Side by side

SWE-agent vs Twill

Both stand on ai coding assistants. Which one you can start free with, which one lets you read the code, and what each costs once you pay.

SWE-agent

Free plan LinuxMacSelf-hosted+2

SWE-agent offers a configurable research-oriented agent for repository work, vulnerability investigation, and custom tasks across major desktop systems. Its maintenance-only status and successor recommendation make mini-swe-agent the direction maintainers currently favor.

Visit SWE-agent

Twill

Free plan AndroidAPIiPhone+5

Twill focuses on moving coding work across agents, machines, and team tools while preserving task context. Its plans distinguish local usage from metered cloud credits, with enterprise deployment and governance options listed.

Visit Twill

The facts

	SWE-agent	Twill
Free plan	Yes	Yes
Open source	Not published	Not published
Runs on	Linux, Mac, Self-hosted, Web, Windows	Android, API, iPhone, Linux, Mac, Self-hosted, Web, Windows
Lowest paid plan	Not published	See the plans
Plans published	None	4
Maker	Not published	Not published
Website	swe-agent.com	twill.ai
On ai coding assistants	#41 of 102	#37 of 102

SWE-agent: what it does well

Open-source and free to use
Autonomous repository browsing, editing, and code execution
Configurable through a documented YAML file
Supports LiteLLM and local models
Runs on Linux, macOS, and Windows

What to know first

Now in maintenance-only mode
Maintainers recommend mini-swe-agent instead
Requires model credentials and sometimes GitHub credentials
Docker may limit environment choices

Twill: what it does well

Moves tasks between local and cloud agents
Keeps branches and conversations during handoff
Runs isolated task environments
Supports scheduled chores and templates
Local runs use no credits

What to know first

Free plan includes 5 monthly credits
Pro costs 50.00 USD monthly
Max costs 200.00 USD monthly
Cloud credits reset monthly

Alternatives to SWE-agent Alternatives to Twill The whole list