200 free apps like FrontierHarness Eval, closest match first.
model-usage
Summarize CodexBar local cost logs by model for Codex or Claude
Codexmate
One dashboard for all your local AI coding agents
AGHub
One hub for every AI coding agent
BOSS Console
Open-source, multi-platform harness for AI agents
Benchmark Heaven
Model benchmarks & costs
agentic-eval
Iterative evaluation and refinement patterns
Abtop
Like htop, but for AI coding agents
test-harness
Install vigiles and test a Claude Code harness
Opentraces
A local-first evidence layer for agent work, capturing what the agent sees
dev-3.0
Mission control for the One Person Studio
coding-agent
Delegate coding work to Codex, Claude Code, or OpenCode as background workers
cli-anything
Codex to build, refine, test, validate
huggingface-community-evals
Run evaluations for Hugging Face Hub models
dynamic-workflow-mode
Design task-local harnesses, eval gates
Superloopy
Lightweight Codex/Claude loop harness with strict evidence gates
Bettercode
Every coding agent in one desktop workspace
Agentsmith
Universal, model-agnostic operating harness for AI agents
hapi
Run and remotely control Claude Code, Codex and Cursor Agent
zeroshot
Enforced QA for Claude Code, Codex and Copilot
qwen-agent
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent
EnsoCode
One Developer. An Entire Fleet of Autonomous Coding Agents
ai-evals
Help users build robust infrastructure for measuring, monitoring
ADHDev
🦦 ADHDev — Agent Dashboard Hub
10x
Up to 20x faster AI coding with multi-step Superpowers
Agentsview
Local-first session search, analytics, insights
Agent Launcher
Configure and run existing coding-agent CLIs from one desktop app
Honey For Devs
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill
Stoneforge
Open-source orchestration for AI coding agents
Happier
Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode
Codeburn
by iamtoruk - Breakdown of local spend down by project, model
Codehamr
A minimal, local-first coding agent for the terminal
Tempest
Agentic Engineering that actually scales
AI Observer
Unified local observability for AI coding assistants
Harness Remote
Native-session control plane for Codex, Claude Code, OpenCode, OMP and PI
Bito AI
Bito speeds up code reviews with AI analysis
DeepSeek-Reasonix
A reliable coding agent for complex software engineering tasks
Cezar
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode
Agenttrail
Local observability for AI coding agents
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud
delegate-skills
Delegates coding work to separate agent CLIs and reviews their diffs
Codirigent
A Rust based terminal workspace for multiple AI coding CLIs in parallel
agent-pulse
Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code
Loongsuite Pilot
Local-first telemetry collector for AI coding agents
ce-agent-native-audit
Run comprehensive agent-native architecture review with scored principles
lazyagent
Monitor all your coding agents from one terminal
Agent Teams AI
Open-source desktop app
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability
Helix
Private Agent Fleet with Spec Coding
ClawMetry
See your agent think
Pentest Harness
Heaven for Hackers