Skip to content
FrontierHarness Eval

Free alternatives to FrontierHarness Eval

200 free apps like FrontierHarness Eval, closest match first.

More like FrontierHarness Eval

101
C

Claw Orchestrator

Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime

Launch
102
L

Lacp

Local-first policy, evidence, memory, and recovery controls for Claude, Codex

Launch
103
D

Devchain

Run a team of AI coding agents

Launch
104
P

Parallel Code

Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

Launch
105
D

diffay

Multi-agent AI code review

Launch
106
N

Netclode

Self hosted cloud coding agent with k3s + kata containers + cloud hypervisor…

Launch
107
S

Shep

Ship features 10x faster

Launch
108
A

Agentlytics

Comprehensive analytics dashboard for AI coding agents

Launch
109
C

Codex Infinity

The infinite coding agent platform

Launch
110
P

Pilot Harness

A CodePilot-inspired desktop client and plugin suite

Launch
111
A

agentty

AI pair programming in your terminal

Launch
112
S

SQZ

Context compression for AI coding agents: compresses tool output before it…

Launch
113
A

Amux

Open-source control plane for AI coding agents

Launch
114
M

Munder Difflin

an open-source alternative to the dots, bots and muses of the world

Launch
115
A

Abralo

Run several coding agents in one window (Claude Code and Codex)

Launch
116
E

EvoTrace

Compile real-world Claude Code and Codex trajectories into verified

Launch
117
R

repo-harness

File-backed workflow harness for reliable Claude Code and Codex sessions

Launch
118
R

Re Gent

Version control for AI agents — track what your agent did, blame any line to…

Launch
119
S

sudocode

Context management system for AI coding agents

Launch
120
A

AI Agent Camp

Non-engineer-friendly AI agent training curriculum

Launch
121
C

CoreCoder

Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code

Launch
122
L

Linkcode

Open-source alternative to Codex App / Workbuddy, supporting Codex, Claude Code

Launch
123
K

Kitaru

Agent traces you can run, not just read

Launch
124
M

MartinLoop

Open-source control plane for AI coding agents

Launch
125
A

Alphacode

Free MIT AI coding agent — no API key needed

Launch
126
G

google-agents-cli-eval

Evaluate ADK agents with metrics, evalsets, and the iterative eval-fix loop

Get
127
H

Hax

A minimalist, terminal-native coding agent written in C

Launch
128
O

OpenAgentCore

Open-source, self-hosted implementation of the OpenAI Agents API

Launch
129
B

basemind

Full AI context and content layer for coding agents over one MCP server

Launch
130
O

Operator Oss

Run many Claude Code (or Codex) sessions in parallel

Launch
131
C

Crew44

Orchestrate a crew of specialist AI agents in one local-first workspace

Launch
132
A

anthropic-essentials

Feature development with code-architect/explorer/reviewer agents

Get
133
R

ReevesAgents

The best local workspace for running AI coding agents side by side

Launch
134
S

Spectra App

Spec-driven development for coding agents

Launch
135
O

open-code-review-delegate

Delegation mode for open-code-review (OCR)

Get
136
K

Kangentic

An agentic development environment for AI coding agents

Launch
137
O

Ordewell

Multi-agent task orchestration for coding agents

Launch
138
P

phoenix-evals

Build and run evaluators for AI/LLM applications using Phoenix

Get
139
C

Codeg

Collaborative multi-agent AI coding workspace: aggregate sessions

Launch
140
M

Moyai

A self-hosted coding agent for background work

Launch
141
L

Localforge

Local coding agent with neat UI

Launch
142
A

AgentBox

Run multiple agents in parallel sandboxed VMs

Launch
143
E

explore-code

Rigor Improve implementation leaf skill

Get
144
C

Claude Harness

Deconstructing Claude Code — interactive source code analysis, guided…

Launch
145
O

Octomind

Open-source AI coding agent and agent runtime: one binary, any model, MCP-native

Launch
146
F

Friday Studio

Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and…

Launch
147
B

Bitloops

Give AI coding agents the context they need to ship production-quality software

Launch
148
P

pydantic-ai-harness

Extend Pydantic AI agents

Get
149
R

review-all

Run a two-agent code review: spawn two fresh, clean-context agents

Get
150
A

Agenttrace

Local-first TUI for inspecting AI coding agent sessions, costs, tokens, latency

Launch