agentboards.org
Compare/fx vs OpenHarness

fxvsOpenHarness

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

fx
Vercel Labs · Terminal agent
#199OSSMCP
Panel
5.8
1 spec wins
Reliability
5.3
Usefulness
5.7
Cost
7.0
Longevity
5.3

“The whole agent is 7.8 MiB, which is smaller than the loading spinner on some tools it competes with.”

OpenHarness
zhijiewong · Terminal agent
#209OSSMCP
Panel
5.7
3 spec wins
Reliability
5.5
Usefulness
5.8
Cost
7.7
Longevity
3.8

“It has agent roles, so the same model can now let you down under several different job titles.”

Spec by spec

SpecfxOpenHarness
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linuxmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsNoYes
Browser controlNoNo
Sandboxed executionNoNo
Multi-agent orchestrationYesYes
Headless / CI modeNoYes
Models
BackboneVercel AI Gateway models, OpenAI, GrokOllama, OpenAI, any LLM
Bring your own modelYesYes
Local modelsNoYes
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseApache-2.0MIT
GitHub stars3,250102

Which one would each critic pick

CriticfxOpenHarnessPick
El Juez——not enough reviews
El Amigo6.06.0no preference
El Crítico5.35.5OpenHarness — Forty-four tools ship in one agent and the only boundary described is a set of permission modes, with no isolation recorded anywhere in the row.
El Profesor6.36.0fx — Output stays shell-shaped rather than a full-screen interface, and it reads a competitor-compatible tool configuration file, which makes the setup portable between agents.
La Inversora5.84.5fx — A labs project rather than a product, with billing that runs through the parent's inference routing service, so the free binary is the metered path in.
La Jefa4.85.3OpenHarness — Free across sixty desks, and an official Python SDK driving the same binary from pipelines is the part that would let me measure it rather than hear about it.
El Hacker7.07.0no preference

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.