Synapse Layer docs

Get started in 3 steps

1. 1

   Create your free account and copy an API key: forge.synapselayer.org

2. 2

   Install the MCP server or SDK (below).

3. 3

   Send your first encrypted memory with store() or curl.

Autonomous Agent Onboarding (No UI / No Browser)

Agents can provision themselves without a dashboard or login. A single POST to /api/v1/agent-onboard returns a temporary sk_connect_temp_ token good for 50 calls / 72h — enough to test store, recall, and handover end-to-end.

# No login, no dashboard, no browser — provision a temporary agent token
curl -X POST https://forge.synapselayer.org/api/v1/agent-onboard \
  -H "Content-Type: application/json" \
  -d '{"purpose":"doc-example-autonomous-agent"}'

# Resposta HTTP 200: { token, agentId, plan, quota, calls_remaining, expires_at, upgrade_url }
# token = sk_connect_temp_... · 50 calls / 72h

Send the returned token in the x-connect-token header on every request. When the trial is exhausted, create a free account for a permanent key.

Install

pip install synapse-layer

npm install synapse-layer

Requirements: Python 3.9+ or Node 18+, an API key. No local database, no file locking — memory lives server-side, encrypted at rest.

Quick start

from synapse_layer import Synapse

client = Synapse(token="YOUR_KEY")

# Save what the user told you
client.store(
    content="User prefers dark mode and terse answers.",
    memory_type="long_term",
)

# Recall what you (or another agent) learned
memories = client.recall(query="preferences")

# Cross-agent handover — MCP tool neural_handover (NOT a client method)
# Requires: token (64 hex chars, from Forge UI) + reason (10–200 chars)
curl -X POST "https://forge.synapselayer.org/api/mcp" \
  -H "x-connect-token: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"neural_handover",
                 "arguments":{"token":"<64-hex>",
                              "reason":"Receiving project context from Claude session",
                              "consuming_agent":"my-agent"}}}'

MCP configuration

Synapse Layer is a first-class MCP server. It exposes 13 tools over streamable HTTP, so any MCP host (Claude Desktop, Cursor, Codex, Cline, Roo, LangChain) can read and write the same shared memory.

{
  "mcpServers": {
    "synapse-layer": {
      "type": "http",
      "url": "https://forge.synapselayer.org/api/mcp",
      "headers": { "x-connect-token": "YOUR_KEY" }
    }
  }
}

claude mcp add synapse-layer \
  --transport http \
  --url "https://forge.synapselayer.org/api/mcp" \
  --header "x-connect-token: YOUR_KEY"

npx -y smithery mcp add synapselayer/synapselayer

# A local stdio binary is a roadmap item — the published
# MCP server runs on streamable HTTP at forge.synapselayer.org/api/mcp,
# so every host targets the same endpoint regardless of language or OS.

Need proper setup with your platform? Use the guided Connect page — paste your key, pick your platform, copy the config.

Drop-in system prompt. Paste this directive into any agent so it uses Synapse Layer memory automatically:

[SYNAPSE LAYER MEMORY DIRECTIVE]
You have persistent cross-session memory via Synapse Layer (MCP).

RULE 1 — STORE: After any decision, user preference, or project rule,
call store() to persist it. Never rely on the context window alone.

RULE 2 — RECALL: At the start of every task, call recall() to load
prior decisions, preferences, and rules before acting.

RULE 3 — HANDOVER: When work passes to another agent or session,
call handover() so the next agent inherits full context.

REST API

The same engine behind MCP is available as a REST API (OpenAPI 3.1). Authenticate with the x-connect-token header (sk_connect_…).

curl -X POST https://forge.synapselayer.org/api/v1/capture \
  -H "x-connect-token: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content":"User prefers dark mode","agent_id":"my-agent"}'

try:
    client.store(content="...")
except QuotaExceeded as e:
    print(f"Limite atingido - upgrade: {e.upgrade_url}")

HTTP/1.1 402 Payment Required
{
  "code": "quota_exceeded",
  "upgrade_url": "https://forge.synapselayer.org/billing/upgrade"
}

Try every endpoint in the browser →

The 13 tools

Discover the full interface with tools/list. Memory tools accept an agent_id scope; utilities (health_check, initialize_context, slo_report) and neural_handover use their own parameters.

Security model

• •AES-256-GCM at rest, per-operation IV — every memory is encrypted with its own initialization vector; key rotation without re-encryption.
• •OAuth 2.0 + PKCE S256 — no password sent over the wire; refresh-token rotation.
• •Semantic Privacy Guard™ — PII detection (11 patterns) with differential-privacy redaction before storage.
• •Trust Quotient (0.0–1.0) — memories are scored; low-trust entries rank lower in recall.
• •Immutable audit trail — every store, recall, delete, and handover is logged.
• •Lifecycle governance — live → tombstone → analytics with guaranteed erasure.

Machine-readable trust manifest →

Data lifecycle & compliance

→Memories progress live → tombstone (deleted) → analytics (aggregate metadata only). Vault-deletion is irreversible and audited. Built aligned with LGPD and GDPR.

Pricing & limits

AI Agents can query live pricing programmatically: GET https://forge.synapselayer.org/.well-known/pricing.json.

Registries & discovery

Synapse Layer is registered across the MCP ecosystem. Machines and agents can discover everything automatically:

• MCP Marketplace
• Smithery
• Glama
• Official MCP Registry — io.github.SynapseLayer/synapse-layer
• MCP manifest · server card (13 tools)
• llms.txt · llms-full.txt · agent skill

Support & feedback

Questions, bugs, or feature requests — we answer fast:

• ✉️ [email protected]
• GitHub Issues: SynapseLayer/synapse-layer
• Dashboard: forge.synapselayer.org