agentboards.org
Compare/Arbor vs Contrabass

ArborvsContrabass

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

Arbor
penso · Agent harness
OSSMCP
Panel
7.2
3 spec wins
Reliability
7.0
Usefulness
7.0
Cost
8.7
Longevity
6.0

“It manages your repositories, your worktrees, your terminals and your processes, so the only unmanaged thing left in the room is you.”

Contrabass
junhoyeo · Agent harness
OSSMCP
Panel
7.1
1 spec wins
Reliability
6.8
Usefulness
7.3
Cost
8.2
Longevity
6.0

“Every issue gets a worktree under workspaces/ named after the ticket, so your filesystem is now a faithful copy of your backlog.”

Spec by spec

SpecArborContrabass
Architecture
CategoryAgent harnessAgent harness
Runslocallocal
Platformsmacos, linux, windows, webmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverYesYes
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYesFiles are changed by the agent runner Contrabass launches in each issue's worktree.
Git operationsYesYes
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationYesYes
Headless / CI modeNoYesA --no-tui flag runs the orchestrator headless with events logged to stdout.
Models
BackboneClaude Code, Codex, OpenCodeCodex app-server, OpenCode, oh-my-opencode, OMX, OMC
Bring your own modelYesYes
Local modelsYesOllama appears among the providers Arbor can be pointed at. No
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITApache-2.0
GitHub stars831223

Which one would each critic pick

CriticArborContrabassPick
El Juez——not enough reviews
El Amigo7.57.5no preference
El Crítico6.86.8no preference
El Profesor7.57.5no preference
La Inversora6.86.5Arbor — 809 stars, a personal namespace and a documentation site on GitHub Pages: nothing to fund, nothing to fail, and nobody to answer the phone.
La Jefa6.36.3no preference
El Hacker8.38.0Arbor — MIT, brew install, MCP consumed and served in both directions, and Ollama among the providers, so the model can be the one running on my box.

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.