swebot-client 0.9.8

Python client for the swebot autonomous coding agent

swebot-client

Python client for the swebot autonomous coding agent.

Pure Python — zero dependencies beyond the standard library.

Install

# pip
pip install swebot-client

# uv
uv add swebot-client

Quick start

from swebot_client import SwebotClient

client = SwebotClient("http://localhost:8080")
session = client.create_session()

# Stream tokens
for token in session.stream("explain goroutines"):
    print(token, end="", flush=True)

# Or get the full reply at once
reply = session.send("what is 2+2?")
print(reply)

Features

• Streaming — real-time token-by-token output via SSE
• Tool callbacks — observe tool invocations and results
• Session management — create, resume, list, delete sessions
• Todos — read and update agent todo items
• MCP management — configure MCP servers programmatically
• Context control — compact or clear session context
• Skills — list and use built-in skill agents

Examples

from swebot_client import SwebotClient, Session, ToolCall, TodoItem

client = SwebotClient("http://localhost:8080")

# Wait for backend to be ready
client.wait_until_ready(timeout=10)

# Create a session with a specific agent
session = client.create_session(agent="developer")

# Stream with tool call callbacks
def on_tool(tc: ToolCall):
    print(f"  ⚙ {tc.name}")

reply = session.send_with_events(
    "create a hello.py file",
    on_tool_start=on_tool,
)

# Read todos
for todo in session.get_todos():
    print(f"[{todo.status}] {todo.title}")

# List MCP servers
for mcp in client.list_mcp():
    print(f"{mcp['name']}: {'connected' if mcp.get('connected') else 'disconnected'}")

# Token usage
usage = session.token_usage()
print(f"Tokens: {usage['tokens_in']:,} in / {usage['tokens_out']:,} out ({usage['usage_pct']}%)")

API reference

SwebotClient(addr="http://localhost:8080")

No token needed for local use. If the backend was started with --token, set SWEBOT_TOKEN in your environment — the SDK reads it automatically.

Method	Description
health()	Check if backend is reachable
wait_until_ready(timeout)	Block until backend responds
create_session(agent)	Create a new session → Session
get_session(id)	Resume an existing session → Session
list_sessions()	List all sessions
delete_session(id)	Delete a session
list_agents()	List available agents
list_providers()	List LLM providers
stats()	Backend stats (model, tokens, uptime)
skills()	List built-in skill agents
list_mcp()	List MCP servers
add_mcp(...)	Add an MCP server
delete_mcp(name)	Remove an MCP server
shutdown()	Gracefully stop the backend

Session

Method	Description
stream(message)	Stream tokens → Iterator[str]
send(message)	Send and get full reply → str
send_with_events(message, ...)	Send with tool callbacks → str
get_todos()	List todo items → list[TodoItem]
update_todo(id, status)	Update a todo's status
compact()	Trigger context compaction
clear()	Clear all session context
token_usage()	Get token usage stats

Requirements

• Python 3.9+
• A running swebot backend (swebot --serve)

License

MIT