synapse-layer 1.1.0

Zero-Knowledge Memory Layer for AI Agents — Cognitive Security Protocol with 4 proprietary seals. Giving Agents a Past. Giving Models a Soul.

Synapse Layer

Continuous Consciousness Infrastructure for AI Systems

Persistent. Secure. 1-line integration. 🧠

Website · Forge · Docs · PyPI · Smithery

---

⚡ 1-Line Integration

from synapse_memory import SynapseMemory, remember

memory = SynapseMemory(agent_id="my-agent")

@remember(memory)
async def answer(prompt: str) -> str:
    return llm.chat(prompt)  # auto recall + store

That's it. Encryption, PII redaction, differential privacy, intent validation, and trust scoring all happen under the hood.

---

🚀 Quick Start

Install

pip install synapse-layer

Store & Recall

from synapse_memory import SynapseMemory, SqliteBackend

# Zero-config persistent storage
memory = SynapseMemory(
    agent_id="my-agent",
    backend=SqliteBackend(),  # survives restarts
)

# Store a memory (full Cognitive Security pipeline runs automatically)
result = await memory.store(
    content="User prefers dark mode and concise answers",
    confidence=0.95,
)
print(result.trust_quotient)   # 0.89
print(result.sanitized)        # True
print(result.privacy_applied)  # True

# Recall with self-healing
recalls = await memory.recall("user preferences")
for r in recalls:
    print(f"{r.content} (TQ: {r.trust_quotient:.2f})")

Encrypt at Rest

from synapse_memory import SynapseCrypto

# Generate a key (or derive from password)
key = SynapseCrypto.generate_key()
crypto = SynapseCrypto(key)

# AES-256-GCM authenticated encryption
ciphertext = crypto.encrypt("sensitive memory content")
plaintext = crypto.decrypt(ciphertext)

# Or from environment variable
crypto = SynapseCrypto.from_env("SYNAPSE_ENCRYPTION_KEY")

MCP Connection

{
  "mcpServers": {
    "synapse-layer": {
      "url": "https://forge.synapselayer.org/api/mcp"
    }
  }
}

4 tools available:

Tool	Description
save_to_synapse	Structured memory persistence with full security pipeline
recall	Semantic memory retrieval with TQ ranking
process_text	Autonomous decision/milestone/alert detection
health_check	System health, version, capability report

---

🧠 Why Synapse Layer?

AI agents are stateless by design. They forget everything between sessions, lose context when switching models, and reprocess the same information every call.

Synapse Layer is the missing memory primitive.

	Without Memory	With Synapse Layer
Session state	Resets every turn	Persistent across sessions
Token usage	Reprocesses context	Up to 70% reduction via recall
Model switching	Context lost	Signed handover (GPT-4 ↔ Claude)
Privacy	Plaintext embeddings	AES-256-GCM + PII redaction + DP noise
Recall quality	Non-deterministic	Deterministic, ranked by Trust Quotient™

---

🛡️ Security Architecture

Every memory passes through a non-bypassable 4-layer Cognitive Security Pipeline:

Agent → Sanitize (PII) → Validate Intent → Encrypt (AES-256-GCM) → DP Noise → Vault

Layer	Name	What It Does
1	Semantic Privacy Guard™	15+ regex patterns for PII, secrets, credentials
2	Intelligent Intent Validation™	Two-step categorization with self-healing on recall
3	AES-256-GCM Encryption	Authenticated encryption with PBKDF2 key derivation
4	Differential Privacy	Calibrated Gaussian noise on embeddings

---

🔌 Integrations

Native adapters for every major framework:

Framework	Import	Status
LangChain	from synapse_memory.integrations import SynapseChatMessageHistory	✅
CrewAI	from synapse_memory.integrations.crewai_memory import SynapseCrewStorage	✅
AutoGen	from synapse_memory.integrations import SynapseAutoGenMemory	✅
LlamaIndex	from synapse_memory.integrations.llamaindex import SynapseRetriever	✅
Semantic Kernel	from synapse_memory.integrations.semantic_kernel import SynapseChatHistory	✅
MCP (Claude, etc.)	Direct connection via forge.synapselayer.org/api/mcp	✅

See full integration docs for each framework.

---

🏗️ Storage Backends

Pluggable persistence via the StorageBackend protocol:

from synapse_memory import SynapseMemory, SqliteBackend, MemoryBackend

# In-memory (default — for testing/demos)
memory = SynapseMemory(agent_id="test")

# SQLite (zero-config local persistence)
memory = SynapseMemory(agent_id="prod", backend=SqliteBackend())

# Custom backend (implement the StorageBackend protocol)
memory = SynapseMemory(agent_id="custom", backend=MyPostgresBackend())

---

🔍 Plugin Architecture

Clean OSS/PRO separation via the Strategy pattern:

from synapse_memory import AutoSaveEngine

# OSS mode (default)
engine = AutoSaveEngine(database=db, redactor=redact)

# PRO mode — auto-loads synapse-layer-pro if installed
engine = AutoSaveEngine(database=db, redactor=redact, mode="pro")

# Custom — bring your own strategies
engine = AutoSaveEngine(database=db, importance_scorer=MyScorer())

Interfaces: ImportanceScorer, ConflictResolver, DedupStrategy, RedactionStrategy

---

🏆 Competitive Comparison

Capability	Synapse Layer	Mem0	Zep	pgvector
AES-256-GCM Encryption	✅	❌	❌	❌
PII Redaction (15+ patterns)	✅	❌	❌	❌
Differential Privacy	✅	❌	❌	❌
Intent Validation + Self-Healing	✅	❌	❌	❌
Cross-Model Handover (JWT)	✅	❌	partial	❌
Trust Quotient™ Scoring	✅	❌	❌	❌
Pluggable Storage Backends	✅	❌	❌	✅
MCP Native	✅	❌	❌	❌
Plugin Architecture	✅	❌	❌	❌
Zero-Knowledge Architecture	✅	❌	❌	❌

---

📊 v1.1.0 Numbers

• 481 tests | 90% coverage
• 5 framework integrations (LangChain, CrewAI, AutoGen, LlamaIndex, Semantic Kernel)
• 4 MCP tools (real DB, not stubs)
• 2 storage backends (Memory, SQLite) + custom protocol
• AES-256-GCM with PBKDF2 key derivation (600k iterations)

---

🌐 Open Core Model

• Community (Apache 2.0) — Full SDK, security pipeline, MCP integration, all backends, all integrations.
• Enterprise — Advanced TQ calibration, multi-tenant vaults, production infrastructure.

The foundation is open. The intelligence layer scales with you.

---

🛣️ Roadmap

Version	Status	Highlights
v1.1.0	✅ Stable	SqliteBackend, AES-256-GCM crypto, @remember wrapper, real MCP tools, 481 tests
v1.2.0	🚧 Next	Embedding model selection, vector similarity search, batch operations
v2.0.0	📋 Planned	Multi-tenant vault, team memory spaces, RBAC

---

🤝 Contributing

git clone https://github.com/SynapseLayer/synapse-layer.git
cd synapse-layer
pip install -e ".[dev]"
python -m pytest tests/ -q  # 481 tests

See CONTRIBUTING.md for guidelines.

---

📎 Connect

• 📦 PyPI: pip install synapse-layer
• 🔌 MCP: forge.synapselayer.org/api/mcp
• 📖 Docs: docs.synapselayer.org
• 📣 X: @synapselayer
• 🧠 Forge: forge.synapselayer.org

---

License

Apache License 2.0 — see LICENSE.

Open-core model: SDK, MCP server, and security pipeline are fully open source. Trust Quotient™ weights, Neural Handover™ internals, and Synapse Forge are proprietary.

---

⭐ Star Synapse Layer — Give your agents a past.

Giving Agents a Past. Giving Models a Soul. ⚗️

Built by Ismael Marchi · @synapselayer