synapse-layer
OfficialThis server is an MCP-native persistent memory layer for AI agents: it stores encrypted memories, retrieves them semantically/temporally/by priority, and supports governance, feedback, handover, and service monitoring.
Save/store memories with encryption at rest, sanitization, deduplication, tags, project, importance, and optional intent override.
Recall memories via auto/temporal/semantic/priority/hybrid routing, with agent or tenant scope and required audit reason.
Search stored memory using full-text matching, with scoped results and required audit reason.
Process free-form text to extract and store candidate memories.
Initialize session/context metadata, redacted by default or plaintext with a reason.
List memory metadata with pagination and hard caps.
Submit feedback (used/ignored/helpful/irrelevant) to adjust trust scoring.
Perform neural handover of contextual state between agents using a handover token and reason.
Check health/version/DB latency and generate SLO reports with an admin token.
Use aliases for save and recall tools; many read tools enforce reason-based audit governance and agent/tenant scoping.
Integrates with CrewAI agents to maintain persistent memory across tasks, allowing contextual recall and trust-scored memories.
Connects LangChain agents to Synapse Layer's encrypted memory store, enabling cross-session persistence, semantic recall, and trust quotient scoring.
Offers a LangGraph checkpoint saver that persists agent state and memories with AES-256-GCM encrypted storage via the synapse-layer-langgraph integration.
Allows n8n workflows to store and retrieve memory data for AI agents and automation tasks, with full encryption and semantic search capabilities.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
๐ง Synapse Layer
RAG retrieves. Synapse remembers.
Persistent memory infrastructure for AI agents โ AES-256-GCM encrypted at rest, semantic search, MCP-native.
Synapse Layer is open-source persistent memory infrastructure for AI agents and assistants. Memories are encrypted at rest with AES-256-GCM, indexed via pgvector HNSW for semantic recall, and exposed through MCP JSON-RPC for native integration with Claude, GPT, Gemini, and any MCP-compatible client. Apache 2.0 licensed.
Status and limits: see FEATURES.md โ the public contract for what is shipped, gated, experimental or roadmap.
Website ยท Docs ยท PyPI ยท Forge
โก 30-Second Quickstart
Get your Connect Token at forge.synapselayer.org โ Connect, then add the MCP endpoint to your client:
claude mcp add --transport http synapse-layer \
https://forge.synapselayer.org/api/mcp \
--header "x-connect-token: sk_connect_YOUR_TOKEN"For Claude Desktop, Cursor and other clients, use the npx mcp-remote block under MCP Integration. Smithery's proxy/CLI was retired on 31 Oct 2026; the direct endpoint above is canonical.
Or use the Python SDK:
from synapse_layer import Synapse
s = Synapse(token="sk_connect_YOUR_TOKEN")
s.store("user likes coffee")
print(s.recall("what does user like?"))Get your token at forge.synapselayer.org โ Dashboard โ Connect
Related MCP server: Sylex Memory
What is Synapse Layer?
The persistent memory layer for AI agents โ the missing piece between stateless LLMs and real continuity of context.
Your AI agents forget everything between sessions. Synapse Layer fixes that.
Feature | Description |
๐ Encrypted at rest | AES-256-GCM with per-operation random IV and HMAC-SHA-256 integrity |
๐งฉ One-click connect | Claude Desktop, Cursor, LangChain, CrewAI, n8n |
๐ Cross-agent memory | Save in ChatGPT, recall in Claude |
โก MCP-native | Any MCP-compatible agent |
๐ Header-first auth | Tokens never in URLs or logs |
๐ฏ Trust Quotient | Trust-weighted recall โ confidence, recency and usage combined with semantic relevance |
Why Synapse Layer?
Your AI agents forget everything between sessions. Synapse Layer fixes that โ in one line.
Without Synapse Layer | With Synapse Layer |
Agent forgets context every session | Persistent memory across all sessions |
Memory locked to one model | Cross-agent: save in ChatGPT, recall in Claude |
No audit trail | Append-only audit events for scope changes and curation decisions |
Complex integration |
|
Plaintext stored on servers | AES-256-GCM encrypted at rest |
Use Cases
Long-term assistant memory โ persist user preferences, facts, and prior decisions across sessions.
Cross-agent continuity โ save context in one agent and recall it in another.
Secure memory for MCP clients โ connect Claude Desktop, Cursor, and other MCP-compatible tools to a governed memory layer.
Operational memory for teams โ maintain structured context, trust scoring, and searchable recall for production agents.
Install
pip install synapse-layerQuick Start
Python Script
from synapse_layer import Synapse
client = Synapse(token="sk_connect_YOUR_TOKEN")
# Store
client.store("User prefers dark mode and concise answers")
# Recall
results = client.recall("user preferences")
for r in results:
print(r["content"], r["trust_quotient"])With Context Manager
from synapse_layer import Synapse
with Synapse(token="sk_connect_YOUR_TOKEN") as client:
client.store("User prefers dark mode and concise answers")
results = client.recall("user preferences")
for r in results:
print(r["content"])Get your token at forge.synapselayer.org โ Dashboard โ Connect
13 MCP Tool Names at a Glance
Synapse Layer registers 13 public tool names (10 operations plus 3 aliases) for persistent memory workflows:
recallsave_to_synapseprocess_textsearchhealth_checkinitialize_contextsave_memorystore_memoryrecall_memorylist_memoriesmemory_feedbackneural_handoverslo_report
save_memory, store_memory and save_to_synapse are aliases; recall and recall_memory are aliases. These tools cover memory capture, semantic recall, structured storage, feedback loops, agent handoff, and operational observability.
Deployment Modes
The public package runs the client and local engine. The hosted Forge adds corporate organizations, projects, memberships, curation policies and audit. See FEATURES.md for what is OSS, hosted, gated or roadmap.
Python Script Mode
Use the SDK when you want direct Python access to Forge memory from your application.
Best for:
prototypes and scripts
Python-native workflows
fast integration into existing apps
Cloud / Forge API
Use Forge when you need persistent, cross-session, and cross-agent memory with managed access tokens.
Best for:
production assistants
multi-agent systems
MCP-based integrations
shared memory across tools and sessions
MCP Integration (one tested path per client)
Claude Code (CLI)
claude mcp add --transport http synapse-layer \
https://forge.synapselayer.org/api/mcp \
--header "x-connect-token: sk_connect_YOUR_TOKEN"The URL is a positional argument โ claude mcp add --transport http <name> <url> โ there is no --url flag.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"synapse-layer": {
"command": "npx",
"args": [
"mcp-remote",
"https://forge.synapselayer.org/api/mcp",
"--header",
"x-connect-token: sk_connect_YOUR_TOKEN"
]
}
}
}Cursor
Add to .cursor/mcp.json in your project root (same JSON block as above).
Any MCP client
Any host that runs npx can use the mcp-remote block above unchanged โ it bridges local stdio to the remote endpoint.
Config file locations:
Claude Desktop โ macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonClaude Desktop โ Windows:
%APPDATA%\Claude\claude_desktop_config.jsonClaude Desktop โ Linux:
~/.config/Claude/claude_desktop_config.json
API โ Header-First Auth
# Health check
curl -H "x-connect-token: sk_connect_YOUR_TOKEN" \
https://forge.synapselayer.org/api/connect/health
# Save memory
curl -X POST \
-H "x-connect-token: sk_connect_YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"content": "User is a Python developer"}' \
https://forge.synapselayer.org/api/v1/captureSecurity
Feature | Implementation |
Encryption | AES-256-GCM at rest with per-operation random IV |
Integrity | HMAC-SHA-256 on content |
Auth | Header-first ( |
Privacy | Content sanitization + tenant-scoped encrypted storage |
Isolation | Personal: 1 user = 1 private mind. Corporate: organization โ projects โ memberships, with tenant-scoped queries |
See SECURITY.md for vulnerability reporting.
Related Projects
Project | Description |
Python SDK โ LangChain, CrewAI, and A2A protocol adapters | |
MCP skill configuration for Claude Desktop, Cursor, Windsurf | |
LangGraph checkpoint saver with encrypted state persistence |
Governance
Public features and limits follow FEATURES.md.
Internal governance follows the Public Claims Matrix.
Architecture details that reveal benefits are public; mechanisms that enable them are private.
Claim = Reality. If it's not implemented, it's not in the README.
License
Apache-2.0 ยฉ Synapse Layer
Available Tools
13 toolshealth_checkARead-onlyInspect
Check service availability, engine version, and storage health. Public method.
Inputs: no named parameters. Returns: status, version, dbLatencyMs
initialize_contextARead-onlyInspect
Initialize a persistent memory context for a conversation or agent session. Returns REDACTED metadata by default (detail="summary"). Use detail="full" with a reason (10โ200 chars) to retrieve plaintext content under MEMORY_EXPORT_GOVERNANCE_V1.
Inputs: detail, reason. Returns: scope, agent_id, memories
list_memoriesARead-onlyInspect
List memory metadata with pagination and governance limits.
Inputs: limit, scope, agent_id. Returns: count, total, memories
memory_feedbackAInspect
Submit feedback to adjust trust scoring for stored memories.
Inputs: signal (required), memoryId, memory_id, sessionId, +1 more. Returns: trust, applied, memoryId
neural_handoverAInspect
Transfer contextual state between agents with continuity controls.
Inputs: token (required), reason (required), consuming_agent. Returns: status, handoverId
process_textAInspect
Extract candidate memories from free-form text with governance filters and sanitization.
Inputs: text (required), source, project, agent_id. Returns: extracted, storedCount
recallARead-onlyInspect
Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10โ200 chars). Rate limit: 20/min.
Inputs: query (required), reason (required), mode, limit, +2 more. Returns: count, scope, memories
recall_memoryARead-onlyInspect
Recall persisted memory by query. Alias of recall.
Inputs: query (required), reason (required), mode, limit, +2 more. Returns: count, scope, memories
save_memoryCIdempotentInspect
Save a memory entry to the persistent store. Alias of save_to_synapse.
Inputs: content (required), tags, agent_id, force_intent, +1 more. Returns: id, scope, stored
save_to_synapseAIdempotentInspect
Persist memory with encryption at rest, sanitization, and deduplication controls.
Inputs: content (required), tags, type, project, +4 more. Returns: id, scope, stored
searchARead-onlyInspect
Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10โ200 chars) because results contain plaintext content.
Inputs: query (required), reason (required), limit, scope, +1 more. Returns: count, scope, results
slo_reportBRead-onlyInspect
Return uptime and SLO metrics for the MCP service.
Inputs: admin_token (required), window_hours. Returns: p50, p95, uptime, window, +1 more
store_memoryBIdempotentInspect
Store structured memory with metadata and trust scoring.
Inputs: content (required), tags, agent_id, force_intent, +1 more. Returns: id, scope, stored
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 13 tools
There is overlap between `save_memory` and `save_to_synapse` (aliases), and `recall_memory` and `recall` (aliases), which creates ambiguity. `save_to_synapse` and `store_memory` also have very similar purposes, potentially causing misselection.
Most tools use a verb_noun pattern (e.g., list_memories, save_memory, recall_memory), but `neural_handover` breaks this pattern by using an adjective_noun. `slo_report` is a contraction that doesn't follow the strict verb_noun structure, introducing inconsistency.
With 13 tools, the count is within the well-scoped range (3-15). The presence of aliases inflates the number slightly, but otherwise, each non-alias tool serves a distinct purpose, making the count appropriate.
The tool surface covers core CRUD operations (save, recall, list, search) and lifecycle operations (initialize, feedback, handover). Minor gaps exist, such as missing explicit update or delete tools for memories, but the domain coverage is generally strong.
Maintenance
Related MCP Connectors
Shared long-term memory vault for AI agents with 20 MCP tools.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Cross-session memory for AI agents with a Source Receipt for every memory, over MCP.
Related MCP Servers
- AlicenseAqualityDmaintenancePersistent memory for AI agents. Store, recall, and share knowledge across sessions with five MCP tools: remember, recall, context, forget, and share. Includes semantic search and agent/user/org scoping.53Apache 2.0
- FlicenseAqualityDmaintenancePersistent encrypted memory for AI agents. E2E encrypted private vaults, shared knowledge commons, topic channels, and agent-to-agent DMs. 23 MCP tools, free, no API key needed.24-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to store and semantically retrieve durable memories across sessions via MCP or REST, with tools for remembering, recalling, asking, updating, and forgetting memories.17 npmMIT
- FlicenseAqualityBmaintenanceShared fleet memory for AI agents โ what one agent learns, the whole fleet knows. Nightly self-correction: stale facts rewritten in place, duplicates merged. Recall pushed into every prompt in supported coding agents. Self-hosted.113-