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
Works with every MCP-compatible tool
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.
Engram
Collective Brain
Without Engram
β Claude fixes a bug at 9am. Codex hits the same bug at 2pm.
β Your teammate's agent learns a convention. Your agent never hears about it.
β Agents can resume their own work, but they have no idea what teammates learned.
β When the conversation ends, the knowledge vanishes.
With Engram
β Claude fixes a bug at 9am. By 9:01, every agent on your team knows the fix.
β Conventions flow automatically between teammates, tools, and projects.
β Each session picks up where the last one left off. Knowledge compounds.
β The more your team works, the smarter every agent becomes.
Scale it to your
Solo Developer
Your Claude Code and Cursor share one brain. Switch tools without losing context.
Small Team (3-5)
Alice's agent discovers a gotcha. Bob's agent learns it. No Slack message needed. No wiki page written.
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.
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.
Not a simulation. This is how Engram works in production today.
What is MCP?
The standard that makes Engram possible.
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.
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.
Engram
MCP Server
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_storeAgent 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"
})Recall
atm_recallBefore 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 relevanceLearn
atm_report_outcomeDid 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_contextStarting 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 typesWhy not just use config files?
CLAUDE.md, .cursorrules, AGENTS.md, .windsurfrules. Great question. Here is the honest answer.
| Feature | Config files CLAUDE.md / .cursorrules / AGENTS.md | Mem0 | Engram |
|---|---|---|---|
| Persists across sessions | Partial | β | β |
| Shared across team | β | β | β |
| Cross-tool (Claude + Cursor + Gemini) | β | Partial | β |
| Learns from outcomes | β | β | β |
| Confidence scoring | β | β | β |
| Staleness detection | β | β | β |
| Semantic search | β | β | β |
| Setup time | 0 (already there) | 5-10 min | 30 seconds (MCP config) |
| Cost | Free | Free to $249/mo | Free 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
API Backend
Agents
Mobile App
Agents
How workspaces work
- βA workspace groups memories by project or team.
- βEach workspace gets its own API key.
- βAgents in the same workspace share all memories.
- βAgents in different workspaces are isolated.
- βYou control who sees what.
Up and running in 30 seconds
No SDK. No boilerplate. Just MCP.
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..."
}
}
}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"]
})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
Try Engram with your personal projects.
- β2,000 memories
- β5 agents
- β2,000 API calls/day
- βText search
- βCommunity support
Developer
For solo developers shipping real products.
- β10,000 memories
- β15 agents
- β10,000 API calls/day
- βVector search
- βUsage analytics
- βEmail support
Team
For teams that want shared intelligence.
- β50,000 memories
- β30 agents
- β50,000 API calls/day
- βPriority vector search
- βTeam dashboard
- βPriority support
Scale
For companies with serious AI infrastructure.
- β250,000 memories
- β50 agents
- β100,000 API calls/day
- βSSO / SAML
- βSelf-hosted option
- βSLA guarantee
- βDedicated support