mnemosyne-memory 3.1.0

The Zero-Dependency, Sub-Millisecond AI Memory System

Mnemosyne

Zero-dependency AI memory that works everywhere. SQLite-backed. Sub-millisecond. Fully private.

Mnemosyne is a universal memory layer for AI agents. Drop it into any agent framework — Hermes, Claude Code, Cursor, Codex, OpenWebUI, OpenClaw, or your own custom agent. One pip install, one SQLite database, zero cloud dependencies.

---

Works With Everything

Platform	Method	Setup
Cursor	MCP	Add to .cursor/mcp.json
Claude Code	MCP	Add to claude.json
OpenAI Codex CLI	MCP	Add to .codex/mcp.json
Windsurf	MCP	Add to .windsurf/mcp_config.json
OpenWebUI	Native @tool	Drop bridge file into data/tools/
OpenClaw	Native provider	pip install mnemosyne-memory[openclaw]
Hermes Agent	MCP + Plugin	Native — ships enabled
Any MCP client	MCP (stdio/SSE)	One config line
Any Python agent	Direct SDK	import mnemosyne

See docs/integrations/ for complete setup guides per platform.

---

Quick Start

pip install mnemosyne-memory

# With all features (vector search + MCP server)
pip install "mnemosyne-memory[all]"

Add to your agent

MCP-based (Cursor, Claude Code, Codex, Windsurf):

{
  "mcpServers": {
    "mnemosyne": {
      "command": "mnemosyne",
      "args": ["mcp"],
      "env": {}
    }
  }
}

Python SDK (any agent):

from mnemosyne import remember, recall

remember("User prefers dark mode interfaces")
results = recall("user preferences")

OpenWebUI: Drop a 1-line bridge file into data/tools/.

OpenClaw: Add provider: mnemosyne.integrations.openclaw:create_provider to config.

---

Benchmark

Mnemosyne v3 scores 65.2% on the BEAM long-context memory benchmark (ICLR 2026) at 100K scale — competitive with cloud alternatives while running fully offline, all in a single SQLite file.

Scale	Mnemosyne v3	Honcho	Hindsight	LIGHT	RAG
100K	65.2%	63.0%	73.4%	35.8%	32.3%

Per-ability (100K): IE 91.5% · MR 87.5% · TR 75.0% · ABS 100.0% · CR 50.0% · KU 50.0% · EO 25.0% · IF 62.5% · PF 54.5% · SUM 55.6%

Full report: docs/beam-benchmark.md

---

CLI Usage

# MCP server (works with any MCP client)
mnemosyne mcp                          # stdio (default)
mnemosyne mcp --transport sse --port 8080  # SSE (web clients)

# Direct memory ops
mnemosyne remember "User likes dark mode"
mnemosyne recall "preferences"
mnemosyne stats
mnemosyne sleep                         # Run consolidation

# Export / import
mnemosyne export --output backup.json
mnemosyne import --input backup.json

---

Python API

from mnemosyne import remember, recall

# Store a fact
remember("User prefers dark mode interfaces",
         importance=0.9, source="preference")

# Store globally (visible across all sessions)
remember("User email is [e-mail]",
         importance=0.95, scope="global")

# Store with expiry
remember("Temp token: abc123",
         importance=0.8, valid_until="2026-12-31")

# Search
results = recall("interface preferences", top_k=3)

# Temporal recall (recency boost)
results = recall("deployments",
                 temporal_weight=0.5, temporal_halflife=48.0)

# Entity extraction
remember("Met with Abdias about the v2 release",
         extract_entities=True)

# LLM-driven fact extraction
remember("User said they prefer Python for backend work",
         extract=True)

# Temporal triples (knowledge graph)
from mnemosyne.core.triples import TripleStore
kg = TripleStore()
kg.add("Maya", "assigned_to", "auth-migration",
       valid_from="2026-01-15")
kg.query("Maya", as_of="2026-02-01")

# Memory banks (per-domain isolation)
from mnemosyne.core.banks import BankManager
BankManager().create_bank("work")
work_mem = Mnemosyne(bank="work")
work_mem.remember("Sprint review on Friday")

Advanced: BEAM Direct Access

from mnemosyne.core.beam import BeamMemory

beam = BeamMemory(session_id="my_session")
beam.remember("Important context", importance=0.9)
beam.consolidate_to_episodic(
    summary="User likes Neovim",
    source_wm_ids=["wm1"]
)
results = beam.recall("editor preferences", top_k=5)

---

Architecture

┌────────────────────────────────────────────────────────────┐
│                    Any AI Agent                            │
│  (Hermes · Claude Code · Cursor · Codex · OpenWebUI · MCP) │
└────────────────────────┬───────────────────────────────────┘
                         │ MCP / SDK / Plugin
┌────────────────────────▼───────────────────────────────────┐
│                      Mnemosyne BEAM                         │
│  ┌────────────┐  ┌──────────────┐  ┌────────────────────┐   │
│  │ Working    │  │ Episodic     │  │ TripleStore         │   │
│  │ Memory     │──▶│ Memory       │  │ (Temporal KG)      │   │
│  │ (hot ctx)  │  │ (long-term)  │  └────────────────────┘   │
│  └────────────┘  └──────┬───────┘                           │
│                         │                                    │
│              ┌──────────▼──────────┐                        │
│              │     SQLite DB       │                        │
│              │  (single file)      │                        │
│              │  sqlite-vec + FTS5  │                        │
│              │  MIB binary vectors │                        │
│              └─────────────────────┘                        │
└─────────────────────────────────────────────────────────────┘

BEAM (Bilevel Episodic-Associative Memory):

• Working memory — Hot context, auto-injected before LLM calls, TTL-based eviction
• Episodic memory — Long-term storage with sqlite-vec + FTS5 hybrid search
• TripleStore — Temporal knowledge graph with version chains

Hybrid scoring: 50% vector similarity + 30% FTS5 rank + 20% importance, all inside SQLite.

Binary vectors: Information-theoretic binarization (MIB) compresses 384-dim float32 embeddings into 48 bytes — 32x reduction. Hamming distance entirely within SQLite. No ANN indices, no external vector DB.

---

Why Mnemosyne?

Feature	Mnemosyne	mem0	Letta	Honcho	SuperMemory	Hindsight	ChromaDB
Local-first	✅ SQLite	⚠️ Hybrid	❌ Docker+PG	⚠️ PG+worker	❌ SaaS	✅ SQLite	✅ Embedded
Zero deps	✅ pip only	❌ Qdrant/PG	❌ PG+vector	❌ PG+3 LLMs	❌ SaaS infra	✅ pip only	✅ pip only
MCP server	✅ Built-in	❌	❌	❌	✅	❌	❌
Python SDK	✅	✅	✅	✅	✅	✅	✅
Multi-platform	✅ 8+ targets	⚠️ 3 adapters	❌ Agent-only	⚠️ 4 adapters	✅ MCP	❌ Agent-only	❌ Library only
Open source	✅ MIT	✅ Apache 2.0	✅ OSS	⚠️ AGPL	❌ Proprietary	✅ MIT	✅ Apache 2.0
Benchmark	65.2% BEAM	49% LongMem	83.2% LoCoMo	90.4% LongMem	85.2% MemoryBench	73.4% BEAM	N/A (vector DB)
Self-hosted	✅ Yes	✅ Optional	✅ Optional	✅ Yes	❌ Enterprise	✅ Yes	✅ Yes
Integration template	✅ Published	❌	❌	❌	❌	❌	❌
Memory architecture	BEAM (3-tier)	Session + facts	OS-virtual context	Peer + reasoning	5-layer stack	Episodic + semantic	Vector store only
Purpose	Full memory system	Memory API	Agent runtime	Managed memory	Consumer + agent	Research memory	Vector database

---

Configuration

Environment Variables

Variable	Default	Description
MNEMOSYNE_DATA_DIR	~/.hermes/mnemosyne/data	Database directory
MNEMOSYNE_VEC_TYPE	int8	Vector compression: float32, int8, or bit
MNEMOSYNE_VEC_WEIGHT	0.5	Vector similarity weight
MNEMOSYNE_FTS_WEIGHT	0.3	FTS5 keyword weight
MNEMOSYNE_IMPORTANCE_WEIGHT	0.2	Importance weight
MNEMOSYNE_WM_MAX_ITEMS	10000	Working memory limit
MNEMOSYNE_RECENCY_HALFLIFE	168	Decay halflife in hours

Full reference: docs/configuration.md

---

Hermes Plugin (17 tools)

When used with Hermes Agent, Mnemosyne exposes 17 tools for memory lifecycle management — 3 lifecycle hooks (pre_llm_call, on_session_start, post_tool_call) for automatic context injection, plus full MCP support.

See docs/hermes-integration.md.

---

Contributing

See CONTRIBUTING.md for guidelines.

Full docs: docs/ · Changelog: CHANGELOG.md · Releases: GitHub Releases · Integrations: docs/integrations/

---

Support

Discord: Join the Mnemosyne community · Issues: GitHub Issues

⭐ Star the repo if you find it useful!

---

License

MIT License — See LICENSE

Copyright (c) 2026 Abdias J

---

"The faintest ink is more powerful than the strongest memory." — Hermes Trismegistus