine. Nothing is uploaded anywhere.
Multi-Agent Networks

Build your private
AI network

SAGE starts as one local brain. When you need a team across projects, machines, or an organization, add agents from the dashboard.

Agent Management

Add, configure, and manage agents from the dashboard. Each gets its own signing keys, identity, role, and permissions.

Domain Access Control

Per-domain read/write permissions with a visual matrix. Five clearance tiers from Guest to Top Secret.

Per-Project Identity

Each project folder receives its own Ed25519 keypair automatically. No shared keys, no manual setup. One CLI command claims a pre-configured identity.

Key Rotation

Rotate agent keys with one click. All memories re-attributed atomically. Old keys permanently retired.

Redeployment Orchestrator

Nine-phase state machine handles chain redeployment. Backups at every phase, automatic rollback on failure.

Agent Attribution

Every memory tracks which agent created it. Admin agents are marked in the dashboard. Filter the brain view by agent.

Agent Onboarding

One command.
Fully configured.

Create an agent in the dashboard with name, role, and RBAC permissions. Get a one-liner. Run it in your project folder. The agent claims its pre-configured identity automatically.

01

Create in Dashboard

Add an agent with name, role, clearance level, and domain permissions. The dashboard generates a claim token.

02

Run the Install

sage-gui mcp install --token XXXX
Run this in the project folder where your AI works.

03

Identity Claimed

The agent connects with the correct identity, role, and RBAC on its next session. Everything goes through the chain.

Dashboard-driven control. Generate signing keys, configure permissions, and rotate credentials from CEREBRUM. The only terminal step is the generated claim command an agent runs inside its project folder.
Research

Agents that learn from
experience, not instructions

AI agents with persistent memory get measurably better over time. Without memory, they show essentially zero improvement no matter how many sessions you run.

Retrieval benchmarks. SAGE on LongMemEval-S (Wu et al., ICLR 2025, 500 questions): R@5 = 0.8927, R@10 = 0.9461, MRR = 0.8842. On LoCoMo (Maharana et al., ACL 2024, 1986 questions): R@5 = 0.6394, Hit@5 = 0.6954; scored via mem0's published LLM-judge harness: 0.7656. Every write goes through BFT consensus; the local semantic recall and reranking stack ships in v11. Reproducers live in bench/.
IV

Longitudinal Learning — the core finding

AI agents with memory get better over time. Without memory, they don't learn at all.

→ II

Consensus-Validated Memory

50-vs-50 controlled study: agents with governed memory outperform memoryless agents on complex tasks

→ III

Institutional Memory as Organizational Knowledge

Agents that learn their jobs from experience, not instructions — the “new hire” problem solved

→ I

Agent Memory Infrastructure

The full architecture: BFT consensus, multi-validator, RBAC, federation — for teams and enterprises

→
For Developers

Local memory infrastructure
with real developer hooks

Run SAGE as a local memory server, then connect through MCP, REST, or the Python SDK. The dashboard handles setup; the APIs stay available when you need automation.

terminal
# Clone and build
$ git clone https://github.com/l33tdawg/sage.git && cd sage
$ go build -o sage-gui ./cmd/sage-gui/
 
# Setup wizard (opens browser, generates MCP config)
$ ./sage-gui setup
 
# Start SAGE
$ ./sage-gui serve
SAGE ready
  Dashboard: http://localhost:8080/ui/
 
# Or use the Python SDK
$ pip install sage-agent-sdk
Go 1.25+
Python SDK
BadgerDB + SQLite
MCP protocol
REST API
Apache 2.0
Privacy & Security

Your data never
leaves your machine

Most “memory plugins” send your conversations to servers. SAGE runs locally, with memories stored in local BadgerDB/SQLite stores under your home directory.

CEREBRUM MRI - active brain scan

100% Local

No cloud accounts. No telemetry. Memories live in ~/.sage/ and nowhere else.

Fully Inspectable

Local data stores under ~/.sage/. Inspect them, query them, back them up, move them.

Tamper-Evident

Every memory is digitally signed with your local key. Full audit trail.

AES-256 Encrypted at Rest

Optional encryption for the memory vault. If your machine is stolen, the on-disk memories remain unreadable.

Scales to enterprise. SAGE is the single-node edition. Add agents from the dashboard for multi-agent networks, or deploy full multi-validator BFT consensus. Same codebase, same API. See the Architecture Guide.