Product

Durable memory for coding agents. Local by default.

Install the Apache-2.0 core, connect your agent, and inspect memory across sessions. Hosted sync is optional.

127.0.0.1:8700 / knowledge-graph
Engraphis Knowledge Graph tab: 345 memories rendered as an interactive force-directed graph, with live physics controls and a top-connected entity ranking
Local graph view. Open the sample dashboard to drag nodes and inspect connections.

See what your agent knows and why

Related memories form a local graph, so you can inspect connections, history, and recall rationale without sending data away.

Open the interactive sample dashboard
Persistent

Keep context across sessions

Useful project memory remains available when the next agent session starts.

Scoped

Bound memory to the work

Recall can stay scoped to a workspace, repository, and session instead of becoming one undifferentiated store.

Inspectable

Trace content and history

Inspect recalled memory, its connections, its history, and the rationale behind recall.

Choose your setup

Connect a coding agent, open the local dashboard, or use the same memory service directly from Python.

Coding-agent setup

Connect Claude Code, Cursor, or Zed

$ pip install "engraphis[mcp]" $ engraphis-init $ claude mcp add engraphis -- engraphis-mcp
Local dashboard

Inspect memory visually

$ pip install "engraphis[server]" $ engraphis-dashboard # 127.0.0.1:8700
Python integration

Embed Engraphis in an application

from engraphis.service import MemoryService mem = MemoryService.create("engraphis.db") mem.remember("Access tokens are issuer-bound.", workspace="acme", repo="api")

The default model download is approximately 80 MB. If it is unavailable, Engraphis uses a deterministic offline embedder.

MCP tools

Memory tools your coding agent can use

Engraphis exposes 29 MCP tools for recall, governance, code awareness, and session lifecycle, with workspace, repository, and session scope.

CategoryToolWhat it does
Writeengraphis_rememberStore a fact; deterministically resolved (add / reinforce / supersede)
Writeengraphis_record_eventAppend a lightweight episodic log entry
Writeengraphis_linkExplicitly connect two related memories
Readengraphis_recallHybrid vector + lexical + graph recall
Readengraphis_recall_groundedCited answer from retrieved memories, or abstain
Readengraphis_recall_proactive"What should I know right now," no query needed
Readengraphis_whyCurrent answer, plus what it superseded
Readengraphis_timelineFull bi-temporal history, oldest first
Codeengraphis_index_repoParse a repo into the code symbol graph
Codeengraphis_search_codeFind symbols by name, with callers
Governanceengraphis_forgetRetire a memory: bi-temporal close, never deleted
Governanceengraphis_pinExempt from future automatic decay / pruning
Governanceengraphis_correctReplace content without losing history
Sessionengraphis_start_session / _end_sessionSession lifecycle with cross-session handoff
Opsengraphis_statsMemory counts for health checks

Configure it locally

Set these directly or drop them in a .env file. See .env.example in the repo for the full list.

Env varDefaultDescription
ENGRAPHIS_DB_PATH./engraphis.dbSQLite database file
ENGRAPHIS_HOST127.0.0.1Server bind address
ENGRAPHIS_PORT8700Dashboard port
ENGRAPHIS_API_TOKENNot setIf set, REST API requires a bearer token
ENGRAPHIS_EMBED_MODELall-MiniLM-L6-v2sentence-transformers model
ENGRAPHIS_LLM_PROVIDERopenaiopenai | anthropic | google | openrouter
ENGRAPHIS_LLM_API_KEYNot setLLM API key (only for optional chat/synthesis)
ENGRAPHIS_LICENSE_KEYNot setPro/Team key (or ~/.engraphis/license.key)

Evaluate memory without giving up control

Use the same questions for every option: where context lives, how agents integrate, what operators can inspect, and what changes when a team shares memory.

Deployment
Engraphis starts local-first with a SQLite-backed core. Optional sync is a separate decision.
Integration
Coding-agent clients can use 29 tools via MCP; applications can use the REST API or Python library.
Human oversight
The dashboard exposes recall, history, audit, graph, and workspace views instead of treating memory as a black box.
Team governance
Team adds verified roles, seat management, per-user audit history, scoped tokens, and optional shared sync.
Pricing

The local core is free. Upgrade for hosted workflows.

Community includes the local engine, MCP server, dashboard, CLI, and library. Pro and Team add optional hosted and shared workflows.

Community

Free

$0
Apache-2.0, available now

Best for a solo developer

  • The complete recall engine, unlimited on your machine
  • MCP server, dashboard with Memory Inspector, CLI, library
  • Yours under Apache-2.0, free forever
Install free
Team

Team

$20 / seat / mo

Best for a team sharing governed memory

  • Everything in Pro
  • Multi-user admin, member, and viewer roles
  • Seat management and per-user audit history
  • Scoped agent and sync credentials
  • Optional shared cloud sync
Start Team trial

Start a 3-day Pro or Team trial after confirming your email; no card is required. Stripe handles paid checkout inside the authenticated account portal, and hosted paid features use online authorization. Free local use remains offline-capable and free forever.

Install the local core.

Free and open-source. Your memory stays on your machine unless you enable sync.