agentboards.org
Compare/graff vs SolonCode

graffvsSolonCode

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

graff
justrach · Terminal agent
#189OSSMCP
Panel
6.0
0 spec wins
Reliability
5.5
Usefulness
5.8
Cost
8.0
Longevity
4.7

“The desktop app talks straight to the ObjC runtime rather than ship Electron, which is a grudge with a build system.”

SolonCode
OpenSolon · Terminal agent
#77OSSMCP
Panel
6.0
2 spec wins
Reliability
5.5
Usefulness
5.8
Cost
7.0
Longevity
5.8

“The command line ships pointed at a cheap default model, which is the most realistic assumption any of these tools has made about its users.”

Spec by spec

SpecgraffSolonCode
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linux, windowsmacos, linux, windows, web
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsNoYesThe desktop workspace shows Git changes alongside the editor and terminal.
Browser controlYesThe desktop app has an experimental browser pane with an Annotate mode for pinning page elements into the conversation. Yessoloncode web serves the agent UI over HTTP; the README does not describe a browser-driving tool.
Sandboxed executionNoNo
Multi-agent orchestrationYesThe desktop app runs several chat tabs, each backed by its own graff acp process. YesAgents are one of the extensible runtime types and are addressed with @ in the CLI; the README's own worked example asks it to design an agent team.
Headless / CI modeNoNo
Models
Backboneexisting AI subscriptionsdeepseek-v4-flash, any configured provider
Bring your own modelYesYes
Local modelsNoYesModel providers are configured freely on the Settings page, so a local endpoint works.
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseNOASSERTIONMIT
GitHub stars279n/a

Which one would each critic pick

CriticgraffSolonCodePick
El Juez——not enough reviews
El Amigo6.56.5no preference
El Crítico6.05.0graff — The sign-in promise rests on subscriptions the documentation never enumerates, so nobody can tell before installing whether the plan they already pay for is one of them.
El Profesor6.86.0graff — Annotate mode pins a page element into the next message with its role, accessible name and selector, which is a structured reference rather than a screenshot.
La Inversora5.36.0SolonCode — A framework team shipping an agent, published on a domestic code host first with a mirror abroad, and released in February 2026 with no adoption recorded yet.
La Jefa5.35.3no preference
El Hacker6.37.5SolonCode — MIT, and it speaks the tool protocol, OpenAPI, the language server protocol and the agent protocol, with a settings page that takes a local endpoint.

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.