langfuse/langfuse
Langfuse is an open-source LLM engineering platform for developing, monitoring, evaluating, and debugging AI applications, offering observability, prompt management, and evaluation capabilities.
Awesome Infra for AI › LLM Observability & Tracing
sodiumsun/agenttrail
agenttrail is an open-source observability layer for AI coding agents such as Claude Code, OpenAI Codex and Cursor. It answers the question a developer has while an agent runs unattended: is it making progress, is it stuck, and has it quietly reopened work it already called done. Running npx agenttrail in a repository starts a local daemon and opens a board in the browser. The model rests on two signals. Declared intent comes from PLAN.md, a small Markdown map that the agents themselves maintain, describing five to nine components with dependencies and honest done, working or blocked states. Observed activity comes from a file watcher plus optional Claude Code hooks that relay run events. When the two disagree, the board shows where to look: a completed card lights up again when its files change, and a live run sits on the component it is touching. The board shows the current run with its task list, streaming tool line, elapsed time and recent calls, a repository tree with just-touched accents, provenance pills separating imminent agent intent from roadmap backlog, and per-agent marks on completed tasks. One daemon runs per repository and every live board appears in a shared tab switcher; agenttrail up relaunches previously used boards after a reboot and agenttrail autostart makes a board start at login. agenttrail init writes the convention into CLAUDE.md and AGENTS.md, creates a starter PLAN.md and installs additive repo-local hooks, only with consent. The implementation is deliberately small: one dependency-free Node daemon of roughly 470 lines and a single static HTML interface, with no database, build step, account or telemetry. It binds to 127.0.0.1 only and never sends a prompt or edits code.
https://github.com/sodiumsun/agenttrail
Also in LLM Observability & Tracing
comet-ml/opik
Opik is an open-source platform for comprehensive observability, evaluation, and optimization of LLM applications, RAG systems, and agentic workflows.
raga-ai-hub/RagaAI-Catalyst
RagaAI Catalyst is a Python SDK for comprehensive observability, monitoring, and evaluation of AI agents and LLM applications, offering tracing, debugging, and advanced analytics.
Arize-ai/phoenix
Phoenix is an open-source AI observability platform for LLM application experimentation, evaluation, and troubleshooting, providing tracing, evaluation, dataset management, prompt management, and a...
VoltAgent/voltagent
VoltAgent is an end-to-end AI Agent Engineering Platform offering an open-source TypeScript framework for building intelligent agents and a VoltOps Console for observability, automation, deployment...
traceloop/openllmetry
OpenLLMetry provides open-source observability for LLM applications by extending OpenTelemetry to capture traces and metrics from LLM providers, vector databases, and AI frameworks.
Helicone/helicone
Helicone is an open-source LLM observability platform and AI gateway that provides monitoring, evaluation, prompt management, and intelligent routing for large language models.
Agenta-AI/agenta
Agenta is an open-source LLMOps platform designed to accelerate the development of reliable LLM applications, offering integrated prompt management, evaluation, and observability features.