agentboards.org
Compare/Claude Code Haha vs Magi

Claude Code HahavsMagi

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

Claude Code Haha
NanmiCoder · Agent harness
OSSMCP
Panel
5.9
4 spec wins
Reliability
4.8
Usefulness
6.5
Cost
7.5
Longevity
4.7

“Ships four desktop pets that react to the task at hand, off by default, which is the only responsible way to ship a pet.”

Magi
MistRipple · Agent harness
OSSMCP
Panel
5.9
0 spec wins
Reliability
6.0
Usefulness
6.0
Cost
6.3
Longevity
5.3

“Its tool list includes image generation, because the thing your failing test suite needed was an illustration.”

Spec by spec

SpecClaude Code HahaMagi
Architecture
CategoryAgent harnessAgent harness
Runslocallocal
Platformsmacos, linux, windowsmacos, linux, windows, web
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesNo
Browser controlYesNo
Sandboxed executionNoNo
Multi-agent orchestrationYesYesRole agents for execution, exploration, architecture, testing and review run in parallel under a mainline agent, each with its own model.
Headless / CI modeNoNo
Models
BackboneanyOpenAI, Anthropic
Bring your own modelYesYes
Local modelsYesNo
Cost
Pricing modelbyokbyok
Starts atn/a$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITApache-2.0
GitHub stars14,816216

Which one would each critic pick

CriticClaude Code HahaMagiPick
El Juez——not enough reviews
El Amigo6.55.8Claude Code Haha — Pick Claude Code Haha if you want branches, worktrees and turn-by-turn diffs in a window; pick Claude Code in the terminal if a wrapper is one layer too many.
El Crítico5.55.0Claude Code Haha — One person's spare-time project ships a skill marketplace, computer control, five chat-app relays and desktop pets, and each of those is a surface somebody has to keep safe.
El Profesor6.37.0Magi — One run trace records the goal, the derived tasks, every tool call, the resulting changes and the verification results, which makes a completed run auditable end to end.
La Inversora5.35.5Magi — 215 stars, a permissive licence, no company, and an install path that begins with building the desktop package from source. Nothing here is trying to be sold yet.
La Jefa4.55.0Magi — Free at sixty desks and governed nowhere: the permission layer it advertises is local to each installation, with its whole state living in a directory under each home folder.
El Hacker7.37.3no 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.