agentboards.org
Compare/Fractal vs Kota

FractalvsKota

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

Fractal
Trampoline AI · Terminal agent
#224OSS
Panel
4.6
3 spec wins
Reliability
3.7
Usefulness
4.2
Cost
6.0
Longevity
4.7

“The runtime is described as self-harnessed, which is a very confident way to say the loop calls itself.”

Kota
StepfenShawn · Terminal agent
#252OSS
Panel
4.8
0 spec wins
Reliability
4.3
Usefulness
4.0
Cost
6.8
Longevity
4.0

“Built on the philosophy of vim, which means the configuration is infinite and the exit is somebody else's problem.”

Spec by spec

SpecFractalKota
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacosmacos, linux
Context windownot documentednot documented
Protocols
MCP clientNoNo
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsNoNo
Browser controlNoNo
Sandboxed executionYesNo
Multi-agent orchestrationYesNo
Headless / CI modeNoNo
Models
Backbonepredict-rlmmultiple providers
Bring your own modelYesYes
Local modelsNoNo
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITMIT
GitHub stars200100

Which one would each critic pick

CriticFractalKotaPick
El Juez——not enough reviews
El Amigo4.55.3Kota — Pick it if you enjoy assembling your own tools; pick something with batteries if you want to type a request tonight and get a change back.
El Crítico4.34.8Kota — It edits across files and has no version control operations of its own, so an unwanted change has no undo path the tool can offer you.
El Profesor5.34.5Fractal — The agent is structured as a recursive language model rather than a flat loop, so decomposition is the control flow instead of a prompt convention.
La Inversora4.83.8Fractal — 200 stars and seventy-three public mentions in a year, from a named company, which is more attention than most projects here and more than the software has earned.
La Jefa3.54.3Kota — The one thing here my team could use is embedding it inside our own service, and there is no console, no single sign-on and nothing that runs unattended.
El Hacker5.56.3Kota — MIT, and the configuration is Lua with custom commands of my own, which is the difference between a settings file and a programmable tool.

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.