Self-Host Overview

AgentX-trace-eval is the open-source, self-hosted build of AgentX’s governance layer. One local install gives you the complete loop - Trace, Monitor, Evaluate, Improve - with no account and no multi-tenant billing. You bring your own OpenAI, Anthropic, or Gemini keys for the LLM-judge features; everything else runs entirely offline.

​

Architecture

• Engine - a TypeScript HTTP API (the same Trace/Monitor/Evaluate logic the hosted product runs) compiled to a single native binary, so no Node or Bun is needed at runtime. SQLite by default, Postgres via one connection string.
• CLI (agentx / agentx-server) - a small Go launcher: starts the engine, opens the dashboard, forwards shutdown signals.
• Dashboard - the real AgentX Governance UI, not a rebuild: the same frontend the hosted product uses, built in self-host mode and served by the engine itself.

Get running in a minute with Installation, then tune Configuration as needed. Every feature page in the Trace, Monitor, Evaluation, and Improve tabs applies to a self-hosted instance; pages marked “Self-host feature” are exclusive to it.

​

What’s included

Observe - Live Traces with span-tree Timeline/Graph views and trajectory metrics, Sessions with conversation-level judging, per-framework tracing guides in the UI. Monitor - built-in and custom patterns, online evaluators (per-trace and per-session), custom evaluators, topics, signal triage with archiving, outcomes and judge calibration, model comparison. Evaluate - datasets with version history, code scorers, evaluator configs, runs with judge scores and trajectory matching, datasets curated from production, model portability, and the interactive Playground with conversation simulation. Improve - Prompt Management and Tools registries with evidence-backed suggestions and measured proposal validation, plus CI gates with recorded history.

​

What stays hosted-only

Hosted’s native autotune workflow (candidate config branching for AgentX-built agents) is tied to the hosted agent-builder and is an explicit non-goal for self-host - the Improve tab here centers on the prompt/tool registries instead, which serve the same “make the agent better” purpose for externally-built agents.

​

Open source scope

The engine, CLI, and Python SDK are Apache-2.0. The dashboard is built from AgentX’s private frontend; only its compiled bundle is published, attached to the repo’s releases - so installs and source builds never need access to the private repo, and dev mode fetches the bundle automatically on first boot.