Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/matrixorigin/memoria/deploymentnpx skills add matrixorigin/memoria --skill deploymentgit clone --depth 1 https://github.com/matrixorigin/memoriaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.01662 |
| Opus 5 | $0.00014 | $0.00831 |
| Sonnet 5 | $0.00006 | $0.00332 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
deployment scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Services: API on `:8100`, MatrixOne on `:6001`. Verify: `curl http://localhost:8100/health` How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Compose (Single Instance)
cd Memoria
cp .env.example .env # Set MEMORIA_MASTER_KEY, MEMORIA_EMBEDDING_API_KEY
docker compose up -d
Services: API on :8100, MatrixOne on :6001. Verify: curl http://localhost:8100/health
Environment Variables
Required
| Variable | Description |
|---|---|
MEMORIA_MASTER_KEY |
Admin API key (min 16 chars) |
Database
| Variable | Default | Description |
|---|---|---|
MEMORIA_DB_HOST |
matrixone |
MatrixOne host |
MEMORIA_DB_PORT |
6001 |
MatrixOne port |
MEMORIA_DB_USER |
root |
Database user |
MEMORIA_DB_PASSWORD |
111 |
Database password |
MEMORIA_DB_NAME |
memoria |
Database name |
Embedding
| Variable | Default | Description |
|---|---|---|
MEMORIA_EMBEDDING_PROVIDER |
local |
local or openai |
MEMORIA_EMBEDDING_MODEL |
all-MiniLM-L6-v2 |
Model name |
MEMORIA_EMBEDDING_API_KEY |
— | Required if provider is openai (single-backend) |
MEMORIA_EMBEDDING_BASE_URL |
— | Custom endpoint, OpenAI-compatible (single-backend) |
MEMORIA_EMBEDDING_ENDPOINTS |
— | JSON array for multi-backend round-robin. When set, supersedes BASE_URL/API_KEY. Format: [{"url":"https://api1.example.com/v1","api_key":"sk-1"},{"url":"https://api2.example.com/v1","api_key":"sk-2"}]. All endpoints must serve the same model. Requests rotate round-robin; failed/rate-limited endpoints are skipped automatically. |
MEMORIA_EMBEDDING_DIM |
0 (auto) |
Embedding dimension |
Distributed
| Variable | Default | Description |
|---|---|---|
MEMORIA_INSTANCE_ID |
Random UUID | Unique instance ID. Set to Pod name in K8s |
MEMORIA_LOCK_TTL_SECS |
120 |
Distributed lock TTL. Heartbeat renews every TTL/3 |
Governance
| Variable | Default | Description |
|---|---|---|
MEMORIA_GOVERNANCE_ENABLED |
false |
Enable background governance scheduler |
MEMORIA_GOVERNANCE_PLUGIN_BINDING |
default |
Repository binding name |
MEMORIA_GOVERNANCE_PLUGIN_SUBJECT |
system |
Subject key for binding resolution |
MEMORIA_GOVERNANCE_PLUGIN_DIR |
— | Local plugin dir (dev mode, skips signature) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 196 lines · 28 tokens per session scan A be088a6e9235
deployment is a skill published in the GitHub repository matrixorigin/memoria (592 stars, last pushed 6d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,662 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
publish-registry
Publish @agentos-software/ registry packages from AgentOS. Use whenever the user asks to publish or release registry software/agent packages.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.