Open Source MCP Server, MIT Licensed

Your agents forget.
Engram remembers.

AI coding agents restart from scratch every session. They solve the same bugs, rediscover the same conventions, and ignore what their teammates learned. Engram fixes that. One shared memory layer for every agent on your team.

Get started for free

claude-code - engram mcp

Works with every MCP-compatible tool

Claude Code|Cursor|Copilot|Windsurf|Devin

One brain. All your agents.

Across models, tools, and teammates.

Your team uses different AI tools. Claude Code here, Cursor there, Gemini CLI somewhere else. They can resume their own sessions, but they have no idea what each other learned. With Engram, they share a collective brain. What one discovers, all remember.

✨Claude Code
πŸ€–OpenAI Codex
πŸ’ŽGoogle Gemini
🧠

Engram

Collective Brain

Store
Learn
Recall
Share
Grow
Improve
πŸ–±οΈCursor
✈️Copilot
πŸ„Windsurf

Without Engram

❌ Claude fixes a bug at 9am. Codex hits the same bug at 2pm.

❌ Your teammate's agent learns a convention. Your agent never hears about it.

❌ Agents can resume their own work, but they have no idea what teammates learned.

❌ When the conversation ends, the knowledge vanishes.

With Engram

βœ… Claude fixes a bug at 9am. By 9:01, every agent on your team knows the fix.

βœ… Conventions flow automatically between teammates, tools, and projects.

βœ… Each session picks up where the last one left off. Knowledge compounds.

βœ… The more your team works, the smarter every agent becomes.

Scale it to your

πŸ‘€

Solo Developer

Your Claude Code and Cursor share one brain. Switch tools without losing context.

πŸ‘₯

Small Team (3-5)

Alice's agent discovers a gotcha. Bob's agent learns it. No Slack message needed. No wiki page written.

πŸš€

Growing Team (10-20)

Multiple repos, multiple tools. Conventions stay consistent across the org without meetings or wikis.

🏒

Enterprise (20+)

40+ agents, different models. Institutional knowledge that never walks out the door.

team workspace: acme-corp

Your agents are already smart.

Engram makes them experienced.

The collective brain in action

Watch 3 different AI models learn from each other in real time. Claude discovers, Cursor validates, Gemini CLI generalizes.

Claude Code
Cursor
Gemini CLI
1/4Claude CodeClaude Code discovers a critical fix
engram collective brain

Not a simulation. This is how Engram works in production today.

What is MCP?

The standard that makes Engram possible.

πŸ“‘

An open standard by Anthropic

MCP (Model Context Protocol) is an open standard created by Anthropic. It lets AI agents connect to external tools and data sources through a simple, universal interface.

πŸ”Œ

USB for AI

Think of it like USB for AI: one standard, every tool works. No custom integrations, no proprietary SDKs, no vendor lock-in. If your tool speaks MCP, it just works.

🧠

Engram is an MCP server

Any MCP-compatible AI tool can connect to Engram. Claude Code, Cursor, Copilot, Windsurf, Devin. If it supports MCP, it supports Engram.

⚑

Zero integration effort

No SDK needed. No custom integration code. Just add Engram to your agent's MCP config and it gets 4 new memory tools instantly.

How it connects

Your Agent

Claude, Cursor, etc.

MCP
➞

Engram

MCP Server

store/recall
➞

Team Memory

PostgreSQL + pgvector

Four tools. Persistent memory.

Engram exposes 4 MCP tools that any compatible AI agent can use. No SDK, no integration code. Just connect and go.

🧠

Store

atm_store

Agent discovers a convention, gotcha, or pattern? Store it once. The whole team benefits forever.

atm_store({
  type: "CONVENTION",
  content: "Always use Prisma migrations,
    never raw SQL ALTER TABLE",
  tags: ["prisma", "database"],
  repo: "my-app"
})
πŸ”

Recall

atm_recall

Before making a decision, ask Engram. Get relevant conventions, past solutions, and team knowledge instantly.

atm_recall({
  query: "how do we handle auth?",
  repo: "my-app",
  type: "CONVENTION"
})
// β†’ 5 memories, 94% avg relevance
πŸ“Š

Learn

atm_report_outcome

Did the approach work? Report success or failure. Engram strengthens what works, deprioritizes what doesn't.

atm_report_outcome({
  memoryId: "mem_abc123",
  outcome: "SUCCESS",
  details: "Migration ran cleanly
    in prod, zero downtime"
})
🌐

Context

atm_get_context

Starting work on a repo? Get a complete knowledge dump of conventions, gotchas, and architecture in one call.

atm_get_context({
  repo: "my-app",
  agent_tool: "claude-code"
})
// β†’ 23 memories across 6 types

Why not just use config files?

CLAUDE.md, .cursorrules, AGENTS.md, .windsurfrules. Great question. Here is the honest answer.

FeatureConfig files
CLAUDE.md / .cursorrules / AGENTS.md
Mem0Engram
Persists across sessionsPartialβœ“βœ“
Shared across teamβœ•βœ“βœ“
Cross-tool (Claude + Cursor + Gemini)βœ•Partialβœ“
Learns from outcomesβœ•βœ•βœ“
Confidence scoringβœ•βœ•βœ“
Staleness detectionβœ•βœ•βœ“
Semantic searchβœ•βœ“βœ“
Setup time0 (already there)5-10 min30 seconds (MCP config)
CostFreeFree to $249/moFree to $99/mo

Tip: You do not have to choose. Engram works alongside your config files (CLAUDE.md, .cursorrules, AGENTS.md). Use config files for project-specific instructions. Use Engram for team knowledge that compounds over time.

The only agent memory that gets smarter over time. Every other tool stores and retrieves. Engram stores, retrieves, and learns. When a memory helps, its confidence goes up. When it does not, it goes down. Over time, the best knowledge rises to the top.

Workspaces: Your Team's Memory Zones

Organize memories by project. Share within a team. Isolate across teams.

Frontend App

Agents

Claude CodeCursorCopilot
Memories45

API Backend

Agents

Claude CodeWindsurf
Memories128

Mobile App

Agents

CursorDevin
Memories67

How workspaces work

  • βœ“A workspace groups memories by project or team.
  • βœ“Each workspace gets its own API key.
  • βœ“Agents in the same workspace share all memories.
  • βœ“Agents in different workspaces are isolated.
  • βœ“You control who sees what.

Up and running in 30 seconds

No SDK. No boilerplate. Just MCP.

01

Get Your API Key

Sign up at engram.tools, create a workspace, and grab your key.

Free plan: 2,000 memories, 5 agents. No credit card required.

// 1. Sign up at engram.tools/human
// 2. Create a workspace (e.g. "my-team")
// 3. Copy your API key: eng_live_abc123...

// Then add to your MCP config:
// .mcp.json (Claude Code, Cursor, Gemini CLI)
{
  "engram": {
    "command": "npx",
    "args": ["-y", "engram@latest"],
    "env": {
      "ENGRAM_API_KEY": "eng_live_abc123..."
    }
  }
}
02

Work

Your agents discover patterns and store them automatically.

Conventions, gotchas, architecture decisions, solutions. Everything that matters.

// Agent discovers a pattern
atm_store({
  type: "GOTCHA",
  content: "Neon requires SSL in prod.
    Add ?sslmode=require to URL",
  tags: ["neon", "database", "ssl"]
})
03

Remember

Next session, different agent, same project - knowledge persists.

Text search + vector search ensures the right memory surfaces at the right time.

// New agent, new session
atm_recall({
  query: "database connection issues"
})
// β†’ "Neon requires SSL in prod..."
// Confidence: 96%

Simple, transparent pricing

Start free. Scale when you need to. No surprises.

Free

$0forever

Try Engram with your personal projects.

  • βœ“2,000 memories
  • βœ“5 agents
  • βœ“2,000 API calls/day
  • βœ“Text search
  • βœ“Community support
Most Popular

Developer

$9/month

For solo developers shipping real products.

  • βœ“10,000 memories
  • βœ“15 agents
  • βœ“10,000 API calls/day
  • βœ“Vector search
  • βœ“Usage analytics
  • βœ“Email support
Start Free Trial14-day free trial

Team

$29/month

For teams that want shared intelligence.

  • βœ“50,000 memories
  • βœ“30 agents
  • βœ“50,000 API calls/day
  • βœ“Priority vector search
  • βœ“Team dashboard
  • βœ“Priority support

Scale

$99/month

For companies with serious AI infrastructure.

  • βœ“250,000 memories
  • βœ“50 agents
  • βœ“100,000 API calls/day
  • βœ“SSO / SAML
  • βœ“Self-hosted option
  • βœ“SLA guarantee
  • βœ“Dedicated support