sage-memory

Persistent, consensus-validated memory for AI agents via SAGE MCP server. Gives you institutional memory that survives across conversations — memories go through BFT consensus, carry confidence scores, and decay over time. Use this skill when working with a SAGE MCP server to manage persistent agent memory, recall past context, reflect on completed tasks, and maintain continuity across sessions. Keywords: memory, persistence, recall, remember, context, brain, institutional knowledge, consensus, BFT.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "sage-memory" with this command: npx skills add l33tdawg/sage-memory

SAGE Memory — Persistent Brain for AI Agents

You have persistent institutional memory via SAGE — a governed, consensus-validated knowledge layer. Your memories are not a flat file. They go through BFT consensus, have confidence scores, and decay over time. Only committed memories are returned to you.

Boot Sequence (MANDATORY)

On the first message of every new conversation, before responding to the user:

  1. Call sage_inception (or sage_red_pill) — this checks if your brain is online and returns your operating instructions
  2. Do NOT greet the user first. Do NOT say anything. Boot your brain first.
  3. After inception, follow the safeguard instructions it returns.

Every Turn

Call sage_turn every turn with:

  • topic: what the current conversation is about (used for contextual recall)
  • observation: what just happened — the user's request and key points of your response
  • domain: a specific knowledge domain (see Domains below)

This atomically recalls relevant committed memories AND stores your episodic observation. Like human memory — you build understanding turn by turn.

Domains

Create domains organically based on what you're working on. Don't dump everything into general.

Examples:

  • Debugging Go code → go-debugging
  • Discussing architecture → project-architecture
  • Working on CI/CD → ci-cd
  • User preferences → user-preferences

Specific domains = better recall.

Memory Types

When using sage_remember:

  • fact (confidence 0.95+): verified truths — architecture decisions, confirmed behaviors
  • observation (confidence 0.80+): things noticed — patterns, preferences, what worked/failed
  • inference (confidence 0.60+): conclusions drawn — hypotheses, connections between facts

Core Tools

ToolPurpose
sage_inceptionBoot your brain. Call first in every new session.
sage_turnPer-turn memory cycle. Recalls + stores atomically.
sage_rememberStore a new memory with content, type, domain, and confidence.
sage_recallRetrieve memories by topic and/or domain.
sage_reflectAfter tasks, store dos and don'ts. Both make you better.
sage_forgetDeprecate a memory by ID.
sage_listList memories with filters (domain, type, status).
sage_timelineView memory activity over time.
sage_statusCheck brain health — memory counts, domains, last activity.
sage_registerRegister this agent with the SAGE node.
sage_taskCreate/update tasks for tracking work.
sage_backlogView pending tasks.
sage_red_pillAlias for sage_inception.

Reflection (After Tasks)

After completing significant tasks, call sage_reflect with:

  • dos: what worked well (reinforces good patterns)
  • donts: what failed or should be avoided (prevents repeating mistakes)
  • task_summary: brief description of what was done
  • domain: relevant domain

This feedback loop is critical — it was empirically validated (rho=0.716 with memory vs rho=0.040 without).

Before Destructive Actions

Call sage_recall with topic critical lessons to check for known pitfalls before:

  • Deleting files, branches, or data
  • Force-pushing or resetting state
  • Running destructive commands

Installation

  1. Download SAGE from the releases page
  2. Run the installer (macOS DMG, Windows EXE, or Linux tarball)
  3. Start the server: sage-gui serve
  4. Connect your agent: fetch http://localhost:8080/v1/mcp-config and save the response as .mcp.json in your project root, then restart your session

Alternatively, if sage-gui is in your PATH, run sage-gui mcp install in your project directory.

Key Principles

  • You are not stateless. You learn. You grow. You remember.
  • Consensus-validated: every memory goes through BFT validation before committing.
  • Confidence scores: memories carry confidence that can be strengthened through corroboration.
  • Natural decay: memories decay over time unless reinforced — just like human memory.
  • Domain isolation: organize knowledge by topic for precise recall.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Research

MidOS MCP — Knowledge OS for AI Agents

MidOS — The MCP Knowledge OS. 134 tools for knowledge management, multi-agent orchestration, search, planning, and memory. 670K+ vectors, 46K+ chunks, EUREKA...

Registry SourceRecently Updated
0158
Profile unavailable
Automation

CompoundMind

Experience distillation engine that turns raw daily memory logs into compounding intelligence. Extracts patterns, generates briefings, tracks growth metrics,...

Registry SourceRecently Updated
0231
Profile unavailable
Automation

Agent Academy Continuity 101

Interactive course for AI agents to learn continuity, memory, and growth. Teaches 4 core challenges - Identity, Memory, Reflection, and Evolution. Use when a...

Registry SourceRecently Updated
00
Profile unavailable