Skip to content
agentboards
Browse sections All boards
Compare/Codewhale vs OpenHarness

CodewhalevsOpenHarness

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

Codewhale
Hmbown · Terminal agent
#183OSSMCP
Panel
5.8
2 spec wins
Reliability
5.5
Usefulness
5.5
Cost
7.3
Longevity
4.7

“Installs on Android through Termux, so you can run a coding agent on the phone you use to ignore your coding agent.”

OpenHarness
zhijiewong · Terminal agent
#210OSSMCP
Panel
5.7
0 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

SpecCodewhaleOpenHarness
Architecture
CategoryTerminal agentTerminal agent
Runslocallocal
Platformsmacos, linux, windowsmacos, linux
Context windownot documentednot documented
Protocols
MCP clientYesYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesYes
Browser controlNoNo
Sandboxed executionYesNo
Multi-agent orchestrationYesYes
Headless / CI modeYesYes
Models
Backbonehosted providers, Ollama, vLLM, SGLangOllama, OpenAI, any LLM
Bring your own modelYesYes
Local modelsYesYes
Cost
Pricing modelbyokbyok
Starts at$0/mo$0/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITMIT
GitHub stars41,179100

Which one would each critic pick

CriticCodewhaleOpenHarnessPick
El Juez——not enough reviews
El Amigo6.56.0Codewhale — Pick Codewhale if you want a Rust terminal agent that runs on Ollama with a Plan mode that only reads; pick OpenCode if you want more providers and a bigger community.
El Crítico5.55.5no preference
El Profesor5.86.0OpenHarness — The project ships its own evaluation suite, which is more than most of this board attempts, and publishes no results from running it.
La Inversora3.84.5OpenHarness — Ninety-six stars, fourteen weekly package installs and six on the Python side: the audience for this is smaller than the feature list implies by two orders of magnitude.
La Jefa5.55.3Codewhale — A single-maintainer terminal agent with shell completions and a non-interactive mode, no SSO, no admin and no vendor; approved with conditions for engineers who already hold keys.
El Hacker7.57.0Codewhale — MIT Rust, Ollama, vLLM and SGLang for local models, a config.example.toml to copy, MCP servers attachable, and builds from Cargo, Nix, Docker or Scoop; it runs offline.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Turn this comparison into a practical check

Give Codewhale and OpenHarness the same small task. Keep a personal record of the tests, time and actual cost, then return to it from the homepage.

Open a test workspace for these agents →
Loading agent listings… Models and guides are ready.
↑↓ navigate · Enter open · Esc closeModels & guides