Skip to main content

​
Install

pip install synap-pipecat

​
What’s included

ClassPurpose
SynapMemoryProcessorInjects Synap context before the LLM frame processor
SynapRecorderRecords user and assistant turns after the response

​
Quick start

from pipecat.pipeline.pipeline import Pipeline
from pipecat.services.openai import OpenAILLMService
from synap_pipecat import SynapMemoryProcessor, SynapRecorder

memory = SynapMemoryProcessor(
    sdk=sdk,
    user_id="alice",
    customer_id="acme",   # optional
    max_results=6,
)

recorder = SynapRecorder(
    sdk=sdk,
    user_id="alice",
    customer_id="acme",
    conversation_id="call-001",   # optional; auto-generated if omitted
)

pipeline = Pipeline([
    transport.input(),
    stt,
    memory,          # inject memory before LLM
    user_aggregator,
    llm,
    tts,
    transport.output(),
    assistant_aggregator,
    recorder,        # record turn after response
])

​
SynapMemoryProcessor

Intercepts LLMMessagesFrame events and prepends a system message containing the user’s relevant memories before the frame reaches the LLM. 
memory = SynapMemoryProcessor(
    sdk=sdk,
    user_id="alice",
    customer_id="acme",
    max_results=6,
    mode="fast",    # "fast" or "accurate"
)
Failures degrade gracefully — the frame passes through unmodified if context retrieval fails.

​
SynapRecorder

Intercepts TranscriptionFrame (user) and LLMFullResponseEndFrame (assistant) events and ingests the completed turn into Synap asynchronously. 
recorder = SynapRecorder(
    sdk=sdk,
    user_id="alice",
    customer_id="acme",
    conversation_id="call-001",
)
Write failures surface as SynapIntegrationError — Pipecat’s frame error handling will catch and log these.

​
Positioning in the pipeline

transport.input()
    │
    ▼
   STT
    │
    ▼
SynapMemoryProcessor  ← fetches context, prepends to system prompt
    │
    ▼
 UserAggregator
    │
    ▼
   LLM
    │
    ▼
   TTS
    │
    ▼
transport.output()
    │
    ▼
AssistantAggregator
    │
    ▼
 SynapRecorder        ← records completed user + assistant turn

​
Next steps

LiveKit Agents

Context preloading and recording for LiveKit voice agents.

Claude Agent SDK

Hooks and MCP server for the Claude Agent SDK.