OpenLIT: Open-Source AI Engineering Platform
OpenLIT is an open-source AI engineering platform built on OpenTelemetry, fully self-hostable, offering LLM observability, evaluations, prompt management, and cost tracking.
About this tool
What
OpenLIT Is OpenLIT is an open-source AI engineering platform for AI engineers, DevOps teams, LLM developers, and data scientists. Built on OpenTelemetry and fully self-hostable, it covers LLM observability, evaluations, prompt management, and cost tracking.
Core Capabilities
- LLM observability and tracing: Trace and monitor LLM calls.
- AI cost tracking: Ships with pricing for popular models and applies it across traces, dashboards, and cost reports; Auto Pricing schedules AI cost tracking for new LLM traces.
- AI spend visibility: See how much each developer, team, and project spends on AI coding tools, broken down by model and vendor across Claude Code, Cursor, and Codex.
- Prompt management: Manage prompts via Prompt Hub, and ask Otter to review a prompt by name or ID.
- Dashboards and analytics: Create dashboards and folders, add widgets, and back up and restore dashboards.
- Agent memory: Store and search long-term agent memories scoped by user, run, or agent.
Deployment
and Integration OpenLIT is open-source and self-hosted, configured through environment variables read once at server process start (no hot-reload). Pre-built binaries are available from GitHub Releases, and it supports GPU metrics collection and eBPF CUDA tracing.
Features & use cases
(/manage-models redirects here) Auto Pricing The Auto Pricing card schedules AI cost tracking for new LLM traces) Toolbar actions (Add Provider, SDK Usage, Import, Export) are icon-only with tooltips), since this isn’t a native VCS integration* metrics Confirm the host has a supported GPU: lspci | grep -E 'VGA|3D|Display' For NVIDIA: verify libnvidia-ml/opentelemetry-gpu-collector For eBPF CUDA tracing support, also run: make setup-bpf # installs bpftool, generates vmlinux16+ Was this page helpful? YesNo Suggest editsRaise issue2Latest patch of a minor version Pre-built binaries Download a binary for your platform from the GitHub Releases page3 Download your dashboard OpenLIT will automatically generate and download a JSON file containing your complete dashboard configurationA “Create a new dashboard or folder” popup will appearA secret’s Key becomes read-only once it’s created - you’d need to create a new secret under a different Key insteadAcceptance % is computed from edit-decision counts - accept and auto_accepted decisions against reject decisions - not from a raw lines-changed ratio.