(S)AGE — Sovereign Agent Governed Experience

Persistent, consensus-validated memory infrastructure for AI agents.

SAGE gives AI agents institutional memory that persists across conversations, goes through BFT consensus validation, carries confidence scores, and decays naturally over time. Not a flat file. Not a vector DB bolted onto a chat app. Infrastructure — built on the same consensus primitives as distributed ledgers.

The architecture is described in Paper 1: Agent Memory Infrastructure.

Just want to install it? Download here — double-click, done. Works with any AI.

Architecture

Agent (Claude, ChatGPT, DeepSeek, Gemini, etc.)
  │ MCP / REST
  ▼
sage-gui
  ├── ABCI App (validation, confidence, decay, Ed25519 sigs)
  ├── App Validators (sentinel, dedup, quality, consistency — BFT 3/4 quorum)
  ├── CometBFT consensus (single-validator or multi-agent network)
  ├── SQLite + optional AES-256-GCM encryption
  ├── CEREBRUM Dashboard (SPA, real-time SSE)
  └── Network Agent Manager (add/remove agents, key rotation, LAN pairing)

Personal mode runs a real CometBFT node with 4 in-process application validators — every memory write goes through pre-validation, signed vote transactions, and BFT quorum before committing. Same consensus pipeline as multi-node deployments. Add more agents from the dashboard when you're ready.

Full deployment guide (multi-agent networks, RBAC, federation, monitoring): Architecture docs

CEREBRUM Dashboard

http://localhost:8080/ui/ — force-directed neural graph, domain filtering, semantic search, real-time updates via SSE.

Network Management

Add agents, configure domain-level read/write permissions, manage clearance levels, rotate keys, download bundles — all from the dashboard.

Settings

What's New in v4.5

• Cross-Agent Visibility Fixed — Org-based access (clearance levels, multi-org federation) now correctly grants visibility across agents. Queries and list operations check direct grants, org membership, and unregistered domain fallback — no more 0-result queries when clearance should allow access.

• Domain Auto-Registration — First write to an unregistered domain auto-registers it with the submitting agent as owner and full access granted. No more propose-succeeds-but-query-404.

• RBAC Gate Simplification — DomainAccess (explicit allowlist) and multi-org gates are alternatives, not stacked. Passing one skips the other.

• Python Agent SDK — sage-agent-sdk on PyPI for building SAGE-integrated agents. CI-tested on every release.

• /v1/mcp-config Endpoint — Agents can self-configure their MCP connection without manual setup.

• Docker Images — Every release auto-builds and pushes to ghcr.io/l33tdawg/sage. Pin a version or pull latest.

v4.4

• CEREBRUM UX Overhaul — Snap-back physics (nodes spring back to cloud on focus exit), forget animation (fade-and-remove instead of full reload), tab backgrounding fix (no physics jumps after alt-tab).

• Clean Synaptic Ledger — Always-visible button with double-click confirmation. Cleanup toggle auto-saves.

• Focus Mode — Single-click to view memory detail, side panel closes on exit. Graph defaults to committed status.

v4.3

• Synaptic Ledger Safeguards — Three-layer defense against silent encryption downgrade: server auto-re-enables if vault.key exists, web login now actually unlocks the vault for writes (was a bug), and the native macOS app icon prompts for your passphrase before launch. Plaintext writes are blocked when the vault is locked.

• Vault-Locked API — /v1/dashboard/health now exposes vault_locked status. MCP tools (sage_remember, sage_turn, sage_reflect) check this flag and return clear errors telling agents to prompt the user to unlock via CEREBRUM — no more silent plaintext fallback.

• Isolated-by-Default RBAC — Agents can only see their own memories by default. Domain-level read/write permissions, clearance levels, and multi-org federation with department filtering.

• Bulk Operations — Multi-select memories in CEREBRUM for bulk domain moves, tag additions, and agent reassignment.

• Dashboard Update Check — Long-open tabs now poll for new releases every 12 hours so you never miss an update.

• Automated Docker + MCP Registry — Release CI now auto-builds Docker images, pushes to GHCR, and updates server.json — MCP registries get new versions without manual intervention.

v4.0

• 4 Application Validators — Every memory now passes through 4 in-process validators before committing: Sentinel (baseline accept, ensures liveness), Dedup (rejects duplicate content by SHA-256 hash), Quality (rejects noise — greeting observations, short content, empty headers), Consistency (enforces confidence thresholds, required fields). Quorum requires 3/4 accept (BFT 2/3 threshold).

• Pre-Validation Endpoint — POST /v1/memory/pre-validate dry-runs all 4 validators without submitting on-chain. Returns per-validator decisions and quorum result. MCP tools use this to reject low-quality memories before they hit the chain.

• Memory Quality Gates — sage_turn filters low-value observations (greeting noise, short content). sage_reflect detects similar existing memories and skips duplicates. Boot safeguard dedup prevents the same inception reminder from accumulating across sessions.

• Upgrade Cleanup — On upgrade from v3.x, automatically deprecates duplicate boot safeguards, noise observations, very short memories, and content-hash duplicates. SQLite is backed up first. ~25-30 noisy memories cleaned per typical install.

v3.6

• Brain Graph Click-to-Focus — Click any memory bubble to focus its domain group. Others fade out while focused memories arrange in a timeline row sorted by creation date. Click again to view detail, click empty space to exit.

• Interactive Timeline — Click time buckets at the bottom of the brain graph to filter memories by time range. Multi-select hours to narrow down. Clear button to reset.

• Draggable Stats Panel — Grab the "Memory Stats" header to reposition the panel anywhere. Position persists between sessions. Resize horizontally with the drag handle.

• Chain Activity Log — Collapsible real-time event stream at the bottom of every page. See memory stored/recalled/forgotten events and consensus votes as they happen. Drag the top edge to resize.

• Agent Tab Ordering — Admin agents appear first in brain view tabs for faster access.

• Renamed to SAGE GUI — Binary renamed from sage-lite to sage-gui. Upgrade migration handles old launchd plists automatically.

v3.5

• On-Chain Agent Identity — Agent registration, metadata updates, and permission changes go through CometBFT consensus. Every identity operation is auditable, tamper-resistant, and federation-ready.

• Auto-Registration — Agents self-register on-chain during their first MCP connection. No manual setup needed.

• Visible Agents — Control which agents' memories each agent can see. Set per-agent visibility from the dashboard.

• sage_register MCP Tool — Agents can register themselves programmatically via MCP.

• Permission Enforcement — On-chain clearance levels and domain access are enforced on every memory operation, with BadgerDB as the source of truth.

• Legacy Migration — Existing agents auto-migrate to on-chain identity on first boot after upgrade.

v3.0

• Multi-Agent Networks — Add and manage agents from the CEREBRUM dashboard. Each agent gets signing keys, role, clearance level, and per-domain read/write permissions.

• LAN Pairing — Generate a 6-character pairing code. New agents fetch their config over your local network in seconds.

• Agent Key Rotation — Rotate agent credentials with one click. Memories are re-attributed atomically.

• Redeployment Orchestrator — 9-phase state machine handles chain reconfiguration with rollback at every phase.

• In-App Auto-Updater — Check for updates, download, and restart from the Settings page.

• Boot Instructions — Customize what your AI does on startup from the admin dashboard.

• Tabbed Settings — Overview, Security, Configuration, and Update tabs keep everything organized.

• Brain Graph Search — Filter memories by content, domain, type, or agent. Only matching bubbles are shown.

Research

Quick Start

git clone https://github.com/l33tdawg/sage.git && cd sage
go build -o sage-gui ./cmd/sage-gui/
./sage-gui setup    # Pick your AI, get MCP config
./sage-gui serve    # SAGE + Dashboard on :8080

Or grab a binary: macOS DMG (signed & notarized) | Windows EXE | Linux tar.gz

Docker

docker pull ghcr.io/l33tdawg/sage:latest
docker run -p 8080:8080 -v ~/.sage:/root/.sage ghcr.io/l33tdawg/sage:latest

Pin a specific version with ghcr.io/l33tdawg/sage:4.5.2.

Documentation

Stack

Go / CometBFT v0.38 / chi / SQLite / Ed25519 + AES-256-GCM + Argon2id / MCP

License

Code: Apache 2.0 | Papers: CC BY 4.0

Author

Dhillon Andrew Kannabhiran (@l33tdawg)