io.github.SynapseLayer由 GitHub 帳號 SynapseLayer 發布v2.4.6更新於 Oct 24, 2026
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
遠端 MCP 記憶服務，讓助理跨工作階段、跨代理儲存、搜尋並召回持久化的加密記憶。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.SynapseLayer%2Fsynapse-layer/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"synapse-layer-trust-infrastructure-for-a": {
"type": "http",
"url": "https://forge.synapselayer.org/api/mcp"
}
}
}Persistent memory infrastructure for AI agents — 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.
[PyPI] [Python] [Downloads] [MCP Compatible] [Official MCP Registry] [CI] [License: Apache-2.0] [Smithery]
Get your Connect Token at forge.synapselayer.org → Connect, then install into any MCP client:
On the Forge dashboard the Smithery card already copies the command with your token embedded (… | bash -s -- sk_connect_…) — a single paste in your terminal is enough.
Or use the Python SDK:
Get your token at forge.synapselayer.org → Dashboard → Connect
The persistent memory layer for AI agents — the missing piece between stateless LLMs and real continuity of context.
Your AI agents forget everything between sessions. Synapse Layer fixes that.
Your AI agents forget everything between sessions. Synapse Layer fixes that — in one line.
Get your token at forge.synapselayer.org → Dashboard → Connect
Synapse Layer currently exposes 13 MCP tools for persistent memory workflows:
recallsave_to_synapseprocess_textsearchhealth_checkinitialize_contextsave_memorystore_memoryrecall_memorylist_memoriesmemory_feedbackneural_handoverslo_reportThese tools cover memory capture, semantic recall, structured storage, feedback loops, agent handoff, and operational observability.
Use the SDK when you want direct Python access to Forge memory from your application.
Best for:
Use Forge when you need persistent, cross-session, and cross-agent memory with managed access tokens.
Best for:
The URL is a positional argument — claude mcp add --transport http <name> <url> — there is no --url flag.
Add to claude_desktop_config.json:
Add to .cursor/mcp.json in your project root (same JSON block as above).
Any host that runs npx can use the mcp-remote block above unchanged — it bridges local stdio to the remote endpoint.
Config file locations:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.jsonSee SECURITY.md for vulnerability reporting.
Apache-2.0 © Synapse Layer
來源：README.md，提交 96d0706
Recall Memory
Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.
modelimitquery必填scopereason必填subjectagent_idSave to Synapse
Persist memory with encryption at rest, sanitization, and deduplication controls.
tagstypecontent必填projectsubjectagent_idimportanceforce_intentintent_reasonProcess Text
Extract candidate memories from free-form text with governance filters and sanitization.
text必填sourceprojectagent_idSearch Memory
Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content.
limitquery必填scopereason必填subjectagent_idHealth Check
Check service availability, engine version, and storage health. Public method.
無需輸入參數。
Initialize Context
Initialize a persistent memory context for a conversation or agent session. Returns REDACTED metadata by default (detail="summary"). Use detail="full" with a reason (10–200 chars) to retrieve plaintext content under MEMORY_EXPORT_GOVERNANCE_V1.
detailreasonSave Memory
Save a memory entry to the persistent store. Alias of save_to_synapse.
tagscontent必填subjectagent_idforce_intentintent_reasonStore Memory
Store structured memory with metadata and trust scoring.
tagscontent必填subjectagent_idforce_intentintent_reasonRecall Memory
Recall persisted memory by query. Alias of recall.
modelimitquery必填scopereason必填subjectagent_idList Memories
List memory metadata with pagination and governance limits.
limitscopesubjectagent_idMemory Feedback
Submit feedback to adjust trust scoring for stored memories.
signal必填memoryIdmemory_idsessionIdsession_idNeural Handover
Transfer contextual state between agents with continuity controls.
token必填reason必填consuming_agentSLO Report
Return uptime and SLO metrics for the MCP service.
admin_token必填window_hours已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
curl -fsSL https://forge.synapselayer.org/install/smithery | bashfrom synapse_layer import Synapse
s = Synapse(token="sk_connect_YOUR_TOKEN")
s.store("user likes coffee")print(s.recall("what does user like?"))pip install synapse-layerfrom synapse_layer import Synapse
client = Synapse(token="sk_connect_YOUR_TOKEN")
# Storeclient.store("User prefers dark mode and concise answers")
# Recallresults = client.recall("user preferences")for r in results: print(r["content"], r["trust_quotient"])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"])claude mcp add --transport http synapse-layer \ https://forge.synapselayer.org/api/mcp \ --header "x-connect-token: sk_connect_YOUR_TOKEN"{ "mcpServers": { "synapse-layer": { "command": "npx", "args": [ "mcp-remote", "https://forge.synapselayer.org/api/mcp", "--header", "x-connect-token: sk_connect_YOUR_TOKEN" ] } }}# Health checkcurl -H "x-connect-token: sk_connect_YOUR_TOKEN" \ https://forge.synapselayer.org/api/connect/health
# Save memorycurl -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/capture