llm-observability repositories

Trending repositories tagged llm-observability, ranked by trending score. Updated daily.

  1. 1
    Continuum-AI-Corp/OrcaReplay

    OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

    GitHub · TypeScript · 1,038 stars · 166 forks · +730 stars in 24 hours · Trending score 5.14

  2. 2
    FailproofAI/failproofai

    Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

    GitHub · TypeScript · 9,877 stars · 580 forks · +218 stars in 24 hours · Trending score 4.22

  3. 3
    langfuse/langfuse

    🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.

    GitHub · TypeScript · 37,664 stars · 4,277 forks · +85 stars in 24 hours · Trending score 3.85

  4. 4
    maximhq/bifrost

    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 200µs of overhead at 5k RPS.

    GitHub · Go · 9,800 stars · 1,628 forks · +73 stars in 24 hours · Trending score 3.67

  5. 5
    scasella/claude-flightdeck

    A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

    GitHub · TypeScript · 333 stars · 52 forks · +76 stars in 24 hours · Trending score 3.28

  6. 6
    comet-ml/opik

    Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

    GitHub · Java · 23,460 stars · 1,964 forks · +10 stars in 24 hours · Trending score 2.61

  7. 7
    traceroot-ai/traceroot

    traceroot: the open-source platform that continuously improves your ai agents.

    GitHub · TypeScript · 1,434 stars · 351 forks · +11 stars in 24 hours · Trending score 2.44

  8. 8
    openlit/openlit

    Same agent, Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.

    GitHub · TypeScript · 3,091 stars · 494 forks · +5 stars in 24 hours · Trending score 2.03

  9. 9
    pydantic/logfire

    AI observability platform for production LLM and agent systems.

    GitHub · Python · 4,561 stars · 376 forks · +6 stars in 24 hours · Trending score 1.90

  10. 10
    lmnr-ai/lmnr

    Laminar - open-source observability platform purpose-built for AI agents. YC S24.

    GitHub · TypeScript · 3,510 stars · 262 forks · +8 stars in 24 hours · Trending score 1.85

  11. 11
    Abilityai/trinity

    Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

    GitHub · Python · 789 stars · 154 forks · +5 stars in 24 hours · Trending score 1.76

  12. 12
    future-agi/future-agi

    Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

    GitHub · Python · 2,288 stars · 725 forks · +2 stars in 24 hours · Trending score 1.55

  13. 13
    ThinkWatchProject/ThinkWatch-Lite

    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.

    GitHub · TypeScript · 1,073 stars · 8 forks · +2 stars in 24 hours · Trending score 1.40

  14. 14
    alibaba/loongsuite-pilot

    Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

    GitHub · TypeScript · 265 stars · 66 forks · +2 stars in 24 hours · Trending score 1.35

  15. 15
    splunk/token-meter

    Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.

    GitHub · Python · 154 stars · 36 forks · +3 stars in 24 hours · Trending score 1.26

  16. 16
    jackulau/coding.sh

    Open-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.

    GitHub · TypeScript · 117 stars · 4 forks · 0 stars in 24 hours · Trending score 1.25

  17. 17
    Helicone/helicone

    🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

    GitHub · TypeScript · 6,278 stars · 704 forks · 0 stars in 24 hours · Trending score 1.25

  18. 18
    agenttrailhq/guard

    Observability and guardrails for your ai agents. AgentTrail Guard traces your agent's execution and automatically compiles repeat failures into permanent guardrails.

    GitHub · TypeScript · 14 stars · 3 forks · +2 stars in 24 hours · Trending score 0.88

  19. 19
    mnfst/llm-gateway

    Open Source LLM Gateway 🦚

    GitHub · TypeScript · 7,639 stars · 531 forks · 0 stars in 24 hours · Trending score 0.83

  20. 20
    anhermon/awesome-agent-observability

    Curated list of LLM and AI agent observability and evaluation tools: tracing, evals, LLM-as-judge, guardrails, OpenTelemetry GenAI, MCP.

    GitHub · Python · 65 stars · 36 forks · +1 stars in 24 hours · Trending score 0.82

  21. 21
    spectra-php/laravel-spectra

    Observability for AI and LLM calls in Laravel. Automatically tracks requests to OpenAI, Anthropic, Gemini, Mistral and more, calculates token and media costs, enforces per-user budgets, and ships a real-time dashboard with OpenTelemetry export.

    GitHub · PHP · 31 stars · 1 forks · +1 stars in 24 hours · Trending score 0.74

  22. 22
    coze-dev/coze-loop

    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.

    GitHub · Go · 5,799 stars · 804 forks · +3 stars in 24 hours · Trending score 0.70

  23. 23
    PerryLink/dsh-observe

    OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, sanitized prompt/completion capture, async batching, bounded offline buffering, retry with backoff

    GitHub · TypeScript · 16 stars · 2 forks · +1 stars in 24 hours · Trending score 0.63

  24. 24
    Necmttn/ax

    the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

    GitHub · TypeScript · 123 stars · 16 forks · 0 stars in 24 hours · Trending score 0.56