Skip to content
FrontierHarness Eval

Free alternatives to FrontierHarness Eval

200 free apps like FrontierHarness Eval, closest match first.

Top picks

  1. E

    eval-harness

    Get

    eval-harness is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It is a formal evaluation framework for Claude Code sessions based on eval-driven development, where evals are treated as the unit tests of AI-assisted

    Free

  2. A

    agent-eval

    Get

    agent-eval is an agent skill from ECC, Affaan Mustafa's open-source agentic engineering toolkit, listed on skills.sh. It compares coding agents such as Claude Code, Aider and Codex head to head on reproducible tasks defined in YAML, so choo

    Free

  3. H

    harness-creator

    Get

    Harness creator is an agent skill for building, auditing and improving the setup that keeps AI coding agents reliable in a repository. A harness is the set of files that tells an agent how to start, what it may change, how to check its work

    Free

  4. C

    Claude Code Workflow

    Launch

    QuietHarness is a small set of working rules for AI coding agents such as Claude Code, Codex and Cursor. Its shared core asks the agent to check existing changes before it edits, keep unrelated changes intact, verify with real tests before

    FreeOpen source

  5. A

    agent-eval

    Get

    agent-eval is a benchmark skill for CodeGraph, the code intelligence tool. It measures how much CodeGraph helps an agent compared with plain grep and file reading, for a chosen CodeGraph version on a chosen real-world repository. It runs th

    Free

  6. E

    eval-harness-first

    Get

    eval-harness-first is an agent skill from the wshobson/agents collection for building the evaluation harness that gates a fine-tuning run. It is the first phase of a fine-tuning workflow: the other skills in that sequence assume the harness

    Free

More like FrontierHarness Eval

7
S

SDD Riper

Lightweight AI Agent Harness for agentic coding: let strong models explore…

Launch
8
A

AgenTopology

Harness as code — the Terraform for AI agents

Launch
9
A

Agentacct

See what your coding agents did and what it cost

Launch
10
T

ThinHarness

Build focused AI agents without framework sprawl

Launch
11
C

Claudexor

Multi-harness control plane for Claude Code, Codex, Cursor

Launch
12
A

ASSERT

Requirement-driven evaluation harness for AI agents and LLM applications

Launch
13
G

gan-style-harness

GAN-inspired Generator-Evaluator agent harness

Get
14
H

HarnessRouter

HarnessRouter Community Edition: the self-hosted

Launch
15
A

agent-evaluation

Evaluate and improve Claude Code commands, skills, and agents

Get
16
C

Cost Xray

See what Claude Code and Codex actually send to the API

Launch
17
E

Evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

Launch
18
H

Harnss

Open-source, desktop client/UI build to harness Claude Code

Launch
19
N

nanostack

A workflow harness that helps AI coding agents plan, review, test

Launch
20
W

Web

An open-source coding agent built for low-cost and open-weight models

Launch
21
P

Paseo

Self-hosted orchestrator for coding agents like Claude Code, Codex, and Cursor

Launch
22
L

LazyCodex

The one and only agent harness for complex codebases

Launch
23
O

Omnigent

Meta-harness that sits above Claude Code, Codex

Launch
24
O

ORG-2

System of record for how agents build software: Built-in rust harness & 20+ CLIs

Launch
25
K

Keesan12/martin-loop

Governed runtime for AI coding agents

Get
26
K

KARIMO

Claude Code harness engineering plugin — plan mode on steroids

Launch
27
A

Agtop

top-style TUI for monitoring AI coding agent sessions

Launch
28
H

Harness Score

Your AI coding agent is only as reliable as the harness around it

Launch
29
A

Archon

The first open-source harness builder for AI coding

Launch
30
H

Harness Books

Harness engineering in two books: constraints, query loops

Launch
31
P

Pi Harness

The operational superset of Pi Coding Agent

Launch
32
D

deepeval

DeepEval evaluation workflow for AI agents and LLM applications

Get
33
C

CodeBurn

Free, local tool to track AI coding token usage and cost across 37 tools

Launch
34
A

Agentglass

Every AI coding agent on your machine, on one screen

Launch
35
D

debug-my-harness

Diagnose why an agent harness misbehaved

Get
36
L

Litefuse

Agent Observability and Evaluation Platform

Launch
37
P

Paritok 4b V1

Non-destructive compression gateway for AI coding agents

Launch
38
B

Bromure

Proper sandboxing for agentic coding and web browsing

Launch
39
C

Codeman

Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi

Get
40
L

Little Coder

A harness optimized to smaller LLMs

Launch
41
E

eval-driven-dev

Improve AI application with evaluation-driven development

Get
42
H

HarnessKit

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs…

Launch
43
C

claude-devfleet

Orchestrate multi-agent coding tasks via Claude DevFleet

Get
44
C

CTX

CTX Fit finds the cheapest AI coding setup

Launch
45
C

cocode

Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI

Launch
46
S

sandbox-agent

Deploy, configure, and integrate Sandbox Agent

Get
47
E

eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session

Get
48
M

Meta_Kim

Governed execution layer for AI coding assistants: clarify intent

Launch
49
T

Trail-code

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster

Launch
50
C

Claudetop

htop for your Claude Code sessions — real-time cost, cache efficiency, model…

Launch

About FrontierHarness Eval

F

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