Memory Crystal MCP Server

Your AI forgets everything between sessions — who you are, what you decided, what failed, what works. Memory Crystal fixes that.

It captures conversations in real time, extracts durable knowledge, manages raw sensory retention, and injects the right context before every response. One install. No prompting gymnastics. Your AI just knows.

curl -fsSL https://memorycrystal.ai/crystal | bash

Works with everything

Install Memory Crystal on any MCP-compatible AI tool in one command:

The universal installer supports cloud, local, and self-hosted backends. It can register MCP clients, configure OpenClaw, install Codex/Claude hook assets, and stage a Dockerized local Convex backend for offline or self-hosted work.

How it works

  You send a message
       │
       ▼
┌─────────────────────────────────────────┐
│           CONTEXT ENGINE                │
│                                         │
│  Semantic search + BM25 across STM/LTM  │
│  Knowledge graph boost                  │
│  Multi-signal reranker                  │
│  Diversity filter + context budgeting   │
│  → Inject top memories into context     │
└─────────────────────────────────────────┘
       │
       ▼
  AI responds with full context
       │
       ▼
┌─────────────────────────────────────────┐
│         MEMORY EXTRACTION               │
│                                         │
│  Raw message → Short-term memory        │
│  LLM extracts facts/decisions → LTM     │
│  Graph enrichment links related memories│
└─────────────────────────────────────────┘

Every response is informed by what came before. Every conversation feeds the next one.

Two memory layers

STM gives recent continuity. LTM gives permanent knowledge. Sensory retention lets Memory Crystal keep durable recall value without keeping every raw payload forever.

Five memory stores

Knowledge graph

Memories don't exist in isolation. An async background job connects related memories — decisions link to the lessons that informed them, people link to their projects, rules link to the events that created them.

When the Context Engine searches, graph-connected memories rank higher. Your AI doesn't just remember facts — it understands relationships.

Adaptive recall

Six modes, automatically selected:

The Context Engine picks the right mode. You don't configure anything.

Knowledge bases

First-class immutable reference collections for docs, policies, runbooks, and imported source material. They sit alongside conversational memory so your agent can keep learned context and stable reference data separate.

• Immutable — imported chunks stay stable, not rewritten by conversation

• Scoped — tenant and scope filters keep KBs private to the right workspace

• Bulk import — standard import or high-volume bulk-insert without blocking on embedding

• Background enrichment — embedding and graph backfill run asynchronously

24 memory tools

Every tool works in any MCP host or automatically within OpenClaw hooks.

HTTP API

All core operations available over authenticated HTTP:

POST /api/mcp/capture              Create a memory
POST /api/mcp/recall               Hybrid recall over all memory
POST /api/mcp/search-messages      Search short-term history

GET  /api/knowledge-bases          List knowledge bases
POST /api/knowledge-bases          Create a knowledge base
POST /api/knowledge-bases/:id/import       Import chunks
POST /api/knowledge-bases/:id/bulk-insert  High-volume migration
POST /api/knowledge-bases/:id/query        Query a knowledge base

All endpoints require Authorization: Bearer <api-key>. Per-key rate limiting enforced.

Architecture

memorycrystal/
├── plugin/                 OpenClaw plugin — hooks into conversation lifecycle
├── plugins/shared/         Shared hook script for Claude Code, Codex, Factory
├── mcp-server/             MCP server — stdio/HTTP compatibility layer
├── packages/mcp-server/    Streamable HTTP MCP variant
├── convex/                 Backend — schema, capture, recall, graph, retention
│   └── crystal/            All Memory Crystal Convex functions
├── apps/
│   ├── web/                Next.js 15 dashboard (Tailwind 4, Convex Auth)
│   └── docs/               Mintlify documentation site
├── scripts/                Install, bootstrap, doctor, enable/disable
└── assets/                 Logos and brand assets

Local development

Contributors can run an opt-in Dockerized Convex backend and dashboard locally, then seed fixture data without touching the managed production deployment:

npm run convex:local:up
npm run convex:local:seed
npm run convex:local:doctor

Provider keys are intentionally split: MEMORY_CRYSTAL_API_KEY is client bearer auth, GEMINI_API_KEY powers Gemini embeddings, and optional OPENROUTER_API_KEY powers organic model features.

The local stack uses http://127.0.0.1:3210 for Convex RPC, http://127.0.0.1:3211 for HTTP actions, and http://127.0.0.1:6791 for the dashboard. See the Local-First Setup guide for end-user setup, local endpoints, backup and rollback behavior, and troubleshooting.

Self-hosted

Run everything on your own infrastructure:

git clone https://github.com/memorycrystal/memorycrystal.git
cd memorycrystal && npm install

# Deploy to your own Convex project
CONVEX_DEPLOYMENT=prod:your-project-123 npx convex deploy

# Configure
echo 'CONVEX_URL=https://your-project-123.convex.cloud' > mcp-server/.env
echo 'GEMINI_API_KEY=your-key' >> mcp-server/.env

# Enable and verify
npm run crystal:enable
npm run crystal:doctor

For install-script OpenClaw installs, verify the loaded plugin directly:

openclaw plugins info crystal-memory
openclaw crystal_status

Full guide: docs.memorycrystal.ai/configuration/self-hosting

Security

• Multi-tenant isolation — owner checks on every retrieval, database-level separation

• API keys — SHA-256 hashed at rest, plaintext never stored

• Content scanner — blocks prompt injection, encoded payloads, credential patterns

• Prompt injection mitigation — recalled memories injected as informational context only

• Rate limiting — per-key enforcement on all endpoints

• Audit logging — all actions logged to crystalAuditLog

• Device flow auth — RFC 8628-style for CLI key provisioning

• Local mode — SQLite fallback, data never leaves your machine

Pricing

Self-hosting is always free. Paid plans are for the managed cloud at memorycrystal.ai.

Contributing

Memory Crystal is MIT open source. PRs welcome.

git clone https://github.com/memorycrystal/memorycrystal.git
cd memorycrystal && npm install && npm run dev

Star History