When an AI agent breaks in production, Tracely freezes that exact run into a replayable regression test and blocks the pull request that would ship the bug again. Span soup hides the failure. OTLP/HTTP traces group into conversation threads, and a waterfall marks the failing span in red with its input and output. Nobody knows if an answer was good. Evaluators sit as columns on the trace table, mixing model-free checks with LLM judges at conversation, run, or span level. Thirty-one broken runs, one issue. Clustering turns them into a single counted issue and can suggest the evaluator that would have caught it. A fix nobody can prove. One click promotes a failing trace into a hermetic case with recorded fixtures and a fail-to-pass contract, and scenarios send a red-team model after an adversarial goal. Model bills on every CI run. The suite replays offline with no API keys and no model spend, and tracely gate posts a commit status, comments on the pull request, and blocks regressions. No warning when it breaks again. Alert flows drawn on a canvas react to failed gates, broken conversations, unseen failure modes, or rising failure rates by messaging Slack, sending email, calling a webhook, or prompting an LLM. Coding agents can read traces and write evaluators through an MCP endpoint. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

An agent run can finish without errors and still give the wrong answer, so TraceRoot traces every model and tool call, flags the production runs that missed the mark, and helps your coding agent ship verified fixes. Each run becomes a browsable call tree with inputs, outputs, latency, and cost, searchable by session or filter. Instrument with the Python or TypeScript SDK, the agent-native CLI, or any OpenTelemetry exporter, with ready integrations for LangChain, LangGraph, OpenAI Agents SDK, CrewAI, Vercel AI SDK, Mastra, and Pydantic AI. Detectors use LLM judges to score live traffic against the behavior you define and can post alerts to Slack. Judge outputs cluster into signals, then a background coding agent reads the traces and your connected GitHub code in a sandbox and recommends changes down to the commit, file, and line. Datasets, test cases, and scored eval runs compare versions so regressions surface before a release, and dashboards of widgets chart your trace data. The CLI hands your coding agent, such as Claude Code or Codex, the traces, signals, detectors, and evals to work from. Self-hosting keeps all of that trace data on infrastructure you control. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed (core edition).

When an AI agent goes wrong at step seven of twelve, Opik, an open-source LLM observability platform, shows the exact trace, tool call, and prompt behind it, then scores your fix against test datasets. Full trace trees capture every LLM call, retrieval step, and tool execution, and you can annotate traces and spans with feedback scores in the UI or through the SDK. Native integrations for OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, Google ADK, and DSPy, plus OpenTelemetry for any language with an OpenTelemetry SDK, feed traces in, or add the @track decorator to your own functions. Datasets and experiments compare prompt and model versions, scored by LLM-as-a-judge metrics for hallucination, moderation, and RAG relevance, with a PyTest integration to run evaluations in CI. A Prompt Playground tests prompts across models, and the Agent Optimizer SDK helps improve prompts and agents. Production dashboards track feedback scores, trace counts, and token usage, online evaluation rules score live traces, and optional guardrails add safety checks. An MCP server lets Claude Code, Cursor, VS Code Copilot, Codex, or opencode read traces and run evaluations from chat. Run it yourself with the ./opik.sh script on Docker Compose, or a Helm chart on Kubernetes, so trace data stays in your infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Every call your AI agents make becomes a searchable trace in LangWatch, and the same platform tests and scores those agents before a new prompt or model reaches users. The Trace Explorer filters by origin, user, model, cost, and evaluator, reads each run as a waterfall, flame graph, topology, or sequence diagram, and takes traces from the Python, TypeScript, and Go SDKs or any OpenTelemetry source. Agent Testing sends simulated users, in text or beta voice calls, through your agent while a judge passes or fails every criterion with its reasoning, adds multi-turn red teaming, and compares two agents side by side. The Experiments workbench scores prompts and agents on datasets with LLM judges, exact match, and RAG checks, then compares runs on cost, latency, and pass rate, while online evaluations monitor live traffic and guardrails block unsafe replies. Prompts keep version history and staging or production tags, Workflows wire prompts, Python code, and HTTP calls on a visual canvas, and annotation queues route traces to human reviewers. Alerts fire when a graph crosses a threshold, automations post to Slack, email, or webhooks, and scheduled reports go out by email or Slack. Claude Code, Codex, Copilot, Gemini CLI, and opencode report session cost, pull request cost, and terminal replays, and an MCP server exposes trace search and prompt management to coding assistants. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Your AI application is burning through API tokens faster than you can refresh the billing page, and you have no idea which prompt template is responsible. OpenLIT plugs that visibility gap with a self-hosted observability platform built specifically for LLM workloads. Add one line of code to instrument 90+ LLM providers, agent frameworks, and vector databases, then watch every request flow through a tracing dashboard that shows tokens consumed, latency measured, and dollars spent per call, per model, per environment. The requests view lists every LLM interaction with provider, model, cost, and token breakdown in a filterable table, while the trace detail panel lets you drill into individual spans to read the exact prompt sent and response received. Prompt Hub turns prompts into versioned artifacts you deploy, rollback, and A/B test without touching application code. OpenGround compares models side by side on the same input, so you can evaluate cost-versus-quality tradeoffs before committing to a provider. Automated evaluations run LLM-as-a-judge scoring on live production traces, flagging hallucinations, bias, and toxicity in real time. The Vault stores and rotates API keys centrally so secrets stay out of your codebase. Custom dashboards let you build drag-and-drop monitoring views with charts, stat cards, and tables backed by SQL queries against ClickHouse. GPU utilization, memory, temperature, and power metrics feed into the same platform for end-to-end infrastructure visibility. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Backed by Y Combinator and trusted by over 2,300 companies processing billions of observations monthly, Langfuse is the most widely adopted open-source platform for building, monitoring, evaluating, and debugging LLM applications. The hierarchical tracing engine captures every LLM call, tool invocation, retrieval step, and agent action as nested spans based on OpenTelemetry, with automatic cost calculation, latency tracking, and token usage attribution across sessions and users. Prompt Management separates prompts from code with versioned artifacts, label-based deployments, one-click rollbacks, and runtime SDK fetching with server-side caching, while linking every generation back to its exact prompt version for attribution analytics. The evaluation system supports LLM-as-a-judge scoring, heuristic code evaluators, user feedback collection, and manual annotation workflows that run automatically on production traces or against curated datasets. The Playground enables interactive prompt testing on real production inputs with side-by-side model comparison across providers. Datasets and Experiments define test cases for systematic benchmarking with comparative result visualization. Native SDKs for Python and TypeScript provide decorator-based instrumentation, while 100+ integrations cover LangChain, LlamaIndex, OpenAI SDK, LiteLLM, Vercel AI SDK, and any OpenTelemetry-instrumented framework. The analytics dashboard surfaces cost breakdowns, quality scores, latency percentiles, and usage trends across models and prompt versions. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Agenta delivers a comprehensive open-source LLMOps workspace that covers the full lifecycle of AI application development — from prompt engineering through production monitoring. The platform supports 15+ model providers including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Together AI, Azure, AWS Bedrock, and self-hosted models via Ollama, enabling teams to switch between providers without code changes. The prompt playground allows side-by-side comparison of different configurations, while the evaluation system offers LLM-as-a-Judge assessment, 20+ pre-built evaluators covering semantic similarity, regex matching, and factual accuracy, plus custom Python evaluators for domain-specific requirements. Teams run evaluations through both the web UI for subject matter experts and the Evaluation SDK for programmatic CI/CD integration. The observability layer captures full trace visibility across complex agentic workflows, flagging quality issues like hallucinations and off-topic responses in real time. Human annotation workflows let domain experts review and annotate LLM outputs, feeding corrections back into the evaluation loop. The architecture supports Chain of Prompts, RAG pipelines, and multi-step agent workflows, integrating with frameworks like LangChain and LlamaIndex. Self-hosting deploys via Docker Compose with Traefik for routing, requiring only a clone, environment configuration, and a single docker compose command. On RepoCloud, deploy Agenta on a dedicated VPS with root SSH access, persistent storage for evaluation datasets and traces, and complete control over model provider credentials, all under the MIT license with no usage restrictions.

Backed by Y Combinator (S24) and processing traces from thousands of AI agents in production, Laminar is the open-source observability platform that treats agent debugging as a first-class engineering discipline rather than an afterthought. Its OpenTelemetry-native SDK auto-instruments Vercel AI SDK, LangChain, OpenAI, Anthropic, Gemini, Browser Use, Stagehand, Mastra, Pydantic AI, and the OpenAI Agents SDK with a single line of code, capturing every LLM turn, tool call, and sub-agent delegation as nested spans with full input/output data and token costs. The Signals engine lets you describe failures in plain language — "agent is stuck in a loop" or "tool returned empty results" — then reads every trace and alerts via Slack when it detects a match. A built-in debugger records runs and replays them from cache so each iteration takes seconds, designed for Claude Code, Cursor, or Codex to drive the repair loop via the MCP server or CLI. Run code-first evaluations in Python or TypeScript locally or in CI/CD pipelines, build datasets from production traces, and query everything with raw SQL through custom dashboards, the in-app editor, or your coding agent. The Rust backend delivers 20x trace compression, a custom real-time streaming engine, ultra-fast full-text search, and gRPC ingestion, while ClickHouse powers columnar analytics and PostgreSQL stores application state. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Software developers running Claude Code, Cursor, Codex, and Aider use AgentsView to trace token expenditures, search full session transcripts, and analyze multi-agent concurrency timelines. Engineers can search through historical developer sessions to locate specific code modifications, prompt chains, or debugging rationales across extensive programming workflows. The real-time activity timeline visualizes concurrent agent operations, revealing peak execution windows, task run durations, and automated tool invocations. The usage analytics engine calculates financial costs and token volumes per model by applying live pricing tables while accounting for prompt caching read discounts. Developers inspect granular turn-by-turn session transcripts complete with raw model payloads, file difference diffs, executed shell commands, and syntax errors. The recall browser extracts key technical context from past programming sessions, organizing facts into an indexed reference knowledge corpus for reuse across future project tasks. Administrators can replicate SQLite session tables into DuckDB analytics files or PostgreSQL warehouses to query longitudinal metrics using SQL analytical tools or custom reporting scripts. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

To pull a team's skills, MCP servers, hooks, prompts, and agent files out of scattered Git repositories, Observal keeps them in one reviewed registry and traces real sessions to show which ones help. Build an agent visually, with a live config preview for every harness. Submissions wait in an admin review queue, where reviewers inspect side-by-side version diffs before approving a release. Teamspaces give each team its own namespace, and approved releases can be forked into independent drafts. One pull command then writes the right config for Claude Code, Cursor, Kiro, Codex, Copilot, Pi, OpenCode, Antigravity, or Goose. Every approved resource is discoverable through the open Agentic Resource Discovery standard, and a running agent can hand part of its task to another approved agent or a remote Agent2Agent service. Hooks record each session as a trace of prompts, tool calls, MCP round trips, tokens, and errors, with turn-by-turn replay for debugging and audits. Insight reports, generated through providers such as Anthropic, OpenAI, or Ollama, list what is working, what is hindering, and quick wins. A dashboard follows adoption, cost, and department usage, a leaderboard ranks agents by downloads, and audit logs, SAML single sign-on, and SCIM provisioning are included. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Stop guessing which model writes better and watch them compete on your own prompts: LMRing runs two to five language models side by side on the same input, streams every answer in real time, and lets you vote for the winner. Each comparison feeds a leaderboard you can read as a ranked table, a bar chart, or a scatter plot, so patterns in cost, speed, and quality stop hiding inside individual chats. The arena goes beyond text, with dedicated modes for comparing generated images, generated video across providers such as Sora and Veo, and live-rendered web development output where model code runs in front of you. More than fifty providers connect through their APIs, including OpenAI, Anthropic, Google, DeepSeek, Mistral, Groq, OpenRouter, and any OpenAI-compatible endpoint you point it at. Your comparison history is saved, shareable, and revisitable, which turns one-off impressions into an evaluation record your team can argue from. Sign-in flexes to your setup with GitHub, Google, or Linux.do OAuth, or email one-time codes, and the interface speaks English, French, and Chinese. Because the arena is yours, the prompts, votes, and provider keys stay on infrastructure you control instead of feeding someone else's public ranking. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

With over 31,000 GitHub stars and native OpenTelemetry support that eliminates vendor lock-in from day one, SigNoz delivers full-stack observability covering metrics, traces, and logs in a single pane of glass without the per-host pricing model of commercial APM platforms. The platform ingests telemetry data through the OpenTelemetry Collector, supporting auto-instrumentation for Java, Python, Node.js, Go, Ruby, PHP, and .NET applications with zero code changes required for basic tracing. ClickHouse serves as the columnar storage backend, providing fast aggregation queries over billions of spans and log lines with configurable retention policies and tiered storage. The distributed tracing view renders flame graphs and Gantt charts showing request flow across microservices with latency breakdowns, error rates, and p99 percentile calculations. Custom dashboards support PromQL and ClickHouse SQL queries with time-series charts, bar graphs, tables, and value widgets. The log management pipeline supports structured and unstructured logs with full-text search, log pipelines for parsing and enrichment, and correlation with traces via trace IDs. Alert rules can be configured on any metric or log query with notification channels including Slack, PagerDuty, OpsGenie, webhooks, and email. The exceptions monitoring module automatically groups and tracks application errors with stack traces, occurrence counts, and first-seen timestamps. Service maps visualize inter-service dependencies with real-time latency and error rate overlays. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed with an enterprise edition available.

Created by Uber Technologies and graduated as the seventh CNCF top-level project in October 2019 with over 23,000 GitHub stars, Jaeger has become one of the most widely deployed open-source distributed tracing platforms, processing billions of spans per day in production environments at organizations including Uber, Red Hat, and Shopify. Version 2 rebuilt the platform on the OpenTelemetry Collector framework, inheriting its extensible pipeline architecture while implementing Jaeger-specific features as extensions and components, enabling seamless integration with the OpenTelemetry ecosystem through native OTLP protocol support. The platform stores traces in Cassandra 4.0+, Elasticsearch 7.x/8.x, OpenSearch 1.0+, ClickHouse, or the embedded Badger database for development setups. Three sampling strategies control trace volume: head-based sampling with constant, probabilistic, and rate-limiting modes, tail-based sampling using the OpenTelemetry Collector processor that evaluates complete traces before storage decisions, and adaptive sampling that dynamically adjusts probabilities based on observed traffic patterns. Service Performance Monitoring computes RED metrics directly from spans, displaying request rates, error rates, and latency percentiles in the Monitor tab with drill-down from aggregate service views to individual traces. The web UI provides trace search with multi-field filtering, trace detail views with span timeline visualization, trace comparison across services, and dependency graphs mapping service relationships from actual traffic. Deployment options range from a single all-in-one binary for development to distributed collector-ingester-query configurations with Kafka intermediate buffering for production scale. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

With 20,500+ GitHub stars and over 6,000 organizations running it in production — including a Fortune 100 company ingesting more than 4 PB per day — OpenObserve is the open-source observability platform that replaces your entire Datadog, Splunk, or ELK stack with a single Rust binary deploying in under two minutes. Apache Parquet columnar storage with zstd compression on S3-compatible object storage delivers 140x lower storage costs than Elasticsearch while providing better query performance on a quarter of the hardware. Ingest logs, metrics, and distributed traces via native OpenTelemetry OTLP endpoints with no vendor lock-in. Query logs and traces with standard SQL, metrics with SQL or PromQL — no proprietary query language to learn. The built-in dashboard builder offers 19 chart types including time-series graphs, heatmaps, gauges, tables, and top-K lists with drag-and-drop layout combining data from all signal types. Data pipelines process, enrich, redact, or normalize ingestion streams using Vector Remap Language for real-time transformations including PII redaction and logs-to-metrics conversion. Real User Monitoring captures frontend performance with session replay. The Service Catalog provides topology-based trace analysis with side-panel drill-downs into database queries and error details. Alerting supports real-time and scheduled rules with SQL and PromQL conditions. Native multi-tenancy isolates organizations and streams with complete data separation. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPLv3 licensed.

The de facto dashboard of observability: Grafana is the open-source frontend that turns the data stores you already run into interactive graphs. It does not store metrics itself; it connects to the data stores you already run and turns their contents into interactive dashboards. Supported sources number over 150 via plugins: Prometheus, Loki, Tempo, InfluxDB, Elasticsearch, MySQL, PostgreSQL, Microsoft SQL Server, AWS CloudWatch, Azure Monitor, Google Cloud Monitoring, and many more. Dashboards are built from a large library of panel types (time series, heatmaps, tables, gauges, logs) with template variables for reusable, parameterized views. Unified alerting evaluates rules against any connected data source, not just Prometheus, and routes notifications to Slack, PagerDuty, email, and other channels with grouping and silencing - unlike Prometheus Alertmanager, a single rule can combine a Loki log pattern, a PostgreSQL query result, and a CloudWatch metric. Dashboards serialize to JSON and data sources configure via provisioning files, so the entire observability setup can live in Git and deploy repeatably across environments. Explore mode adds ad-hoc querying outside dashboards, with split view for correlating a metric spike against the matching log lines, and access control spans organizations, teams, folder permissions, and OAuth, LDAP, and SAML integration. Written in Go and TypeScript, AGPL-licensed. Self-hosting gives you unlimited users, dashboards, and queries at flat hosting cost, without Grafana Cloud's usage-based pricing.