synth-agent-sdk 0.6.1

Autonomous agents, engineered. A Python SDK for building production-grade AI agents and multi-agent systems.

Synth

Autonomous agents, engineered.

Latest Version: 0.6.1 | PyPI | Changelog

A Python SDK for building production-grade AI agents and multi-agent systems. From a 3-line single agent to complex, stateful, resumable multi-agent graphs — with model-agnostic provider support, streaming, observability, evaluation, and guardrails out of the box.

---

Table of Contents

1. What is Synth?
2. Installation
3. Quick Start
4. Core Concepts
5. Creating an Agent
6. Tools
7. Running Your Agent
8. Streaming
9. Model Providers
10. Memory
11. Guards
12. Structured Output
13. Pipelines
14. Graphs
15. Human-in-the-Loop
16. Agent Teams
17. Tracing
18. Checkpointing
19. Evaluation
20. CLI Commands
21. Deploying to AWS AgentCore
22. Error Handling
23. Environment Variables
24. FAQ

---

What is Synth?

Synth is a Python library for building AI-powered agents. An agent uses a large language model (Claude, GPT, Gemini, etc.) to understand instructions, make decisions, and take actions — calling functions, searching databases, generating reports, or coordinating with other agents.

Synth handles the plumbing (provider communication, conversation management, retries, cost tracking) so you focus on what your agent actually does.

---

Installation

Requires Python 3.10+.

pip install synth-agent-sdk[anthropic]     # Anthropic Claude (recommended)

Other options:

pip install synth-agent-sdk[quickstart]    # Claude + GPT (tutorials/demos)
pip install synth-agent-sdk[openai]        # OpenAI GPT
pip install synth-agent-sdk[google]        # Google Gemini
pip install synth-agent-sdk[ollama]        # Local Ollama models
pip install synth-agent-sdk[bedrock]       # AWS Bedrock
pip install synth-agent-sdk[agentcore]     # AWS AgentCore deployment
pip install synth-agent-sdk[all]           # All providers

Set your API key:

export ANTHROPIC_API_KEY="your-key-here"   # Claude
export OPENAI_API_KEY="your-key-here"      # GPT
export GOOGLE_API_KEY="your-key-here"      # Gemini
# AWS Bedrock uses standard IAM credentials — no Synth-specific key needed

Verify your setup:

synth doctor

---

Quick Start

from synth import Agent

agent = Agent(model="claude-sonnet-4-5", instructions="You are a helpful assistant.")
result = agent.run("What is the capital of France?")
print(result.text)
# => "The capital of France is Paris."

---

Core Concepts

Concept	What It Is
Agent	The main building block. Wraps an AI model with tools, memory, and guards.
Tool	A Python function your agent can call.
ToolKit	A bundle of related tools.
RunResult	Returned by agent.run() — text, token usage, cost, latency, trace.
Memory	Lets your agent remember previous conversations.
Guard	A safety rule applied to input or output.
Pipeline	Chains agents sequentially.
Graph	A workflow with branching, loops, and conditional logic.
AgentTeam	Multiple agents coordinated by an orchestrator.
Trace	A detailed record of everything that happened during a run.
Checkpoint	A saved snapshot of a run's state for resumption.

---

Creating an Agent

from synth import Agent, Guard, Memory

agent = Agent(
    model="claude-sonnet-4-5",        # AI model to use
    instructions="You are helpful.",   # System prompt
    tools=[my_tool, my_toolkit],      # Optional tools
    memory=Memory.thread(),           # Optional memory
    guards=[Guard.no_pii_output()],   # Optional safety rules
    output_schema=MyModel,            # Optional Pydantic schema
    max_retries=3,                    # Retry on transient errors
    retry_backoff=1.0,                # Base delay between retries (seconds)
)

All parameters except model are optional. Default model is claude-sonnet-4-5.

---

Tools

Tools are Python functions your agent can call. Mark them with @tool — Synth auto-generates JSON schemas from type hints and docstrings.

from synth import tool

@tool
def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"The weather in {city} is sunny, 72°F."

agent = Agent(
    model="claude-sonnet-4-5",
    instructions="You are a weather assistant.",
    tools=[get_weather],
)

Rules: every parameter needs a type annotation, and the function needs a docstring. Missing either raises ToolDefinitionError immediately.

Group related tools with ToolKit:

from synth import ToolKit

math_tools = ToolKit([add, multiply, divide])
agent = Agent(model="gpt-4o", tools=[math_tools, get_weather])

Inspect tool calls after a run:

for tc in result.tool_calls:
    print(f"{tc.name}({tc.args}) → {tc.result}  [{tc.latency_ms:.1f}ms]")

---

Running Your Agent

Synchronous:

result = agent.run("Explain quantum computing in simple terms.")
print(result.text)        # Response text
print(result.tokens)      # TokenUsage(input, output, total)
print(result.cost)        # Estimated cost in USD
print(result.latency_ms)  # Latency in milliseconds
print(result.tool_calls)  # Tools that were called
print(result.trace)       # Full execution trace
print(result.output)      # Parsed structured output (if output_schema set)

Asynchronous:

import asyncio

async def main():
    result = await agent.arun("What is 2 + 2?")
    print(result.text)

asyncio.run(main())

---

Streaming

from synth import TokenEvent, ToolCallEvent, ToolResultEvent, DoneEvent, ErrorEvent

for event in agent.stream("Write a short poem about coding."):
    if isinstance(event, TokenEvent):
        print(event.text, end="", flush=True)
    elif isinstance(event, ToolCallEvent):
        print(f"\n[Calling: {event.name}]")
    elif isinstance(event, DoneEvent):
        print(f"\n\nTokens: {event.result.tokens.total_tokens}")

Async streaming:

async for event in agent.astream("Write a haiku."):
    if isinstance(event, TokenEvent):
        print(event.text, end="", flush=True)

Event	When
TokenEvent	Model produced a text token
ToolCallEvent	Model decided to call a tool
ToolResultEvent	Tool finished executing
ThinkingEvent	Model produced a reasoning token
DoneEvent	Stream completed — contains full RunResult
ErrorEvent	Something went wrong

---

Model Providers

Switch providers by changing the model string — no other code changes needed.

Provider	Model String Examples	Extra	API Key
Anthropic	"claude-sonnet-4-5", "claude-haiku-3-5"	synth[anthropic]	ANTHROPIC_API_KEY
OpenAI	"gpt-4o", "gpt-4o-mini"	synth[openai]	OPENAI_API_KEY
Google	"gemini-2.0-flash"	synth[google]	GOOGLE_API_KEY
Ollama	"ollama/llama3", "ollama/mistral"	synth[ollama]	None (local)
AWS Bedrock	"bedrock/claude-sonnet-4-5"	synth[bedrock]	AWS IAM

Custom endpoint:

agent = Agent(model="my-model", base_url="https://my-proxy.example.com/v1")

---

Memory

By default each run() is stateless. Add memory to persist conversations.

Thread memory (in-process, fast):

agent = Agent(model="claude-sonnet-4-5", memory=Memory.thread())

agent.run("My name is Alice.", thread_id="user-123")
result = agent.run("What's my name?", thread_id="user-123")
print(result.text)  # "Your name is Alice."

Persistent memory (Redis, survives restarts):

agent = Agent(model="gpt-4o", memory=Memory.persistent("redis://localhost:6379"))

Semantic memory (vector embeddings, retrieves most relevant context):

agent = Agent(model="gemini-2.0-flash", memory=Memory.semantic(embedder=my_embedder_fn))

---

Guards

Declarative safety rules applied automatically to every run.

from synth import Guard

agent = Agent(
    model="claude-sonnet-4-5",
    guards=[
        Guard.no_pii_output(),             # Block PII in responses
        Guard.max_cost(dollars=0.50),       # Stop if cost exceeds $0.50
        Guard.no_tool_calls(["delete_*"]), # Block tools matching glob
        Guard.custom(my_check_fn),          # Your own check function
    ],
)

Guards run in order. First failure stops execution and raises GuardViolationError.

---

Structured Output

Get typed Pydantic objects back instead of raw text:

from pydantic import BaseModel

class MovieReview(BaseModel):
    title: str
    rating: float
    summary: str
    recommended: bool

agent = Agent(
    model="claude-sonnet-4-5",
    instructions="You are a movie critic.",
    output_schema=MovieReview,
)

result = agent.run("Review the movie Inception.")
review = result.output  # MovieReview instance

print(review.title)        # "Inception"
print(review.rating)       # 9.2
print(review.recommended)  # True

If parsing fails, Synth retries with a corrective prompt up to max_retries times.

---

Pipelines

Chain agents sequentially — output of each becomes input of the next:

from synth import Pipeline

researcher = Agent(model="claude-sonnet-4-5", instructions="You research topics.")
writer = Agent(model="claude-sonnet-4-5", instructions="You write clear articles.")
editor = Agent(model="claude-sonnet-4-5", instructions="You edit for clarity.")

pipeline = Pipeline([researcher, writer, editor])
result = pipeline.run("The history of the internet")

Run stages in parallel with ParallelGroup:

from synth.orchestration.pipeline import ParallelGroup

pipeline = Pipeline([
    writer,
    ParallelGroup([fact_checker, style_checker]),  # Run concurrently
    editor,
])

Stream with stage labels:

for stage_event in pipeline.stream("Write about AI"):
    print(f"[{stage_event.stage_name}] {stage_event.event}")

---

Graphs

Directed-graph workflows with branching, loops, and conditional logic:

from synth import Graph, node

graph = Graph()

@node(graph)
def classify(state):
    state["priority"] = "high" if "urgent" in state["text"].lower() else "low"
    return state

@node(graph)
def handle_urgent(state):
    state["response"] = "Escalating immediately."
    return state

@node(graph)
def handle_normal(state):
    state["response"] = "We'll respond within 24 hours."
    return state

graph.set_entry("classify")
graph.add_edge("classify", "handle_urgent", when=lambda s: s["priority"] == "high")
graph.add_edge("classify", "handle_normal", when=lambda s: s["priority"] == "low")
graph.add_edge("handle_urgent", Graph.END)
graph.add_edge("handle_normal", Graph.END)

result = graph.run({"text": "This is urgent! Server is down!"})
print(result.output["response"])

Loops are supported. Synth enforces max_iterations=100 by default to prevent infinite loops.

Visualize your graph:

print(graph.visualise())  # Outputs a Mermaid diagram

---

Human-in-the-Loop

Pause a graph at specific nodes for human review before continuing:

graph.with_human_in_the_loop(pause_at=["draft_email"], timeout=3600)
graph.with_checkpointing()

result = graph.run({"customer": "Alice"}, run_id="email-001")
# result is a PausedRun — inspect result.state["draft"] here

final = graph.resume("email-001", human_input="Looks good, send it.")

---

Agent Teams

Coordinate multiple specialized agents under an orchestrator:

from synth import AgentTeam

team = AgentTeam(
    orchestrator="claude-sonnet-4-5",
    agents=[researcher, writer, analyst],
    strategy="auto",   # orchestrator decides who does what
)

result = team.run("Write a report on renewable energy trends.")
print(result.answer)
print(result.contributions)   # Each agent's individual contribution
print(result.total_cost)

Use strategy="parallel" to run all agents concurrently.

---

Tracing

Every run automatically records a detailed trace:

result = agent.run("Summarize this document.")
trace = result.trace

print(f"Tokens: {trace.total_tokens}")
print(f"Cost: ${trace.total_cost:.4f}")
print(f"Latency: {trace.total_latency_ms:.1f}ms")

result.trace.show()                    # Open visual timeline in browser
path = result.trace.export()           # Export as OpenTelemetry JSON

Auto-forward all traces to an OTel collector:

export SYNTH_TRACE_ENDPOINT="https://my-otel-collector.example.com/v1/traces"

---

Checkpointing

Save and resume graph execution state:

graph.with_checkpointing()
result = graph.run(initial_state, run_id="my-run-001")

# Later, even in a different process
result = graph.resume("my-run-001")

Redis backend for distributed systems:

from synth.checkpointing.redis import RedisCheckpointStore

graph.with_checkpointing(store=RedisCheckpointStore("redis://localhost:6379"))

---

Evaluation

Run structured tests against your agent:

from synth import Eval

evaluation = Eval(agent=agent)
evaluation.add_case(input="Capital of France?", expected="Paris")
evaluation.add_case(input="Capital of Japan?", expected="Tokyo")

report = evaluation.run()
print(f"Score: {report.overall_score}")

for case in report.cases:
    status = "PASS" if case.passed else "FAIL"
    print(f"  [{status}] {case.input} → {case.actual}")

Custom checker:

def contains_keyword(output: str, expected: str) -> float:
    return 1.0 if expected.lower() in output.lower() else 0.0

evaluation.add_case(input="Explain photosynthesis.", expected="chlorophyll", checker=contains_keyword)

---

CLI Commands

Run synth with no arguments to launch the interactive shell:

synth

synth> run agent.py "Hello"
synth> create agent my-bot
synth> doctor
synth> exit

All commands also work directly:

synth init                                  # Interactive project setup wizard
synth create agent my-bot                   # Scaffold an agent project
synth create agent my-bot -p openai         # Skip prompt, use OpenAI
synth create agentcore my-service           # AWS AgentCore project
synth create team my-team                   # Multi-agent team + pipeline
synth create tool my-tools                  # Standalone tools file
synth create mcp my-server                  # MCP server with FastMCP
synth create ui my-ui                       # Local browser testing UI
synth dev my_agent.py                       # Rich terminal UI with hot-reload
synth run my_agent.py "prompt"              # Execute agent, print result
synth bench my_agent.py "prompt" --runs 20  # Benchmark latency/cost
synth eval my_agent.py --dataset cases.json # Run evaluation suite
synth trace <run_id>                        # Open trace in browser
synth deploy --target agentcore             # Deploy to AWS AgentCore
synth deploy --target agentcore --dry-run   # Validate without deploying
synth edit agent agent.py                   # Modify existing agent config
synth doctor                                # Check env, credentials, deps
synth info --extra anthropic                # Show package info
synth help                                  # Quick reference card

synth init

The fastest way to start a new project. Walks you through:

1. Project name and description
2. Provider selection
3. Model selection (region-aware for AgentCore with Bedrock model catalog)
4. Agent instructions
5. Tool Wizard — pick pre-built tools or scaffold custom @tool stubs
6. MCP Wizard — pick pre-built MCP servers or scaffold custom @mcp.tool() stubs
7. Feature toggles (memory, guards, structured output, eval, deploy)
8. Credential check (AgentCore only)
9. Summary and confirmation
10. Project generation
11. Optional "Deploy now?" prompt (AgentCore only)

For AgentCore projects, synth init also:

• Auto-detects AWS credentials (env vars → ~/.aws/credentials → AWS Toolkit profiles)
• Prompts for target AWS region (default: us-east-1)
• Shows Bedrock models available in that region
• Writes aws_region, model_id, cris_enabled, and aws_profile to agentcore.yaml

synth dev

Rich terminal UI for interactive development:

synth dev my_agent.py

Features: streaming token-by-token output, tool call visualization, slash commands (/tools, /reload, /trace, /export, /clear, /cost, /quit), markdown rendering, status bar with live cost/token tracking.

synth deploy

Guided six-stage deployment wizard:

synth deploy --target agentcore my_agent.py
synth deploy --target agentcore --dry-run my_agent.py  # Stages 1–4 only

Stages: credential validation → dependency check → file validation → manifest generation → artifact packaging → AgentCore API submission. Each prints [ OK ] or [FAIL] with a corrective suggestion on failure.

synth edit agent

Interactively modify an existing agent without editing files manually:

synth edit agent agent.py

Menu options: (a) instructions, (b) model, (c) tools, (d) MCP servers. Shows a diff before writing. Uses atomic temp-file rename to prevent corruption.

synth doctor

synth doctor

Checks: Python version, core dependencies, provider API keys, SYNTH_TRACE_ENDPOINT format, optional provider packages, and (when agentcore.yaml is present) AgentCore config fields (aws_region, model_id, cris_enabled, aws_profile).

synth bench

synth bench my_agent.py "Hello" --runs 20 --warmup 2

Reports p50/p95/p99 latency, average tokens, cost per run, and success rate.

---

Deploying to AWS AgentCore

Prerequisites

pip install synth-agent-sdk[agentcore]

Wrapping Your Agent

from synth import Agent
from synth.deploy.agentcore import agentcore_handler

agent = Agent(
    model="bedrock/claude-sonnet-4-5",
    instructions="You are a customer support agent.",
    tools=[lookup_order, check_inventory],
)

app = agentcore_handler(agent)

Deploy

synth deploy --target agentcore --dry-run   # Validate first
synth deploy --target agentcore             # Deploy

The packager automatically excludes .env files, credential files, and .synth/checkpoints/ from the artifact. It also scans agentcore.yaml for accidental credential patterns and aborts if any are found.

Secure User Identity

from synth.deploy.agentcore import extract_user_id

user_id = extract_user_id(context)  # Extracts from signed JWT in RequestContext

Gateway MCP Client

from synth.deploy.agentcore import create_gateway_client

client = create_gateway_client(
    gateway_url="https://my-gateway.example.com",
    client_id_param="/myapp/gateway/client_id",
    client_secret_param="/myapp/gateway/client_secret",
)
mcp_client = client.as_mcp_client()

Code Interpreter

from synth.deploy.agentcore import CodeInterpreterTools

ci = CodeInterpreterTools()
result = ci.execute_python("import math; print(math.sqrt(144))")
print(result)  # "12.0"

SSM Config

from synth.deploy.agentcore import get_ssm_parameter

db_url = get_ssm_parameter("/myapp/prod/db_url")
api_key = get_ssm_parameter("/myapp/prod/api_key", decrypt=True)

---

Error Handling

All Synth errors inherit from SynthError and include component and suggestion fields.

Error	When
SynthConfigError	Missing API key, invalid model, missing provider package
ToolDefinitionError	@tool missing type annotations or docstring
ToolExecutionError	Tool function raised an exception
GuardViolationError	A guard check failed
CostLimitError	Cost guard limit exceeded
SynthParseError	Structured output couldn't be parsed after retries
GraphRoutingError	No edge condition matched at a graph node
GraphLoopError	Graph exceeded max_iterations
RunNotFoundError	No checkpoint found for the given run_id
PipelineError	A pipeline stage failed

from synth.errors import SynthConfigError, ToolExecutionError, GuardViolationError

try:
    result = agent.run("Do something risky.")
except GuardViolationError as e:
    print(f"Guard '{e.guard_name}' blocked: {e.remediation}")
except ToolExecutionError as e:
    print(f"Tool '{e.tool_name}' failed: {e.original_error}")
except SynthConfigError as e:
    print(f"Config issue in {e.component}: {e.suggestion}")

---

Environment Variables

Variable	Purpose	Required?
ANTHROPIC_API_KEY	Anthropic Claude API key	Only for claude-* models
OPENAI_API_KEY	OpenAI GPT API key	Only for gpt-* models
GOOGLE_API_KEY	Google Gemini API key	Only for gemini-* models
AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY	AWS credentials for Bedrock	Only for bedrock/* (or use IAM)
SYNTH_TRACE_ENDPOINT	HTTPS URL of an OTel collector	No
SYNTH_NO_BANNER	Set to 1 to skip the boot sequence	No
NO_COLOR	Disable colored terminal output	No

---

FAQ

Do I need an API key? Yes, for cloud models. Ollama runs locally and needs no key.

Can I use Synth in Jupyter? Yes. Synth detects an existing event loop and handles it automatically.

How do I switch models? Change the model string. Install the matching extra and set the API key.

What if the provider is down? Synth retries on HTTP 429 and 5xx with exponential backoff. Configure with max_retries and retry_backoff.

Can I use multiple models in one app? Yes. Each Agent has its own model.

How do I debug what my agent is doing? Use result.trace.show() for a visual timeline, or synth dev my_agent.py for an interactive terminal UI with /trace command.

Is my data secure? Synth never logs or serializes API keys. Guards run before side-effecting operations. Checkpoints use JSON only. All provider calls use HTTPS.

What are the core dependencies? pydantic, httpx, click, typing-extensions, rich, prompt-toolkit. Provider SDKs are optional extras.

---

License

MIT