Self-hosted alternatives to FrontierHarness Eval
200 self-hosted apps like FrontierHarness Eval, closest match first.
Top picks
- H

HarnessRouter
LaunchHarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure
FreeOpen sourceSelf-hosted
- O
ORG-2
LaunchOpen-source workspace that runs 20+ AI coding agents and records every session as a replayable trajectory. Replay any session, review as a team, and trace every line back to the decision behind it.
FreeOpen sourceSelf-hosted
- A

ADHDev
LaunchThe control plane for your coding agents. See every Claude Code, Codex CLI, Kimi, Cursor CLI, Antigravity CLI, Grok and OpenCode session on every machine, hand them one shared task queue across Mac, Windows and Linux, and merge only the wor
FreeOpen sourceSelf-hosted
- 1
10x
Launch⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.
FreeOpen sourceSelf-hosted
- H

Happier
LaunchHappier is an open-source web, desktop and mobile client for running AI coding agents such as Claude Code, Codex and OpenCode, along with others including Pi, Cursor, Grok, Kimi, Qwen and Gemini. You install it on the computer where your co
FreeOpen sourceSelf-hosted
- C
Cezar
LaunchOpen-source orchestrator that runs Claude Code, Codex, OpenCode and other coding agents in parallel, on your laptop or 24/7 on your own server, using the subscriptions you already pay for. No API keys.
FreeOpen sourceSelf-hosted
More like FrontierHarness Eval
Friday Studio
Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and…
About FrontierHarness Eval

FrontierHarness Eval
9 harness, same model, cost per pass varies 17x
FrontierHarness Eval is a public benchmark that compares AI coding agent harnesses while keeping the model fixed. It tested 9 harnesses in 12 configurations, among them Codex, Claude Code, Pi, Oh My Pi, Kimi Code, OpenCode, Hermes, Exo Harness and several DSH variants, on the same software engineering tasks. Every run used the Kimi K3 model on Runta, starting from an identical fresh checkpoint with the same CPU, memory and disk, for 360 trials in all. Results are shown for pass rate, median cost per task and per successful task, cache hit rate and time. The headline finding is that pass rates were close, roughly 50 to 67 percent, while cost per success differed by about 17 times. The evaluation code and a skill for testing your own harness are on GitHub.
- Price
- Free trial
- Category
- Developer Tools
- Website
- frontierharness.org