agentboards.org
Compare/BitFun vs Xum

BitFunvsXum

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

BitFun
GCWing · Agent harness
OSSMCP
Panel
6.8
3 spec wins
Reliability
6.2
Usefulness
7.2
Cost
8.0
Longevity
5.7

“Customising it has four tiers, which is three more tiers than most people reach before they go back to the defaults.”

Xum
Coder · Agent harness
OSS
Panel
6.8
1 spec wins
Reliability
6.3
Usefulness
6.3
Cost
8.3
Longevity
6.2

“It renders mermaid diagrams and LaTeX in your terminal, so the agent can now hand you an architecture you did not ask for, beautifully.”

Spec by spec

SpecBitFunXum
Architecture
CategoryAgent harnessAgent harness
Runslocallocal
Platformsmacos, linux, windowsmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesYes
Browser controlYesNo
Sandboxed executionNoNo
Multi-agent orchestrationYesCustom agents are the first of BitFun's four customisation tiers. Yes
Headless / CI modeNoNo
Models
BackboneanyAnthropic, OpenAI, Grok, Ollama, OpenRouter
Bring your own modelYesBitFun is described as model-agnostic: you pick a provider, enter its API key and choose models at first run. Yes
Local modelsNoYes
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITAGPL-3.0
GitHub stars2,3702,045

Which one would each critic pick

CriticBitFunXumPick
El Juez——not enough reviews
El Amigo7.37.3no preference
El Crítico6.56.3BitFun — It drives the browser, the terminal, desktop applications, the filesystem and remote workspaces, and the row records no sandbox around any of it.
El Profesor6.86.8no preference
La Inversora6.56.5no preference
La Jefa6.06.3Xum — Free for sixty engineers, and the copyleft licence means my counsel reads it before anyone embeds it, while the remote workspaces fit the development servers we already run.
El Hacker7.57.8Xum — AGPL-3.0, a prebuilt binary with no runtime to install, and Ollama sits beside the hosted providers in the model config, so local inference is a config value.

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.