Remembra

The memory layer for AI that actually works.
Persistent memory with entity resolution, temporal decay, and graph-aware recall.
Self-host in minutes. No vendor lock-in.

Documentation • Website • Quick Start • Why Remembra? • Twitter • Discord

🚀 What's New in v0.16.0 — Lossless Memory

Most memory layers store an LLM's paraphrase of what you said. Remembra now keeps the receipts.

• 🧾 Verbatim source records — the exact original text is preserved as an immutable record whenever facts are derived from it. Never LLM-merged, never rewritten.
• 🔗 Receipts on every fact — each derived fact carries metadata.source_id pointing back to its source. Recall a fact, fetch its evidence.
• 🛡️ Hallucination flagging — every derived fact is verified against its source; facts that don't overlap the original are stored flagged verified: false, not silently trusted.
• ⚡ Fast writes (opt-in) — REMEMBRA_ASYNC_ENRICHMENT=true stores the verbatim source instantly and runs extraction in the background.
• 🩺 Production reliability — request IDs on every response, honest 429/502 upstream error mapping, embedding cache (~8× faster repeat recalls), litestream backups, and the opaque store-500 class of failures fixed at the root.

Previous highlights

• 🧠 Brain layer (v0.15+) — GraphRAG-style community detection over your entity graph; 2D/3D knowledge graph in the dashboard
• 🌐 Remote MCP — multi-tenant streamable-HTTP MCP: connect any agent with just a URL + API key
• 🔐 Dashboard v2 — 2FA, teams, admin console, audit log, entity browser

Supported Agents (6+)

Claude Desktop • Claude Code • Codex CLI • Cursor • Windsurf • Gemini

The Problem

Every AI app needs memory. Your chatbot forgets users between sessions. Your agent can't recall decisions from yesterday. Your assistant asks the same questions over and over.

Existing solutions have tradeoffs:

• Mem0: Graph features require $249/mo plan; limited self-hosting documentation
• Zep: Academic approach, complex deployment
• Letta: Research-grade, not production-ready
• LangChain Memory: Too basic, no persistence

The Solution

from remembra import Memory

memory = Memory(user_id="user_123")

# Store — entities and facts extracted automatically
memory.store("Had a meeting with Sarah from Acme Corp. She prefers email over Slack.")

# Recall — semantic search finds relevant memories
result = memory.recall("How should I contact Sarah?")
print(result.context)
# → "Sarah from Acme Corp prefers email over Slack."

# It knows "Sarah" and "Acme Corp" are entities. It builds relationships.
# It persists across sessions, reboots, context windows. Forever.

⚡ Quick Start (2 Minutes)

One Command Install

curl -sSL https://raw.githubusercontent.com/remembra-ai/remembra/main/quickstart.sh | bash

That's it. Remembra + Qdrant + Ollama start locally. No API keys needed.

Or with Docker Compose directly:

git clone https://github.com/remembra-ai/remembra && cd remembra
docker compose -f docker-compose.quickstart.yml up -d

Try it:

# Store a memory
curl -X POST http://localhost:8787/api/v1/memories \
  -H "Content-Type: application/json" \
  -d '{"content": "Alice is CEO of Acme Corp", "user_id": "demo"}'

# Recall it
curl -X POST http://localhost:8787/api/v1/memories/recall \
  -H "Content-Type: application/json" \
  -d '{"query": "Who runs Acme?", "user_id": "demo"}'

Connect ALL Your AI Agents (NEW in v0.10.0)

One command configures everything:

pip install remembra
remembra-install --all --url http://localhost:8787

This auto-detects and configures: Claude Desktop, Claude Code, Codex CLI, Cursor, Windsurf, Gemini.

Verify setup:

remembra-doctor all

{
  "mcpServers": {
    "remembra": {
      "command": "remembra-mcp",
      "env": {
        "REMEMBRA_URL": "http://localhost:8787",
        "REMEMBRA_USER_ID": "default"
      }
    }
  }
}

Claude Code:

claude mcp add remembra -e REMEMBRA_URL=http://localhost:8787 -- remembra-mcp

Cursor — add to .cursor/mcp.json:

{
  "mcpServers": {
    "remembra": {
      "command": "remembra-mcp",
      "env": {
        "REMEMBRA_URL": "http://localhost:8787"
      }
    }
  }
}

Now ask Claude: "Remember that Alice is CEO of Acme Corp" — then later: "Who runs Acme?"

Python SDK

pip install remembra

from remembra import Memory

memory = Memory(user_id="user_123")
memory.store("Had a meeting with Sarah from Acme Corp. She prefers email over Slack.")
result = memory.recall("How should I contact Sarah?")
print(result.context)  # "Sarah from Acme Corp prefers email over Slack."

TypeScript SDK

npm install remembra

import { Remembra } from 'remembra';

const memory = new Remembra({ url: 'http://localhost:8787' });
await memory.store('User prefers dark mode');
const result = await memory.recall('preferences');

🔥 Why Remembra?

Feature Comparison

Core Features

🧠 Smart Extraction — LLM-powered fact extraction from raw text

👥 Entity Resolution — "Adam", "Mr. Smith", "my husband" → same person

⏱️ Temporal Memory — TTL, decay curves, historical queries

🔍 Hybrid Search — Semantic + keyword for accurate recall

🔒 Security — PII detection, anomaly monitoring, audit logs

📊 Dashboard — Visual memory browser, entity graphs, analytics

📊 Benchmark Results

Tested on the LoCoMo benchmark (Snap Research, ACL 2024) — the standard academic benchmark for AI memory systems.

Scored with LLM judge (GPT-4o-mini). Adversarial detection not yet implemented. Run your own: python benchmarks/locomo_runner.py --data /tmp/locomo/data/locomo10.json

📖 Documentation

🛠️ MCP Server

Give any AI coding tool persistent memory with one command. Works with Claude Code, Cursor, VS Code + Copilot, Windsurf, JetBrains, Zed, OpenAI Codex, and any MCP-compatible client.

pip install remembra[mcp]
claude mcp add remembra -e REMEMBRA_URL=http://localhost:8787 -- remembra-mcp

Available Tools (11 total):