
The AI workspace where teams and agents get work done together
#1Arize AI records 249,028 monthly visits with +3.2% month-over-month growth and Paid, Contact for Pricing pricing. Fact0 records 0 monthly visits with 0% growth and Open Source (MIT); self-hosted, no subscription fees pricing.

Self-hosted audit history and execution replay for AI agents
| +7.67K (+3.2%) |
| 0 (0%) |
| Primary Market & Share | 🇺🇸 United States (51.6%) | 🌐 Global (—) |
|---|
| Direct Visits / mo | 107.84K | 0 |
|---|
| User Rating | 4.6 | 4.5 |
|---|
| Supported Platforms | Website | Website |
|---|

Agent observability, evaluation, and continuous improvement for production AI
Capture spans, traces, and sessions across agents and LLM calls using OpenInference conventions built on OpenTelemetry, so instrumentation stays portable.
Run evaluations at span, trace, and session level to grade retrieval quality, tool use, and final answers across large production datasets.
An in-product agent that inspects traces, diagnoses likely root causes, and proposes fixes that engineers can review before shipping.
Self-host the leading open-source tracing and eval tool when you need to keep trace data inside your own infrastructure.

Self-hosted audit history and execution replay for AI agents
Run the API, dashboard and PostgreSQL in your own environment via Docker Compose, then point your agent at the local instance with an API key. Data and signing keys stay with your installation.
Record Python agents through the SDK (execution spans, tool results, supported model content, audit events) and Claude Code sessions through the collector plugin, then inspect both in the same workspace.
Follow a run through a graph, a timing waterfall and recorded spans, then step through saved events at your own pace. Replay reconstructs the record without re-running the agent.
Check the consistency of stored events against their hashes and preceding links, with capture gaps reported visibly rather than hidden.

The AI workspace where teams and agents get work done together
#1Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.


Free / Open-sourceOpen-source personal AI assistant that runs on your own machine and works from chat apps
#3No-code builder for custom AI agents and workflows

Free / Open-sourceOpen-source desktop AI workforce that runs browser, file, and app tasks for you

Excels at experiment tracking and model registry workflows, but is less purpose-built for real-time LLM production observability.

Free / Open-sourceOpen-source workspace to build, deploy and govern AI agents

Free / Open-sourceSelf-driving agent platform you run in your own cloud

Free / Open-sourceIncludes integrated guardrails and simulation tools, but is less mature for large-scale enterprise production telemetry monitoring.

Free / Open-sourceFeatures strong testing and prompt evaluation tools, though its monitoring interface is less oriented towards massive telemetry streams.

Focuses heavily on prompt management and versioning control, whereas Arize prioritizes end-to-end tracing and ML observability.

Offers comprehensive LLM evaluation and unit testing via DeepEval, but lacks Arize's deep production monitoring infrastructure.
Free / Open-sourceA free, open-source personal AI agent that learns your projects and works across every messaging app.
Free / Open-sourceOpen-source personal AI assistant that runs on your own machine and works from chat apps
No-code builder for custom AI agents and workflows
Excels at experiment tracking and model registry workflows, but is less purpose-built for real-time LLM production observability.
Free / Open-sourceIncludes integrated guardrails and simulation tools, but is less mature for large-scale enterprise production telemetry monitoring.
Free / Open-sourceFeatures strong testing and prompt evaluation tools, though its monitoring interface is less oriented towards massive telemetry streams.
Focuses heavily on prompt management and versioning control, whereas Arize prioritizes end-to-end tracing and ML observability.
Offers comprehensive LLM evaluation and unit testing via DeepEval, but lacks Arize's deep production monitoring infrastructure.