Using LWC Memory and Graphs
sickn33/agentic-awesome-skills
Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.
Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context
Install Trusty Memory
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bobmatnyc/claude-mpm trusty-memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/trusty-memory .claude/skills/trusty-memory && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .claude/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bobmatnyc/claude-mpm trusty-memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/trusty-memory .agents/skills/trusty-memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .agents/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bobmatnyc/claude-mpm trusty-memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/trusty-memory .cursor/skills/trusty-memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .cursor/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bobmatnyc/claude-mpm.git --path .claude/skills/trusty-memory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bobmatnyc/claude-mpm trusty-memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/trusty-memory .gemini/skills/trusty-memory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .gemini/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bobmatnyc/claude-mpm trusty-memoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/trusty-memory .github/skills/trusty-memory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .github/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bobmatnyc/claude-mpm trusty-memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/trusty-memory .opencode/skills/trusty-memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "trusty-memory" agent skill from https://github.com/bobmatnyc/claude-mpm/tree/main/.claude/skills/trusty-memory into .opencode/skills/trusty-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trusty-memory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
trusty-memory- GitHub stars
- 155
- Token cost
- ~2k tokens
- SKILL.md length
- 522 words
- Files
- 2
- Skills in repo
- 52
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context
- Works in 3 steps: Auto-loaded: L0 identity + L1 top-15… → Targeted recall: For task-specific context → Check KG for relevant entity relationships
- Tasks that involve Knowledge graphs
- SKILL.md covers When to Use, Architecture, Tool Reference and Room Type Selection, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Trusty Memory is an agent skill from bobmatnyc/claude-mpm. Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`). Compatibility notes: claude-code
It sits in Agent Workflows, covering Knowledge graphs, Agent memory and Session handoff. The repository describes itself as: Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and plugin system for Claude. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Knowledge graphs
- Tasks that involve Agent memory
- Tasks that involve Session handoff
Example prompts
- “/trusty-memory”
Requirements
- Compatibility (from SKILL.md): claude-code
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Auto-loaded: L0 identity + L1 top-15 drawers appear in context automatically.
- Targeted recall: For task-specific context
- Check KG for relevant entity relationships
What it can do on your machine
Read from SKILL.md and the folder at commit 25203d3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
claude-code
From compatibility in the SKILL.md frontmatter.
Context cost
Trusty Memory loads about 2k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 522 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from bobmatnyc/claude-mpm at commit 25203d3, republished under its Apache-2.0 licence (© bobmatnyc). 522 words, ~2,027 tokens.
Download SKILL.mdSave it as
.claude/skills/trusty-memory/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- trusty-memory
- description
- Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context
- compatibility
- claude-code
- user-invocable
- false
- disable-model-invocation
- false
- license
- Apache-2.0
trusty-memory
Persistent memory system using the Memory Palace metaphor for organizing context across sessions. Replaces mcp__kuzu-memory__* tools.
When to Use
- Session start: Recall relevant context for the current task
- Decision moments: Store key architectural/design decisions
- Learning capture: Remember new patterns, conventions, gotchas discovered
- Relationship tracking: Assert facts in the knowledge graph (X depends on Y, A replaces B)
- Session end: Persist outcomes and next steps
Do NOT use for: ephemeral scratch notes, code snippets (use trusty-search), or content that belongs in source files.
Architecture
Palace (project) e.g. "claude-mpm"
└── Wing (area) e.g. "Backend"
└── Room e.g. "Backend", "Frontend", "Testing", "Planning",
"Documentation", "Research", "Configuration",
"Meetings", "General"
└── Closet (sub-category)
└── Drawer (memory item: uuid, content, tags, importance)Progressive Retrieval Layers
| Layer | Tokens | When | Trigger |
|---|---|---|---|
| L0 | ~100 | Always | Identity / project context auto-loaded |
| L1 | ~800 | Always | Top-15 drawers by importance auto-loaded |
| L2 | variable | On topic match | memory_recall — metadata-filtered vector search |
| L3 | exhaustive | Explicit | memory_recall_deep — full HNSW deep search |
Always try memory_recall first. Escalate to memory_recall_deep only if results are insufficient.
Tool Reference
Retrieval
memory_recall — Fast progressive retrieval (L0+L1+L2). Use this first.
mcp__trusty-memory__memory_recall(
query="how does the migration registry work",
room="Backend", # optional filter
limit=10 # optional
)memory_recall_deep — Full HNSW deep search (L3). Use when memory_recall insufficient.
mcp__trusty-memory__memory_recall_deep(
query="rare edge case in hook dispatcher",
limit=20
)memory_list — Browse drawers by room/tag (no semantic query).
mcp__trusty-memory__memory_list(room="Planning", tag="release-workflow")Storage
memory_remember — Store a drawer.
mcp__trusty-memory__memory_remember(
content="The migration runner uses run_pending_migrations() at startup; state in ~/.claude-mpm/migrations.json",
room="Backend",
tags=["migrations", "startup"],
importance=0.8 # 0.0-1.0; higher = more likely to appear in L1
)memory_forget — Delete by UUID.
mcp__trusty-memory__memory_forget(drawer_id="<uuid>")Palace Management
mcp__trusty-memory__palace_list()
mcp__trusty-memory__palace_info(palace="claude-mpm")
mcp__trusty-memory__palace_create(name="new-project")Knowledge Graph (temporal triples)
kg_assert — Assert a (subject, predicate, object) fact.
mcp__trusty-memory__kg_assert(
subject="trusty-memory",
predicate="replaces",
object="kuzu-memory"
)kg_query — Query triples for a subject.
mcp__trusty-memory__kg_query(subject="trusty-memory")Room Type Selection
| Room | Use For |
|---|---|
| Backend | Server-side logic, APIs, services, data layer |
| Frontend | UI, components, styling, client-state |
| Testing | Test patterns, fixtures, flaky test notes, coverage decisions |
| Planning | Roadmaps, architectural decisions, ticket plans |
| Documentation | Doc conventions, README structure, public API docs |
| Research | Investigations, spike findings, library evaluations |
| Configuration | Build setup, env vars, deploy config, tooling |
| Meetings | Decisions from sync calls, action items |
| General | Cross-cutting concerns, miscellaneous |
When unsure, prefer the most-specific room. Tags handle the rest.
KG Triple Patterns
Use consistent predicates for queryable graphs:
| Predicate | Example |
|---|---|
replaces | (trusty-memory, replaces, kuzu-memory) |
depends_on | (release-publish, depends_on, gh-account-bobmatnyc) |
implements | (migration_runner, implements, run_pending_migrations) |
documented_in | (release_workflow, documented_in, CLAUDE.md) |
owned_by | (planner-agent, owned_by, .claude/agents/planner.md) |
version_of | (6.2.67, version_of, claude-mpm) |
triggers | (SessionStart, triggers, model_tier_hook) |
Workflow Protocols
Session Start Protocol
- Auto-loaded: L0 identity + L1 top-15 drawers appear in context automatically.
- Targeted recall: For task-specific context:
memory_recall(query="<current task domain>", limit=10) - Check KG for relevant entity relationships:
kg_query(subject="<entity being modified>")
Show full SKILL.md (224 more words)Show less
Session End Protocol
For each significant outcome, persist it:
Decisions →
memory_rememberwith high importance (0.7-0.9)memory_remember( content="Decided to consolidate hook scripts under claude-hook-fast.sh; old per-event scripts deprecated", room="Backend", tags=["hooks", "decision"], importance=0.85 )Relationships →
kg_assertkg_assert(subject="claude-hook-fast.sh", predicate="replaces", object="per-event-hook-scripts")Gotchas / learnings →
memory_rememberwith tags for discoverabilitymemory_remember( content="release-publish requires `claude-mpm gh switch` to bobmatnyc first; bob-duetto account causes auth failures", room="Configuration", tags=["release", "gotcha", "github-auth"], importance=0.9 )
Recall vs Recall-Deep Decision
| Situation | Use |
|---|---|
| Standard context lookup | memory_recall |
| Top-N relevant results enough | memory_recall |
memory_recall returned <3 hits | memory_recall_deep |
| Investigating obscure / rare topic | memory_recall_deep |
| Need exhaustive coverage of a concept | memory_recall_deep |
Importance Scoring
| Score | Type |
|---|---|
| 0.9-1.0 | Critical: release gotchas, security constraints, hard rules |
| 0.7-0.9 | Architectural decisions, major patterns |
| 0.5-0.7 | Useful conventions, common patterns |
| 0.3-0.5 | Project trivia, minor preferences |
| 0.0-0.3 | Ephemeral, rarely-useful |
L1 surfaces the top 15 by importance — score accordingly.
Migration from kuzu-memory
| Old | New |
|---|---|
mcp__kuzu-memory__kuzu_recall | mcp__trusty-memory__memory_recall |
mcp__kuzu-memory__kuzu_learn | mcp__trusty-memory__memory_remember |
mcp__kuzu-memory__kuzu_remember | mcp__trusty-memory__memory_remember |
mcp__kuzu-memory__kuzu_project_context | Auto-loaded via L0 |
mcp__kuzu-memory__kuzu_stats | mcp__trusty-memory__palace_info |
Integration with trusty-search
Common pattern: search → understand → remember.
# 1. Find code with trusty-search
search_code(query="migration runner", query_type="Definition")
# 2. After investigating, persist the learning
memory_remember(
content="Migration runner pattern: registry.py registers each migrate_*.py module; run_pending_migrations iterates by version",
room="Backend",
tags=["migrations", "pattern"],
importance=0.75
)Best Practices
- Be specific: "Release workflow requires bobmatnyc gh account" beats "Check gh account before releasing"
- Include WHY: Decision rationale beats decision alone
- Tag generously: Tags enable cross-room discovery
- Use KG for relationships: Don't bury "X replaces Y" in prose — assert it
- Update over duplicate: Forget stale drawers when superseded
- Prefer recall over recall_deep: Save the expensive call for when you need it
© bobmatnyc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/trusty-memory of bobmatnyc/claude-mpm.
- SKILL.md
- metadata.json
Open the folder on GitHubat commit 25203d3
Compare with similar skills
Trusty Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Trusty Memory this skillbobmatnyc/claude-mpm | 155 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Using LWC Memory and Graphssickn33/agentic-awesome-skills | 47k | 1 repos | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Ogham Maintainogham-mcp/ogham-mcp | 115 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ogham Recallogham-mcp/ogham-mcp | 115 | — | ~1k | Automated safety check: Pass | MIT | |
| Memoryautomateyournetwork/netclaw | 675 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Git Notes Memorysundial-org/awesome-openclaw-skills | 663 | — | ~2.7k | Automated safety check: Pass | None |
Similar skills
Ogham Maintain
ogham-mcp/ogham-mcp
Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Ogham Recall
ogham-mcp/ogham-mcp
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Memory
automateyournetwork/netclaw
NetClaw's native persistent memory (spec 033) — structured facts with temporal validity, semantic search across past sessions, decision logging, and entity relationships, backed by SQLite + ChromaDB…
Git Notes Memory
sundial-org/awesome-openclaw-skills
Git-Notes-Based knowledge graph memory system. An agent skill from sundial-org/awesome-openclaw-skills.
Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
More from bobmatnyc/claude-mpm
All 52 skills in this repoBuild MCP Server
bobmatnyc/claude-mpm
Create high-quality MCP servers that enable LLMs to effectively interact with external services.
Env Manager
bobmatnyc/claude-mpm
Environment variable validation, synchronization, and management across local development, CI/CD, and deployment platforms
Session Analyzer
bobmatnyc/claude-mpm
Debug and teach agentic coding: a deterministic-first session timeline + cost report, with optional narrative polish and a standalone JSX visualiser.
Software Patterns
bobmatnyc/claude-mpm
Decision framework for architectural patterns including DI, SOA, Repository, Domain Events, Circuit Breaker, and Anti-Corruption Layer.
Verification Before Completion
bobmatnyc/claude-mpm
Run verification commands and confirm output before claiming success
Dependency Audit
bobmatnyc/claude-mpm
Dependency audit and cleanup workflow for maintaining healthy project dependencies.
Related
Categories
Questions about Trusty Memory
What does Trusty Memory do?
Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context. Trusty Memory is an agent skill from bobmatnyc/claude-mpm.
When should I use Trusty Memory?
Trusty Memory fits situations like: tasks that involve Knowledge graphs; tasks that involve Agent memory; tasks that involve Session handoff.
How do I install Trusty Memory in Claude Code?
Run `npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a claude-code`. Or copy the skill folder (.claude/skills/trusty-memory in bobmatnyc/claude-mpm) into .claude/skills/trusty-memory in your project. Claude Code loads it when a task matches its description.
How do I install Trusty Memory in Codex?
Run `npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a codex`. Or copy the skill folder (.claude/skills/trusty-memory in bobmatnyc/claude-mpm) into .agents/skills/trusty-memory in your project. Codex loads it when a task matches its description.
Can I use Trusty Memory in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bobmatnyc/claude-mpm --skill trusty-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/trusty-memory, .gemini/skills/trusty-memory, .github/skills/trusty-memory and .opencode/skills/trusty-memory in your project.
What does Trusty Memory need to run?
SKILL.md names no scripts, command-line tools or credentials: Trusty Memory is instructions for the agent only. Compatibility (from SKILL.md): claude-code.
Does Trusty Memory access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Trusty Memory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Trusty Memory use?
Trusty Memory is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Trusty Memory use?
About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Trusty Memory?
Skills that share tags, products or a category with Trusty Memory: Using LWC Memory and Graphs (sickn33/agentic-awesome-skills, 47k stars), Ogham Maintain (ogham-mcp/ogham-mcp, 115 stars), Ogham Recall (ogham-mcp/ogham-mcp, 115 stars) and Memory (automateyournetwork/netclaw, 675 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Trusty Memory?
bobmatnyc (a GitHub user) maintains it in bobmatnyc/claude-mpm, which has 155 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on August 31, 2026.
Source: bobmatnyc/claude-mpm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.