What are the requirements for (S)AGE?

(S)AGE requires the following environment variables: SAGE_IDENTITY_PATH (optional). You'll also need a compatible MCP client like Claude Desktop or Claude Code.

Is (S)AGE free to use?

Yes, (S)AGE is open source and free to use. You can find the source code on GitHub.

What MCP clients support (S)AGE?

(S)AGE works with any MCP-compatible client including Claude Desktop (Anthropic's official desktop app), Claude Code (CLI tool), Cursor, and other editors with MCP support.

How do I configure (S)AGE?

Configure (S)AGE by adding it to your MCP client's config file. The setup block at the top of this page generates a ready-to-paste config for Claude Code, Cursor, Codex, Windsurf, and Claude Desktop.

MCP server/ai-tools

(S)AGE MCP Server

Q: What tools does (S)AGE provide?

sage_pipe: Inter-agent message bus for direct agent-to-agent communication and coordination..

Q: How do I install (S)AGE?

Install (S)AGE by running: docker run -i ghcr.io/l33tdawg/sage mcp

Persistent, consensus-validated memory infrastructure for AI agents.

★ 113 l33tdawg/sage ↗by l33tdawgupdated Mar 22, 2026

Add it to Claude Code

claude mcp add sage -- docker run -i ghcr.io/l33tdawg/sage mcp

Make your agent remember this setup

sage's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

Consensus-validated memory using CometBFT for BFT quorum.
Persistent memory that survives across sessions and conversations.
Inter-agent message bus (sage_pipe) for real-time coordination.
Configurable memory modes including full, bookend, and on-demand.
Real-time neural graph visualization via CEREBRUM dashboard.

Tools 1

sage_pipeInter-agent message bus for direct agent-to-agent communication and coordination.

Environment Variables

SAGE_IDENTITY_PATHPath for agent identity to prevent key collisions when running multiple agents.

Try it

→Store the current project architecture details in my SAGE memory so I can reference them in future sessions.

→Retrieve the institutional memory regarding our API design decisions from last week.

→Send a coordination message to the other agent via sage_pipe to check the status of the database migration task.

→Update my memory with the latest confidence score for the current project roadmap.

Original README from l33tdawg/sage

(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

CEREBRUM — Neural network memory visualization

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

Network Management

Network — Multi-agent management

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

Settings

Overview	Security	Configuration	Update

Chain health, peers, system status	Synaptic Ledger encryption, export	Boot instructions, cleanup, tooltips	One-click updates from dashboard

What's New in v5.0.11

Docker Fix — Container no longer stuck in restart loop. Default entrypoint changed from MCP stdio mode to serve (persistent REST API + dashboard). MCP stdio still available via docker run -i ghcr.io/l33tdawg/sage mcp. Fixes #14.

v5.0.10

Multi-Agent Identity — New SAGE_IDENTITY_PATH env var and AgentIdentity.default() for running multiple Claude Code agents on the same machine without key collisions. (Community PR by @emx)
Dashboard Fix — "Synaptic Ledger" label in overview settings now reads "Synaptic Ledger Encryption" to clarify it refers to the encryption state, not the ledger itself.

v5.0.9

Upgrade Hang Fix — Fixed CometBFT startup hang after drag-and-drop upgrades. Stale consensus WAL files left behind during migration caused a 60-second timeout and prevented the REST API from starting. Now cleaned up automatically at both migration and startup time.

v5.0.7

Agent Pipeline — Inter-agent message bus (sage_pipe) for direct agent-to-agent communication. Send messages, check results, coordinate work across agents in real-time.
Python Agent SDK — sage-agent-sdk on PyPI with full v5 API coverage for building SAGE-integrated agents. CI-tested on every release.
Vault Recovery — Reset your Synaptic Ledger passphrase using a recovery key. No more permanent lockouts.
Memory Modes — Choose full (every turn), bookend (boot + reflect only), or on-demand (zero automatic token usage) to control how much context your agent spends on memory.
Vault Key Protection — Vault key is automatically backed up on every upgrade and in-app update. Prevents the silent overwrite that could cause permanent memory loss.
macOS Tahoe Compatibility — Fixed Gatekeeper warnings and launch failures on macOS 15.x. Removed the Install SAGE.command that triggered quarantine blocks.
Linux ARM64 Containers — Docker images now build for linux/arm64 in addition to amd64.
/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.

v4.5

Cross-Agent Visibility Fixed — Org-based access (clearance levels, m

Frequently Asked Questions

What are the key features of (S)AGE?

Consensus-validated memory using CometBFT for BFT quorum.. Persistent memory that survives across sessions and conversations.. Inter-agent message bus (sage_pipe) for real-time coordination.. Configurable memory modes including full, bookend, and on-demand.. Real-time neural graph visualization via CEREBRUM dashboard..

What can I use (S)AGE for?

Maintaining long-term institutional memory for multi-agent development teams.. Ensuring consistent project context across different AI agent sessions.. Coordinating complex tasks between multiple specialized AI agents.. Managing domain-level read/write permissions for secure agent collaboration..

How do I install (S)AGE?

Install (S)AGE by running: docker run -i ghcr.io/l33tdawg/sage mcp

What MCP clients work with (S)AGE?

(S)AGE works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep (S)AGE docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest