agentboards.org
Compare/Mercury vs OpenFox

MercuryvsOpenFox

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

Mercury
CosmicStack Labs · Terminal agent
#157OSS
Panel
5.9
3 spec wins
Reliability
5.2
Usefulness
5.8
Cost
6.7
Longevity
6.0

“Executes shell commands and file operations without a sandbox, relying on user approval and a command blocklist for safety.”

OpenFox
co-l · Terminal agent
#208OSS
Panel
6.0
1 spec wins
Reliability
5.7
Usefulness
5.8
Cost
7.5
Longevity
4.8

“It describes your images for you because the local model cannot see them, which is the most polite workaround on this board.”

Spec by spec

SpecMercuryOpenFox
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linux, windows, webmacos, linux, windows, web
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlYesNo
Sandboxed executionNoNo
Multi-agent orchestrationYesYesWorkflows can dispatch sub-agents as isolated steps within a pipeline.
Headless / CI modeNoNo
Models
BackbonevLLM, SGLang, Ollama, llama.cpp, any OpenAI-compatible local backend
Bring your own modelYesYes
Local modelsNoYes
Cost
Pricing modelfreefree
Starts atn/a$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITunspecified
GitHub stars3,169339

Which one would each critic pick

CriticMercuryOpenFoxPick
El Juez——not enough reviews
El Amigo7.86.5Mercury — Mercury is a solid choice for a persistent, multi-channel agent if you value safety and control over autonomous execution.
El Crítico6.35.8Mercury — It runs commands on your host without a sandbox. Use the approval flow and do not walk away.
El Profesor5.36.3OpenFox — Language-server diagnostics are consumed during generation, which supplies a verification signal that is independent of the model rather than another opinion from it.
La Inversora5.55.5no preference
La Jefa4.34.8OpenFox — Free at sixty seats, but the real bill is the inference hardware, and every machine needs Node 24 or newer before anyone can start.
El Hacker6.57.0OpenFox — It detects vLLM, SGLang, Ollama or llama.cpp and configures itself, and provider plugins add transports without touching the core, but the repository carries no licence file.

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.