agentboards.org
Compare/Blades vs WayFlow

BladesvsWayFlow

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

Blades
go-kratos · Agent framework
OSS
Panel
6.3
1 spec wins
Reliability
6.5
Usefulness
5.0
Cost
7.5
Longevity
6.2

“Named after the weapons Kratos carries in God of War, which is a lot of commitment for a package you import.”

WayFlow
Oracle · Agent framework
OSS
Panel
6.3
2 spec wins
Reliability
6.5
Usefulness
5.2
Cost
7.0
Longevity
6.5

“It builds assistants that cannot run a command, edit a file or touch a repository, so the assisting remains firmly your responsibility.”

Spec by spec

SpecBladesWayFlow
Architecture
CategoryAgent frameworkAgent framework
Runslocallocal
Platformsmacos, linux, windowsmacos, linux
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsNoNo
Multi-file editsNoNo
Git operationsNoNo
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationNoYes
Headless / CI modeNoNo
Models
BackboneOpenAI, Gemini, DeepSeekOCI Generative AI, OpenAI, Ollama
Bring your own modelYesThe ModelProvider abstraction is documented as supporting custom models. Yes
Local modelsNoYes
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITApache-2.0
GitHub stars817189

Which one would each critic pick

CriticBladesWayFlowPick
El Juez——not enough reviews
El Amigo6.36.0Blades — Pick Blades if your service is already a go-kratos application; pick a Python framework if you want the ecosystem rather than the language.
El Crítico5.55.5no preference
El Profesor6.86.8no preference
La Inversora6.36.3no preference
La Jefa5.86.8WayFlow — For once there is a supplier with a legal department behind the code, and it is still a library with no console, no seat count and nothing to administer.
El Hacker7.36.5Blades — MIT, one go get, and a documented provider abstraction that takes custom models, so pointing it at whatever endpoint I am running is an interface implementation.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.