1. Conduid
  2. Search
  3. Silo
MCP server · Search

Silo

Persistent knowledge packs for AI agents. Store, search, and serve claims across sessions

34Low

Scored 4 months ago · breakdown

About Silo

Silo is an MCP server in the Search category: persistent knowledge packs for AI agents. Store, search, and serve claims across sessions. It has been installed 0 times through Conduid.

Install

Clone
git clone https://github.com/grainulation/silo

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Silo

Powered by Claude · Grounded in docs

I know everything about Silo. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • ·Scoped permissionsNot checked yet.

README

Instead of starting every sprint from scratch, pull in battle-tested constraint sets, risk patterns, and decision templates. Grab a starter pack in one command:

npx @grainulation/silo pull compliance --into ./claims.json

Install

npm install -g @grainulation/silo

Built-in packs

24 knowledge packs with 268 curated claims. Run silo packs for the current list with descriptions. The core domain packs:

Pack Claims What's inside
api-design 13 REST conventions, versioning, pagination, error formats, GraphQL tradeoffs
architecture 12 Monolith vs micro, build vs buy, SQL vs NoSQL decision claims
ci-cd 12 CI/CD pipeline patterns, caching, rollback strategies
compliance 14 HIPAA, SOC 2, GDPR constraint sets with regulatory citations
data-engineering 12 ETL patterns, data quality, warehouse design
frontend 12 Frontend architecture, performance, accessibility patterns
migration 10 Database/cloud/framework migration risks and patterns
observability 12 Logging, metrics, tracing, alerting patterns
security 12 Security constraints, threat models, authentication patterns
team-process 12 Team workflow, code review, incident response patterns
testing 10 Testing strategies, coverage, test architecture

Also includes: adr, architecture-decision, coverage-ramp, incident-postmortem, qa-simulation, vendor-eval, 5 hackathon packs. The full list is silo packs.

Quick start

# See available packs
silo packs

# Pull compliance constraints into your sprint
silo pull compliance --into ./claims.json

# Pull only GDPR constraints
silo pull compliance --into ./claims.json --type constraint

# Search across stored claims
silo search "encryption at rest"

# Store your sprint's findings for reuse
silo store "q4-migration-findings" --from ./claims.json

# List everything in your silo
silo list

CLI

Command Description
silo list List all stored collections
silo pull <pack> --into <file> Pull claims into a claims file
silo store <name> --from <file> Store claims from a sprint
silo search <query> Full-text search across claims
silo packs List available knowledge packs
silo publish <name> --collections <ids> Bundle collections into a pack
silo install <file> Install a pack from a JSON file
`silo fetch [--mode auto concise
`silo cache stats clear

Testing

npm test             # unit + extraction tests (no network)
npm run test:live    # includes live regression fixtures (FETCH_LIVE=1)

How it works

Silo uses your filesystem for storage (~/.silo by default). No database, no network calls, no accounts.

When you pull, Silo re-prefixes claim IDs to avoid collisions, deduplicates against existing claims, and merges into your claims.json.

When you store, Silo hashes the content for versioning, saves to ~/.silo/claims/, and updates the search index.

Programmatic API

const { Store } = require("@grainulation/silo/lib/store");
const { Search } = require("@grainulation/silo/lib/search");
const { ImportExport } = require("@grainulation/silo/lib/import-export");

const store = new Store().init();
const search = new Search(store);
const io = new ImportExport(store);

const results = search.query("encryption", { type: "constraint" });
io.pull("compliance", "./claims.json");
io.push("./claims.json", "my-sprint-findings");

Zero third-party dependencies

Depends only on @grainulation/barn (internal ecosystem utilities); no third-party runtime deps. Node built-ins otherwise. Filesystem-based storage. Works offline.

Part of the grainulation ecosystem

Tool Role
wheat Research engine -- grow structured evidence
farmer Permission dashboard -- approve AI actions in real time
barn Shared tools -- templates, validators, sprint detection
mill Format conversion -- export to PDF, CSV, slides, 26 formats
silo Knowledge storage -- reusable claim libraries and packs
harvest Analytics -- cross-sprint patterns and prediction scoring
orchard Orchestration -- multi-sprint coordination and dependencies
grainulation Unified CLI -- single entry point to the ecosystem

Releases

See CHANGELOG.md for release history.

License

MIT

README mirrored from the source repository 4 months ago. The original is authoritative.

Questions

About Silo

How do I install Silo?

Run git clone https://github.com/grainulation/silo, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Silo safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Silo still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.