swebot-client 0.11.0

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
• Mode / model control — switch modes, models, thinking, reasoning
• Todos & checkpoints — read, create, update, delete todos; list/restore checkpoints
• MCP management — configure MCP servers programmatically
• Plugin management — install, remove, enable, disable plugins
• AgentSpeak — multi-agent collaboration (join, leave, send messages)
• Context control — compact or clear session context
• Skills — list built-in skill agents

Examples

from swebot_client import SwebotClient, ToolCall

client = SwebotClient("http://localhost:8080")
client.wait_until_ready(timeout=10)

# Set mode to autonomous so the agent executes (not plans)
client.set_mode("autonomous")

# Enable extended thinking
client.set_thinking("high")

# Switch model
client.set_model("claude-opus-4-5")

# Create a session and send a message
session = client.create_session(agent="developer")

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}")

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

Pipeline example

from swebot_client import SwebotClient

client = SwebotClient()
client.wait_until_ready()
client.set_mode("autonomous")

# Stage 1: generate
s1 = client.create_session()
code = s1.send("Write a Python prime sieve for 0-1000000")

# Stage 2: review
s2 = client.create_session("code_auditor")
review = s2.send(f"Review this code:\n{code}")
print(review)

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.

Sessions

Method	Description
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

Agents / Providers / Models

Method	Description
list_agents()	List available agents
get_agent(name)	Get agent details (name, system_prompt, tools)
list_providers()	List LLM providers
list_models(provider)	List models for a provider → {provider, active, models}
set_model(model, provider)	Switch model (and optionally provider)

Mode / Thinking / Reasoning

Method	Description
get_mode()	Current mode (plan, agent, autonomous)
set_mode(mode)	Set mode: "plan", "agent", "autonomous"
get_thinking()	Current thinking level
set_thinking(level)	Set thinking: "", "low", "medium", "high"
get_reasoning()	Current reasoning depth
set_reasoning(level)	Set reasoning: "low", "medium", "high"

MCP Servers

Method	Description
list_mcp()	List MCP servers with connection state
add_mcp(name, ...)	Add a new MCP server
update_mcp(name, ...)	Update an existing server
delete_mcp(name)	Remove a server
enable_mcp(name)	Enable a disabled server
disable_mcp(name)	Disable without removing
reload_mcp()	Reconnect all enabled servers

Plugins

Method	Description
list_plugins()	List installed plugins
install_plugin(url)	Install from GitHub (owner/repo)
remove_plugin(name)	Uninstall a plugin
enable_plugin(name)	Re-enable a disabled plugin
disable_plugin(name)	Disable without removing

AgentSpeak (Multi-Agent)

Method	Description
agentspeak_status()	Connection status → {connected, project, role, url}
agentspeak_projects()	List visible projects
agentspeak_who()	List agents in current project
agentspeak_messages(since)	Fetch recent messages
agentspeak_join(url, project, role)	Connect and join a project
agentspeak_leave()	Disconnect from project
agentspeak_send(message, to)	Send message (broadcast or targeted)

Backend Management

Method	Description
health()	Check if backend is reachable
wait_until_ready(timeout)	Block until backend responds
stats()	Backend stats (model, tokens, uptime)
version()	Version info (version, commit, latest)
skills()	List built-in skill agents
panic()	Emergency stop — cancel all, reset to plan mode
shutdown()	Gracefully stop the backend

Session

Messaging

Method	Description
stream(message)	Stream tokens → Iterator[str]
send(message)	Send and get full reply → str
send_with_events(msg, on_token, on_tool_start, on_tool_result)	Send with callbacks → str

Todos

Method	Description
get_todos()	List todo items → list[TodoItem]
create_todo(title)	Create a new todo
update_todo(id, status)	Update status: pending, in_progress, done
delete_todo(id)	Delete a todo

Checkpoints

Method	Description
list_checkpoints()	List file checkpoints → list[dict]
restore_checkpoint(id)	Restore a file to a previous checkpoint

Context

Method	Description
compact()	Trigger context compaction
clear()	Clear all session context
token_usage()	Token usage stats → {tokens_in, tokens_out, context_window, usage_pct}

Info

Method	Description
refresh()	Reload session data from backend
message_count	Number of messages (property)

Publishing to PyPI

cd sdk/python
python3 -m build
UV_PUBLISH_TOKEN=pypi-YOUR-TOKEN uv publish dist/*

Requirements

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

License

MIT