Self-host Engraphis
v1.7.11Local-first memory engine for AI coding agents
docker compose up- Stars
- 182
- Ports
- 8700 (Dashboard and API), 8711 (MCP-over-HTTP server), 8720 (Read-only graph/recall server)
What is Engraphis?
Engraphis provides a local-first memory engine for AI coding agents. It stores scoped project knowledge organized by workspace, repository, and session, and retrieves relevant evidence using vector, lexical, graph, and code-aware search. The engine preserves provenance and temporal history, cites supporting memories, and abstains when evidence is insufficient. It includes a self-hosted WebUI dashboard for inspecting memories, timelines, graph relationships, and recall rationale. The core runs offline with SQLite and requires no cloud account. It exposes 9 Smart MCP tools and a REST API for integration with coding agents. Optional hosted Pro and Team plans add cloud sync, analytics, automation, and managed decision support (Jev), but the local core remains free under Apache-2.0.
Should you self-host Engraphis?
Engraphis scores 49/100 on selfhost.directory (how scoring works) and ranks #53 of 125 in AI. It has 182 GitHub stars.
It shipped 9 stable releases in the past year. The latest, v1.7.11, came out on 26 October 2026. New versions land roughly every 4 days.
Setup is moderate: expect some configuration beyond a single command. It is Apache-2.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is ComfyUI (93/100, 143 741 stars). It scores higher overall, so compare the two before you pick. See Engraphis vs ComfyUI side by side.
Features
- Bi-temporal history
- Cloud Sync (Pro/Team)Requires Pro or Team subscription; not available in free local core.
- Code indexing
- Document import
- Durable scoped memory for AI agents
- Encryption at RestRequires `engraphis[encryption]` extra.
- Grounded recall with citations
- Knowledge graph visualization
- Local-first / offline operation
- Local OCR and transcriptionRequires optional dependencies.
- Model Context Protocol (MCP) support
- Multi-Modal Retrieval
- Python library and REST API
- Self-hosted WebUI dashboard
Engraphis README
FAQ
Is the dashboard demo connected to a backend?
No. The interactive website demo uses seeded sample data and runs only in the browser tab.
Which agents work with Engraphis?
Engraphis provides 9 Smart MCP tools with advanced discovery for supported coding-agent clients, plus a REST API and Python library.
Where does my memory live?
The local core stores memory in SQLite on your machine. You can inspect, back up, and operate it yourself.
Do I need an API key?
Not for memory operations. Optional chat and synthesis features use the LLM provider you select.
More in Knowledge Management
EpicenterOpen-source, local-first app suite — notes, voice transcription, and a CRDT sync server you run self-hosted on Bun or Cloudflare Workers.
epocheEpoche is a self-hosted, open-source wiki engine with Node.js and SQLite, supporting Markdown and math rendering for personal use and small teams.
evc-team-relaySelf-hosted open-source server that brings real-time collaborative editing and web publishing to Obsidian, with SSO auth and Docker Compose setup.
EventCatalogSelf-hosted architecture catalog for domains, systems, messages and specs, with OpenAPI/AsyncAPI generators plus AI chat and an MCP endpoint for querying your docs.
FalkorDBA super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).
favedFree open-source bookmark manager with nested tags, automatic metadata fetching and browser/Raindrop/Pocket import, self-hosted as one Docker container.
Feather WikiA self-hosted, open-source wiki that fits in a single browser-run HTML file, with Markdown or WYSIWYG editing and optional save-back to your own web server.
Files.mdA self-hosted, open-source Markdown workspace for notes, journaling, tasks and checklists that keeps files local in your browser, with a Go sync server and Telegram bot.
Flamehaven-FilesearchSelf-hosted RAG search engine with BM25+semantic hybrid search across 34 formats, multi-LLM support (Gemini, OpenAI, Claude, Ollama) for private document search.
FlareMoFlareMo is a self-hosted knowledge base on Cloudflare Workers with D1, R2, Memos API, AI memory via MCP, and team collaboration — zero server maintenance.
flatnotesSelf-hosted, open-source note app storing every note as a plain markdown file — no database. Full-text search, tags, wikilinks, dark theme, REST API.
fortemiHost your own AI knowledge base with hybrid search, knowledge graphs, multiple LLM backends, and multimodal ingestion. Docker deployment on regular hardware.
0 comments