Alternatives to Pezzo

LangSmith is agent and LLM observability from the LangChain team: trace, monitor, evaluate, and deploy AI agents.

Open-source LLM observability: trace agents, manage prompts, and run evals on one MIT-licensed platform.

Open source AI engineering platform for agent and LLM tracing, evaluation, prompt management, and ML lifecycle work.

Open-source LLM observability, evaluation, and cost tracking for teams shipping agentic AI

Open-source LLM observability and agent evaluation you can trace, self-host, and eval end to end.

LangWatch is an open-source LLMOps platform for agent testing, LLM evaluation and OpenTelemetry-native LLM observability.

Open-source AI evaluation and observability for LLMs, RAG apps, AI agents, and ML models.

Laminar delivers open-source AI agent observability that auto-captures every LLM and tool call and surfaces failures with Signals.

OpenLIT delivers OpenTelemetry-native LLM tracing, evals, guardrails, and prompt management you self-host free under Apache 2.0.

Local, MIT-licensed token usage and cost tracking for AI coding agents — reads the logs your agents already write.

Token Monitor tracks AI coding token usage, cost, and quota limits across 44+ tools in one free desktop widget.

PandaProbe is open-source agent observability that traces runs, evaluates outcomes, and turns failures into validated fixes via its Repair

Maxim AI simulates, evaluates and observes AI agents — with Bifrost, its open-source LLM gateway, for routing and guardrails.

Open-source AI agent improvement: trace production runs, detect failures, investigate signals, verify fixes with evals.

Track AI spend across OpenAI, Anthropic, Google AI, Bedrock and Azure in one live cost dashboard.

Conan is a native macOS HUD for Claude Code that streams every prompt, tool call, skill and token live as the session runs.

Open-source Python framework that traces every AI agent span and scores runs with benchmarked, explainable LLM judges.

PromptLayer is the collaboration layer for AI engineering teams — a prompt CMS, eval harness, and agent observability stack in one dashboard.

Open-source Python library that turns vibe checks into reproducible evaluation loops for RAG pipelines and AI agents.

Edgee Team token observability puts every coding agent on a budget you set, with per-repo and per-PR attribution.

Open-source OpenTelemetry tracing, versioning, and sessions for Python LLM apps—bring your own backend.

AgentNotch streams live Claude Code and Codex token and cost telemetry into your Mac's notch

Open-source benchmark that scores AI agents on real, multi-step software-company work tasks.

Open-source toolkit for benchmarking vision-language models across 80+ multimodal tasks, with rankings published on the Open VLM Leaderboard.

Open-source React components for rendering AI agent traces, tool calls and reasoning inside your own app.

Open-source collaboration layer that turns domain expertise into AI agent test suites

Open-source PyTorch toolkit for feature attribution in sequence generation models

OpenJudge is an Apache 2.0 open-source AI evaluation framework shipping 50+ benchmark-validated graders for agents, LLMs, code, math, and multimodal models.

Zero-config local dashboard that shows what your OpenClaw agents actually did, what they cost, and whether they leaked secrets

AI quality workspace for LLM evaluation, production observability, red teaming, and governance