#llm-observability Repositories
Discover 30 active open source GitHub repositories tagged with #llm-observability, accumulating 151,448 total stars (averaging 5,048 stars per project). Leading this topic is langfuse/langfuse with 37,696 stars.
30 repositories total
๐ชข Open-source AI engineering platform: AI Gateway, agent observability, evaluations, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200ยตs of overhead at 5k RPS.
๐ง Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 ๐
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.
Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
Same agent, smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing ยท Evals ยท Simulations ยท Datasets ยท Gateway ยท Guardrails. Self-hostable. Apache 2.0.
traceroot: the open-source platform that continuously improves your AI agents.
Trace-native CI/CD for AI agents โ production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
OrcaReplay โ Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
Local-first observability for AI coding agents. Every Claude Code and Codex session's tokens, cache, models and cost, on this machine and every machine you connect through a self-hosted team hub. Presenting mode, policy hooks, Apple-signed and notarized macOS builds, attested releases. MIT.
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
DataBuff is an AI-native APM built on OpenTelemetry, with multi-agent troubleshooting out of the box.
๐ฆ Official plugin for OpenClaw that exports agent traces to Opik. See and monitor agent behaviour, cost, tokens, errors and more.
Full Stack application for retrieving Stock Data and News using LLM, LangChain and LangGraph
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
Frequently Asked Questions
What is the most popular #llm-observability repository on GitHub?
The top ranked open source #llm-observability project on GitHub is langfuse/langfuse with 37,696 stars. ๐ชข Open-source AI engineering platform: AI Gateway, agent observability, evaluations, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
Which programming languages are most used in #llm-observability repositories?
Among the top ranked #llm-observability projects on GitHub, the most common programming languages are TypeScript, Python, Java, Go.
How is the #llm-observability repository ranking calculated?
We track 30 active open source repositories tagged with #llm-observability (500+ stars), totaling 151,448 stars with an average of 5,048 stars per repository. Rankings update daily from the GitHub API.