AUTOMATIONSWITCH
CommunityAI / ML

Engram

by Gentleman-Programming (community)

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5 backend, MCP server, HTTP API, CLI, and TUI. 3,341 GitHub stars and 100 commits on main in the last 30 days.

3,341·6 tools·Released OCT 2025·MIT
go install github.com/Gentleman-Programming/engram@latest
Share:

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5 backend, MCP server, HTTP API, CLI, and TUI. 3,341 stars and 100 commits on main in the last 30 days.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

{ "mcpServers": { "engram": { "command": "engram", "args": [ "mcp", "serve" ], "env": { "ENGRAM_DB_PATH": "/Users/me/.engram/db.sqlite" } } } }
PrereqInstall via `go install github.com/Gentleman-Programming/engram@latest`. Set ENGRAM_DB_PATH to a sandboxed directory. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "engram": { "command": "engram", "args": [ "mcp", "serve" ], "env": { "ENGRAM_DB_PATH": "/Users/me/.engram/db.sqlite" } } } }
{ "mcpServers": { "engram": { "command": "engram", "args": [ "mcp", "serve" ], "env": { "ENGRAM_DB_PATH": "/Users/me/.engram/db.sqlite" } } } }
{ "mcpServers": { "engram": { "command": "engram", "args": [ "mcp", "serve" ], "env": { "ENGRAM_DB_PATH": "/Users/me/.engram/db.sqlite" } } } }
{ "mcpServers": { "engram": { "command": "engram", "args": [ "mcp", "serve" ], "env": { "ENGRAM_DB_PATH": "/Users/me/.engram/db.sqlite" } } } }

6 TOOLS AVAILABLE

remember
Store a memory entry with content and metadata
Admin
recall
Recall memories matching a query (FTS5 full-text search)
Read
list_memories
List recent memory entries with filters
Read
forget
Delete a memory entry by ID
Admin
tag_memory
Add tags to a memory for later retrieval
Admin
export_memories
Export the memory store as JSON or markdown
Read

OUR ASSESSMENT

Strengths
  • 3,341 GitHub stars.
  • 100 commits on main in the last 30 days. Top cadence among memory MCPs.
  • MIT license.
  • Go binary; no Node or Python runtime required.
  • SQLite + FTS5 backend; offline-first.
  • Agent-agnostic; works across Claude, Codex, Cursor.
Weaknesses
  • Local SQLite; multi-machine sync requires manual file sync or external backup.
  • FTS5 search is keyword-based; no semantic embeddings out of the box.
  • Community-maintained.
Security Notes

Memory store is a local SQLite file. Set ENGRAM_DB_PATH to a sandboxed directory. remember can store arbitrary content; review whether the agent should persist secrets or PII before mounting in production.

Best For

Coding agents that need session-to-session memory; multi-agent flows where agents share a memory store; offline-first dev where the memory store should not depend on a cloud vector DB.

TECHNICAL DETAILS

Language
go
Transport
stdiostreamable-http
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
MIT
GitHub
npm
engram
Last Release
engram (Go release)MAY 8, 2026
First Released
OCT 1, 2025

ADOPTION METRICS

// GitHub Stars
3,341

// Reading this3,341 stars on Gentleman-Programming/engram. 100 commits on main in the last 30 days.

// Popularity Rank
#4
Globally · #4 in AI / ML

// Reading thisPairs with Codebase Memory, Cognee, Pinecone, Qdrant in ai-ml. Engram owns the offline-first agent memory slot.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 8, 2026
02
Cross-referenced
4 directories
PulseMCP, MCP.so, Glama, Smithery
03
Verified against
Claude Desktop, Cursor, Claude Code
Installed and tested across clients
04
Last re-checked
MAY 8, 2026
Weekly re-verification
// How other directories see it

The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.4editorial3,341MAY 8, 2026
PulseMCP— unratedunavailableunavailableMAY 8, 2026
MCP.so— unratedunavailableunavailableMAY 8, 2026
Glama— unratedunavailableunavailableMAY 8, 2026
Smithery— unratedunavailableunavailableMAY 8, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER AI / ML MCP SERVERS

Community4.6

Cognee MCP

topoteretes

Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.

8 tools16,997
Community4.6

Codebase Memory MCP

DeusData

High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.

9 tools2,021
Vendor4.5

Arize Phoenix MCP

Arize AI

LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.

8 tools9,496
Vendor4.5

Qdrant MCP Server

Qdrant

Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.

2 tools1,373
Community4.4

Mastra

mastra-ai (Gatsby team)

TypeScript framework for building AI-powered applications and agents, with built-in MCP server support. From the team behind Gatsby. 23,680 GitHub stars and 100 commits on main in the last 30 days.

6 tools23,680
Official4.4

Amazon Bedrock AgentCore MCP

AWS Labs

Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation and surface deployment guides for runtime, memory, and gateway resources. Apache-2.0 within awslabs/mcp monorepo (8,924 parent stars).

5 tools8,924
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →