Engrama MCP server
Commit Nov 7, 2026Provides AI agents with a persistent, graph-based long-term memory framework using SQLite or Neo4j to store entities, observations, and relationships.
Also known as scops/engrama
- Stars
- 9
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 7, 2026
- License
- Apache-2.0
What is Engrama MCP?
Engrama provides AI agents with a persistent, graph-based long-term memory framework using SQLite or Neo4j to store entities, observations, and relationships.
Summary generated from the project's README
About Engrama MCP server
Engrama provides AI agents with a structured, graph-based long-term memory framework. Instead of using simple key-value pairs, it organizes information into entities, observations, and relationships. This allows agents to traverse a knowledge graph to reason about what they have learned. Developers can choose between two primary backends: a local SQLite setup using sqlite-vec for zero-dependency use, or a Neo4j backend for large-scale production environments and Cypher support.
Users can run this locally as a single-process installation or deploy it in multi-tenant environments. The system includes built-in security features like identity-based ownership for every node and relation, ensuring that data access is fail-closed. For compliance, the engrama_gdpr_forget tool allows identities to permanently erase their own memory. The framework is designed to be self-hosted via pip, though a managed hosted version is also available in beta.
What you can do with it
- 1Build persistent agent memoryAn AI agent can store and retrieve complex relationships between different pieces of information using a knowledge graph.
- 2Ensure data privacy and complianceYou can implement a system where users have the right to delete their stored memories entirely.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablescops/engrama is public and reachablegithub.com/scops/engrama ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-07github.com/scops/engrama ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubEngrama
Graph-based long-term memory framework for AI agents.
Engrama gives any AI agent persistent, structured memory backed by a knowledge graph. Instead of flat key-value stores or opaque vector databases, Engrama stores entities, observations, and relationships — and lets agents traverse that graph to reason about their accumulated knowledge.
Two backends are first-class:
- SQLite +
sqlite-vec(default since 0.9) — single file, zero external services,pip install engramaand you're running. - Neo4j 5.26 LTS (opt-in) — for multi-process production setups, large-scale vector search, or teams that already use Cypher.
The data model is identical on both. See docs/backends.md for a full decision guide; the rest of this README assumes the SQLite default.
Since 0.13.0, every node and relation is owned by an
(org_id, user_id) identity and reads are fail-closed: a missing or
partial scope matches nothing rather than falling back to "see all". A
single-process install runs as one stable standalone identity and needs
no configuration; a multi-tenant deployment supplies the identity per
request from an authenticating gateway. Each identity can permanently
erase its own memory through the engrama_gdpr_forget tool
(GDPR right-to-erasure). See
docs/security.md.
Inspired by Karpathy's second-brain concept, but built for agents instead of humans — and with graphs instead of wikis.
Why graphs?
| Flat JSON / KV | Vector DB | Engrama (Graph) | |
|---|---|---|---|
| Relationship queries | ❌ | ❌ | ✅ native |
| Scales to 10k+ memories | ❌ slow | ✅ | ✅ |
| Works without embeddings | ✅ | ❌ | ✅ (optional) |
| Local-first / private | ✅ | depends | ✅ |
| Zero external services | ✅ | ❌ | ✅ (SQLite) |
| "What projects use FastMCP?" | full scan | approximate | 1-hop traversal |
Prerequisites
You need two things to run on the default SQLite backend. Docker is not required unless you opt into Neo4j.
| Requirement | Version | How to check | Install guide |
|---|---|---|---|
| Python | 3.11 or newer | python --version |
python.org/downloads |
| uv (Python package manager) | any recent | uv --version |
docs.astral.sh/uv |
Windows users: after installing Python, make sure "Add Python to PATH" is checked. After installing uv, you may need to restart your terminal.
Optional:
- Obsidian — for vault sync features.
- A local embedder for semantic search.
- Docker Desktop — only if you opt into the Neo4j backend.
Quick start (SQLite, zero-dep)
Step 1: Install
From PyPI (recommended):
pip install engrama # or: uv add engrama
Or from source, for development:
git clone https://github.com/scops/engrama
cd engrama
uv sync
The commands below assume a PyPI install (
engrama ...). From a source checkout, prefix each one withuv run(uv run engrama ...).
Step 2: Initialise the schema
engrama init --profile developer
Step 3: Verify
engrama verify
Step 4: Use it
A) From Python:
from engrama import Engrama
with Engrama() as eng:
eng.remember("Technology", "FastAPI", "High-performance async framework")
eng.associate("MyProject", "Project", "USES", "FastAPI", "Technology")
results = eng.search("microservices")
B) From the command line:
engrama search "FastAPI"
engrama reflect
Quick start (Neo4j, opt-in)
If you need multi-process writes, very large vector indexes, or an existing Cypher toolchain, install with the Neo4j extra:
pip install "engrama[neo4j]" # or, from source: uv sync --extra neo4j
Configure your credentials by copying .env.example to .env and setting GRAPH_BACKEND=neo4j. Start Neo4j with docker compose up -d, and then initialize the schema:
engrama init --profile developer
engrama verify
Hosted (beta)
Engrama is built to be self-hosted: pip install, and it runs on your machine
with your data in a local file. If you would rather not operate and secure a
remote instance yourself, engrama.sinensia.com
is a managed deployment of this same server — EU-hosted, OAuth 2.1 in front of
/mcp, per-identity isolation and GDPR erasure already wired, with setup guides
for Claude, ChatGPT, Gemini, Cursor, VS Code, Windsurf, Zed and Codex.
It is invitation-only during the beta: request access. The open-source server in this repository is not a cut-down edition of it — same tools, same graph model, same code.
Security considerations
Engrama stores everything an agent learns, so treat the memory graph as sensitive data. The full policy lives in docs/security.md; the essentials:
- Data residency. On the default SQLite backend all data lives in a
single local file (
~/.engrama/engrama.dbby default) — nothing leaves your machine. It is plain SQLite: keep it off shared filesystems, back it up, and rely on filesystem permissions for at-rest protection. On the Neo4j backend, data resides wherever you host Neo4j; you own that deployment and its region. - Neo4j authentication. Supply credentials through
.env/ environment variables (NEO4J_URI,NEO4J_USERNAME,NEO4J_PASSWORD) — never commit them. The shippeddocker-compose.ymlis for local dev; change the default password and enable TLS before any networked use. - Embedding providers. Endpoints reached via
OPENAI_BASE_URLshould use HTTPS unless they are on localhost or a trusted network. WithEMBEDDING_PROVIDER=noneno text is sent anywhere; search degrades to fulltext-only. - Tenant isolation. Since 0.13.0 every node and relation is owned by an
(org_id, user_id)identity and reads are fail-closed. A single install runs as one stable standalone identity; a multi-tenant deployment must inject the identity per request from an authenticating gateway (setENGRAMA_REQUIRE_IDENTITY=1to fail closed on missing headers). See docs/security.md. - Right to erasure. Each identity can permanently erase its own memory
via the
engrama_gdpr_forgettool (GDPR). There is no undo and no server-side backup. - Network exposure. The MCP server is meant for a local client. The optional Streamable HTTP transport ships without authentication — keep it on loopback or behind your own authenticated gateway, or use the hosted service, which puts OAuth 2.1 in front of it.
📚 Full Documentation
All further details, including MCP integration (Claude Desktop), Obsidian sync, Architecture, and the complete API Reference, are available in the official documentation.
Engrama MCP questions
How can an agent erase its memory for GDPR compliance?
Each identity can permanently erase its own memory using the engrama_gdpr_forget tool.