mnemonic
Unified memory system - aggregates communications and AI sessions across all channels into searchable, analyzable memory
Best use case
mnemonic is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Unified memory system - aggregates communications and AI sessions across all channels into searchable, analyzable memory
Teams using mnemonic should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/mnemonic/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How mnemonic Compares
| Feature / Agent | mnemonic | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Unified memory system - aggregates communications and AI sessions across all channels into searchable, analyzable memory
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Mnemonic — Unified Memory System
Mnemonic aggregates your communications and AI sessions across all channels (iMessage, Gmail, Cursor, Codex, etc.) into a unified searchable memory with identity resolution, semantic search, and analysis.
## Why Mnemonic?
Your communications and AI interactions are fragmented:
- iMessage threads with some people
- Email conversations with others
- AI chat sessions in Cursor
- More AI sessions in Codex
Mnemonic unifies them into one memory layer, so you can:
- Search across ALL channels semantically
- Extract memories and entities automatically
- Enable smart forking for AI sessions
- Query your complete communication history
## Architecture
Mnemonic uses a **ledger-based** architecture:
- **Core Ledger** — Shared infrastructure: episodes, analysis runs, facets, embeddings
- **Events Ledger** — Human communications: iMessage, Gmail, calendar, trimmed AI turns
- **Agents Ledger** — Full fidelity AI sessions: messages, turns, tool calls (for smart forking)
## Quick Start
```bash
# Initialize
mnemonic init
# Configure your identity
mnemonic me set --name "Your Name" --phone "+1234567890" --email "you@example.com"
# Connect adapters
mnemonic connect imessage
mnemonic connect gmail --account you@gmail.com
mnemonic connect cursor # AI sessions via AIX
# Sync all channels
mnemonic sync
# Query
mnemonic events --person "Dad" --since "2025-01-01"
mnemonic search "authentication flow"
mnemonic people --top 20
```
## Commands
### Setup
| Command | Description |
|---------|-------------|
| `mnemonic init` | Initialize config and database |
| `mnemonic me set --name "..." --phone "..." --email "..."` | Configure your identity |
| `mnemonic connect <adapter>` | Configure a channel adapter |
| `mnemonic adapters` | List configured adapters |
### Sync
| Command | Description |
|---------|-------------|
| `mnemonic sync` | Sync all enabled adapters |
| `mnemonic sync imessage` | Sync specific adapter (positional) |
| `mnemonic sync --adapter imessage` | Sync specific adapter |
| `mnemonic sync --full` | Force full re-sync |
### Query
| Command | Description |
|---------|-------------|
| `mnemonic events` | List events with filters |
| `mnemonic events --person "Dad"` | Filter by person |
| `mnemonic events --channel imessage` | Filter by channel |
| `mnemonic events --since 2025-01-01` | Filter by date |
| `mnemonic search "query"` | Semantic search across all content |
| `mnemonic people` | List all people |
| `mnemonic people --top 20` | Top contacts by event count |
| `mnemonic timeline 2026-01` | Events in time period |
| `mnemonic db query <sql>` | Raw SQL access |
### Identity Management
| Command | Description |
|---------|-------------|
| `mnemonic identify` | List all people + identities |
| `mnemonic identify --merge "Person A" "Person B"` | Merge two people |
| `mnemonic identify --add "Dad" --email "dad@example.com"` | Add identity |
## Adapters
### iMessage (via Eve)
Prerequisites:
```bash
brew install Napageneral/tap/eve
eve init && eve sync
```
Connect:
```bash
mnemonic connect imessage
```
### Gmail (via gogcli)
Prerequisites:
```bash
brew install steipete/tap/gogcli
gog auth add your@gmail.com
```
Connect:
```bash
mnemonic connect gmail --account your@gmail.com
```
### AI Sessions (via AIX)
Connect:
```bash
mnemonic connect cursor
```
This imports AI sessions from Cursor via AIX:
- **Events Ledger**: Trimmed turns (user message + response)
- **Agents Ledger**: Full fidelity (all messages, tool calls, turns)
## Output Formats
All commands support `--json` / `-j`:
```bash
mnemonic events --json | jq '.events[] | select(.channel == "imessage")'
mnemonic people --top 10 --json
```
## Configuration
Config: `~/.config/mnemonic/config.yaml`
```yaml
me:
canonical_name: "Your Name"
identities:
- channel: imessage
identifier: "+1234567890"
- channel: email
identifier: "you@example.com"
adapters:
imessage:
type: eve
enabled: true
gmail:
type: gogcli
enabled: true
account: you@gmail.com
cursor:
type: aix
enabled: true
```
Data: `~/Library/Application Support/Mnemonic/mnemonic.db`
## Bootstrap (for AI agents)
```bash
# Check if installed
which mnemonic && mnemonic version
# Install
brew install Napageneral/tap/mnemonic
# OR: go install github.com/Napageneral/mnemonic/cmd/mnemonic@latest
# Setup
mnemonic init
# Configure identity
mnemonic me set --name "User Name" --email "user@example.com"
# Connect adapters (assumes Eve/gogcli/AIX already set up)
mnemonic connect imessage
mnemonic connect gmail --account user@gmail.com
mnemonic connect cursor
# Sync
mnemonic sync
# Verify
mnemonic db query "SELECT COUNT(*) as count FROM events"
mnemonic people --top 5
```
## Tips for Agents
1. Use `mnemonic people --top 10` to understand who the user communicates with most
2. Use `mnemonic events --person "Name"` to get context on a relationship
3. Use `mnemonic search "topic"` for semantic search across all content
4. Use `mnemonic timeline --today` for recent activity
5. Filter by channel to focus on specific contexts
6. Use `--json` output for programmatic access
7. Raw SQL via `mnemonic db query` for complex queriesRelated Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
obsidian-daily
Manage Obsidian Daily Notes via obsidian-cli. Create and open daily notes, append entries (journals, logs, tasks, links), read past notes by date, and search vault content. Handles relative dates like "yesterday", "last Friday", "3 days ago".
obsidian-additions
Create supplementary materials attached to existing notes: experiments, meetings, reports, logs, conspectuses, practice sessions, annotations, AI outputs, links collections. Two-step process: (1) create aggregator space, (2) create concrete addition in base/additions/. INVOKE when user wants to attach any supplementary material to an existing note. Triggers: "addition", "create addition", "experiment", "meeting notes", "report", "conspectus", "log", "practice", "annotations", "links", "link collection", "аддишн", "конспект", "встреча", "отчёт", "эксперимент", "практика", "аннотации", "ссылки", "добавь к заметке".
observe
Query and manage Observe using the Observe CLI. Use when the user wants to run OPAL queries, list datasets, manage objects, or interact with their Observe tenant from the command line.
observability-review
AI agent that analyzes operational signals (metrics, logs, traces, alerts, SLO/SLI reports) from observability platforms (Prometheus, Datadog, New Relic, CloudWatch, Grafana, Elastic) and produces practical, risk-aware triage and recommendations. Use when reviewing system health, investigating performance issues, analyzing monitoring data, evaluating service reliability, or providing SRE analysis of operational metrics. Distinguishes between critical issues requiring action, items needing investigation, and informational observations requiring no action.
nvidia-nim
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
numpy-string-ops
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
nova-act-usability
AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. Tests real user workflows (booking, checkout, posting) with safety guardrails. Use when asked to "test website usability", "run usability test", "generate usability report", "evaluate user experience", "test checkout flow", "test booking process", or "analyze website UX".
notebook-writer
Create and document Jupyter notebooks for reproducible analyses
nomistakes
Error prevention and best practices enforcement for agent-assisted coding. Use when writing code to catch common mistakes, enforce patterns, prevent bugs, validate inputs, handle errors, follow coding standards, avoid anti-patterns, and ensure code quality through proactive checks and guardrails.
nlss
Workspace-first R statistics suite with subskills and agent-run metaskills (including run-demo for guided onboarding, explain-statistics for concept explanations, explain-results for interpreting outputs, format-document for NLSS format alignment, screen-data for diagnostics, check-assumptions for model-specific checks, and write-full-report for end-to-end reporting) that produce NLSS format tables/narratives and JSONL logs from CSV/SAV/RDS/RData/Parquet. Covers descriptives, frequencies/crosstabs, correlations, t-tests/ANOVA/nonparametric, regression/mixed models, SEM/CFA/mediation, EFA, power, reliability/scale analysis, assumptions, plots, missingness/imputation, data transforms, and workspace management.
nexus-bootstrap
Enables your AI agent to discover and install skills from the Nexus Skills Marketplace. Install this skill first to unlock self-service skill management.