AutoMem

August 28, 2026 · View on GitHub

AutoMem

npm version License Discord X LoCoMo on the neutral Agent Memory Benchmark LongMemEval full on AutoMem's internal harness: 87.0% BEAM 10M on the neutral Agent Memory Benchmark Deploy on Railway

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

TypeUse caseExample
RELATES_TOGeneral connectionBug report → Related issue
LEADS_TOCausal relationshipProblem → Solution
OCCURRED_BEFORETemporal sequencePlanning → Execution
PREFERS_OVERUser preferencesPostgreSQL → MongoDB
EXEMPLIFIESPattern examplesCode review → Best practice
CONTRADICTSConflicting infoOld approach → New approach
REINFORCESSupporting evidenceDecision → Validation
INVALIDATED_BYOutdated infoLegacy docs → Current docs
EVOLVED_INTOKnowledge evolutionInitial design → Final design
DERIVED_FROMSource trackingImplementation → Spec
PART_OFHierarchical structureFeature → Epic

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.

CycleFrequencyPurpose
DecayDailyExponential relevance scoring (age, access, connections, importance)
CreativeWeeklyREM-like processing that discovers non-obvious connections
ClusterMonthlyGroups similar memories, generates meta-patterns
ForgetOff by defaultArchives low-relevance memories (<0.2), deletes very old (<0.05)

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)

Deploy on Railway

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-automem (the MCP bridge for ChatGPT, Claude.ai, and ElevenLabs). Services use pre-built Docker images and auto-redeploy on :stable, so Railway does not spend compute rebuilding source.

→ Full setup: INSTALLATION.md

Docker Compose (local)

git clone https://github.com/verygoodplugins/automem.git
cd automem
make dev
ServiceURLPurpose
AutoMem APIhttp://localhost:8001Memory REST API
FalkorDBlocalhost:6379Graph database
Qdrantlocalhost:6333Vector database
FalkorDB Browserhttp://localhost:3000Local graph inspection UI

→ Full setup: INSTALLATION.md

Python (development)

make install
source .venv/bin/activate
PORT=8001 python app.py

Requires Python 3.10+ (3.12 recommended). → INSTALLATION.md

Contributing: feature PRs target the develop branch. main only moves via validated release merges, so users deploying from main (e.g. Railway auto-deploys) see one deploy per release instead of one per PR.

Connect your AI

ClientModeSetup
Claude Desktop, Cursor, Claude Code, Codex, Copilot, AntigravityLocal MCP bridgenpx @verygoodplugins/mcp-automem setup
ChatGPT (developer mode), Claude.ai web/mobile, ElevenLabs AgentsRemote MCP (HTTPS)docs/MCP_SSE.md
Anything elseDirect REST APIdocs/API.md

The MCP bridge is published as @verygoodplugins/mcp-automem. It handles client-specific config (rules files, hooks, templates) and proxies to your AutoMem service — local or Railway.

Direct API call:

import requests

token = "your-automem-api-token"

requests.post(
    "https://your-automem.railway.app/memory",
    headers={"Authorization": f"Bearer {token}"},
    json={
        "content": "Chose PostgreSQL over MongoDB for ACID compliance",
        "type": "Decision",
        "tags": ["database", "architecture"],
        "importance": 0.9,
    },
)

Screenshots

Screenshots will be added once the referenced in-repo image assets are available.

Known limitations

AutoMem is pre-1.0 and honest about its rough edges. The active ones for recall quality:

  • Tags are a hard gate, not a soft boost. Tags filter before scoring, so a memory missing the queried tag won't surface even on a perfect semantic match. Within a tag scope, high-importance off-topic memories can still over-rank — mitigated by the opt-in RECALL_RELEVANCE_GATE, not yet on by default (#130).
  • Temporal and preference updates. Recall doesn't yet reliably prefer the newest version of a conflicting fact, or fully resolve multi-session preference updates. The RECALL_RECENCY_BIAS=auto re-rank helps temporal-intent queries but stays opt-in pending broader validation (#158, #159).
  • The MCP SSE bridge doesn't forward state_mode. The HTTP recall API supports it; the SSE proxy doesn't pass it through yet (#172).
  • Entity-node synthesis is experimental and off by default. First-class Entity nodes (IDENTITY_SYNTHESIS_ENABLED) are gated off while people-entity word-pair noise is addressed (#181).

Docs, community, and license

Setup

API and integration

  • API reference — endpoints, scoring, enrichment
  • Remote MCP — ChatGPT, Claude.ai, ElevenLabs
  • Migrations — embedding dimensions, 0.16.0 data migrations, MCP SQLite import

Research and comparison

Operations

Community

Sibling repos

MIT licensed. Deploy anywhere. No vendor lock-in.