200 apps like Opik, closest match first.
Overmind
The platform for continuously improving AI agents
VibeCheck AI
Scan. Fix. Ship. The automated checklist
Kelet
Find and Fix AI Agent & LLM App Failures
agent-inspect
Local evidence debugger and trajectory-test toolkit
Obot AI
Complete AI Governance Platform from Obot AI
Opali.xyz
Most affordable privacy-friendly analytics tool for SMEs
DeepEval
LLM 界的 Pytest。将评测集成到 CI/CD 流程中,支持 50+ 指标
eval-audit
Audit an LLM eval pipeline and surface problems: missing error analysis
potpie-ai/potpie
Open Source AI Agents for your codebase in minutes
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud
Octomind
Open-source AI coding agent and agent runtime: one binary, any model, MCP-native
Braintrust
The active observability platform for agents
Bitloops
Give AI coding agents the context they need to ship production-quality software
observability-llm-obs
Answer questions about LLM and agentic-application behavior
Phoenix
Arize Phoenix: Open Source AI Development Platform
Adrian
Open-source runtime AI agent security tool
hidai25/eval-view
Regression testing for AI agents: save golden baselines
ITOps Agent Platform
China's 1st enterprise multi-agent IT ops platform
datadog-labs/dd-llmo-eval-bootstrap
Analyze production LLM traces and generate evaluators
KitOps
Simple, secure, and reproducible packaging for AI/ML projects
Aim
An easy-to-use & supercharged open-source experiment tracker
Infere
Platform for LLM observability, evaluators and git-like prompt management
google-agents-cli-observability
Set up tracing, logging, and monitoring
agentkitai/agentlens
Tamper-evident AI agent observability: hash-chained audit log
Verax
Verax provides visibility and control for your LLMs in production
Open WebUI
Run AI on your own terms
Opengeni
Open, self-hostable agentic service for organizations
Otari
Open-source, OpenAI-compatible LLM gateway you run yourself
ObsidianArc
A self-hosted AI platform with a Go server, multi-provider routing, usage…
Prompttools
Open-source tools for prompt testing and experimentation
Unofficial OpenAI Status
View OpenAI's current status and historical performance
phoenix-evals
Build and run evaluators for AI/LLM applications using Phoenix
Signoz
Application monitoring and observability platform
GoModel
AI gateway written in Go with a unified OpenAI-compatible API
oncell
Agents that get better in production
Agtop
top-style TUI for monitoring AI coding agent sessions
Agentsview
Local-first session search, analytics, insights
Dify
Open-source LLM app development platform
arize-prompt-optimization
Optimizes, improves, and debugs LLM prompts
OrcaReplay
Time travel for AI agents
OS
Enables organizations to create and deploy customizable AI agents
health
Audits agent config, instruction drift, hooks or MCP, and AI maintainability
EpicStaff
Source-available, self-hosted platform for building AI agent flows
python-observability
Python observability patterns including structured logging, metrics
BugTraceAI
Open-source, self-hosted web pentesting suite
Inferly
LLM telemetry without touching prompt content
google-agents-cli-eval
Evaluate ADK agents with metrics, evalsets, and the iterative eval-fix loop
asqav
Monitor and govern AI agent behavior securely
Opal by Google
Google's enterprise platform for building and deploying AI agents