Long-term memory for AI assistants — fast, private, and yours.

AutoMem

AutoMem gives your AI a memory that survives the chat.

Save the decisions, preferences, notes, and context that matter. The next time you open Claude, Cursor, Codex, ChatGPT, or another connected assistant, it can bring back the right details instead of making you repeat yourself.

Ask, “Why did we choose PostgreSQL?” and AutoMem can return the decision, the alternatives you considered, the principle behind it, and the work that followed — not just a pile of similarly worded snippets.

Why AutoMem feels different

No LLM call in the middle of recall. AutoMem looks up memories directly through its graph and vector index. That keeps normal retrieval fast and avoids an extra generative-LLM charge every time your assistant needs context. It still uses embeddings — from Voyage, OpenAI, or a local provider — and optional enrichment can add more structure over time.

More than vector search. A vector match finds something similar; AutoMem also records typed relationships between memories. It can follow the connections between a decision, its rationale, and its consequences, so your assistant has a better chance of returning the why, not only the words it recognizes.

One memory across your tools. Use the local MCP bridge with Claude Desktop, Cursor, Claude Code, Codex, Copilot, and more. For cloud agents, Remote MCP connects the same service to ChatGPT Developer Mode, Claude.ai, and ElevenLabs over HTTPS. Your memory is not locked to one chat app.

Own the data and the setup. Run AutoMem locally with Docker, on your own infrastructure, or as a small Railway service group. It exposes both MCP and a REST API, so it fits into the tools and workflows you already use.

Proven where long context gets hard

On the independent Agent Memory Benchmark's BEAM long-context tests, AutoMem scored 57.4% at 10 million source tokens while giving the answerer an average of only ~2.6–4.8k retrieved tokens. That is the kind of efficiency that lets memory stay useful as an agent's history grows.

The full picture — test setup, raw outputs, methodology, historical runs, and reproduction commands — is in automem.ai/benchmarks and benchmarks/EXPERIMENT_LOG.md.

How it works

AutoMem combines two storage layers behind a single API:

• FalkorDB stores memories as nodes with 11 typed relationships between them. The graph is the canonical record.
• Qdrant stores an embedding for every memory. Recall is a hybrid query — semantic similarity, graph traversal, temporal alignment, tag overlap, and importance — ranked by a 9-component score.

flowchart TB
    subgraph service [AutoMem Service Flask]
        API[REST API<br/>Memory Lifecycle]
        Enrichment[Background Enrichment<br/>Pipeline]
        Consolidation[Consolidation<br/>Engine]
        Backups[Automated Backups<br/>Optional]
    end

    subgraph storage [Dual Storage Layer]
        FalkorDB[(FalkorDB<br/>Graph Database)]
        Qdrant[(Qdrant<br/>Vector Database)]
    end

    Client[AI Client] -->|Store/Recall/Associate| API
    API --> FalkorDB
    API --> Qdrant
    Enrichment -->|11 edge types<br/>Pattern nodes| FalkorDB
    Enrichment -->|Semantic search<br/>1024-d vectors| Qdrant
    Consolidation --> FalkorDB
    Consolidation --> Qdrant
    Backups -.->|Optional| FalkorDB
    Backups -.->|Optional| Qdrant

If Qdrant is unavailable, the graph still serves recall in a degraded mode. If FalkorDB is down, the API returns 503 — the graph is the source of truth.

Multi-hop bridge discovery

Ask "why boring tech for Kafka?" and AutoMem doesn't just match the word "Kafka". It traverses the graph from the seed memories to find the bridge that connects them:

• Seed 1: "Migrated to PostgreSQL for operational simplicity"
• Seed 2: "Evaluating Kafka vs RabbitMQ for message queue"
• Bridge: "Team prefers boring technology — proven, debuggable systems"

Both seeds carry an EXEMPLIFIES edge to the bridge memory. AutoMem ranks the bridge above the seeds and surfaces it in the recall response, so the assistant answers with your reasoning, not isolated facts. Tune via expand_relations, relation_limit, and expansion_limit on GET /recall.

11 authorable relationship types

Three more edge types are added automatically by the enrichment pipeline and consolidation engine: SIMILAR_TO, PRECEDED_BY, and DISCOVERED.

Memory consolidation, neuroscience-inspired

AutoMem implements biological memory consolidation cycles. Wrong rabbit holes fade naturally. Important memories with strong connections strengthen over time.

Tune intervals via CONSOLIDATION_*_INTERVAL_SECONDS. See docs/ENVIRONMENT_VARIABLES.md.

For more on the recall scoring formula, enrichment internals, and how AutoMem differs from RAG and pure vector databases, see docs/COMPARISON.md.

Research foundation

AutoMem implements techniques from peer-reviewed memory research:

• HippoRAG 2 (Ohio State, 2025) — graph + vector hybrid for associative memory
• A-MEM (2025) — Zettelkasten-inspired dynamic memory organization
• MELODI (DeepMind, 2024) — gist-based memory compression
• ReadAgent (DeepMind, 2024) — episodic memory for context extension

Full writeups, findings, and how AutoMem implements each → docs/RESEARCH.md.

Run it

Railway (60 seconds)

Recommended Railway projects run AutoMem as a small service group: automem (the API), automem-graph-viewer (the standalone UI), falkordb (graph), qdrant (vectors), and `mcp-aut