agent-observability repositories

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

  1. 1
    FailproofAI/failproofai

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

    GitHub · TypeScript · 9,893 stars · 580 forks · +99 stars in 24 hours · Trending score 3.83

  2. 2
    alexeyw/lot-map

    Lot Map for Claude Code: a live map beside the chat that shows what the agent is doing. Tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in 7 languages.

    GitHub · TypeScript · 1,057 stars · 116 forks · +48 stars in 24 hours · Trending score 3.61

  3. 3
    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 · 334 stars · 52 forks · +77 stars in 24 hours · Trending score 3.28

  4. 4
    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 · 149 stars · 6 forks · +21 stars in 24 hours · Trending score 2.75

  5. 5
    traceroot-ai/traceroot

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

    GitHub · TypeScript · 1,439 stars · 355 forks · +18 stars in 24 hours · Trending score 2.65

  6. 6
    oriliz/agent-crop

    给 AI 编程助手一根马鞭:本地记录时间去向,把复盘写回 agent 指令/技能/工具;改没改好,用数据说话。 | A whip for coding agents: local timing, red-line nudges, and an evidence-backed, auditable self-improvement loop. DSH / Claude Code / Codex.

    GitHub · Python · 174 stars · 0 forks · +81 stars in 24 hours · Trending score 2.15

  7. 7
    liaohch3/claude-tap

    Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

    GitHub · Python · 3,355 stars · 292 forks · +10 stars in 24 hours · Trending score 2.06

  8. 8
    Agenta-AI/agenta

    Agenta is a workspace where you and your team build agents and automations.

    GitHub · TypeScript · 4,923 stars · 731 forks · +7 stars in 24 hours · Trending score 1.99

  9. 9
    builderz-labs/mission-control

    Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.

    GitHub · TypeScript · 6,514 stars · 142 forks · +7 stars in 24 hours · Trending score 1.97

  10. 10
    wangmiaozero/pi-harness

    The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

    GitHub · TypeScript · 329 stars · 29 forks · +7 stars in 24 hours · Trending score 1.90

  11. 11
    InnerAura/hyperweave

    Visual CLI for agents. Deterministic SVG diagrams, tables, and charts with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.

    GitHub · Python · 62 stars · 10 forks · +14 stars in 24 hours · Trending score 1.88

  12. 12
    sodiumsun/agenttrail

    Local observability for AI coding agents. Agenttrail Map shows your project as a live map of what each agent is working on, in the browser or natively in Herdr.

    GitHub · JavaScript · 1,041 stars · 78 forks · +6 stars in 24 hours · Trending score 1.82

  13. 13
    taichuy/1flowbase

    Build for agents — from the AI Gateway to the entire application stack.

    GitHub · Rust · 296 stars · 24 forks · +9 stars in 24 hours · Trending score 1.69

  14. 14
    oxbshw/watch-skill

    Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

    GitHub · Python · 586 stars · 84 forks · 0 stars in 24 hours · Trending score 1.69

  15. 15
    pydantic/logfire

    AI observability platform for production LLM and agent systems.

    GitHub · Python · 4,564 stars · 377 forks · +3 stars in 24 hours · Trending score 1.58

  16. 16
    lmnr-ai/lmnr

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

    GitHub · TypeScript · 3,514 stars · 262 forks · +5 stars in 24 hours · Trending score 1.58

  17. 17
    dunetrace/dunetrace

    The runtime reliability layer for AI agents.

    GitHub · Python · 73 stars · 26 forks · +2 stars in 24 hours · Trending score 1.21

  18. 18
    najeed/ai-agent-eval-harness

    The open-source MultiAgentOps evaluation and verification harness for any industry business workflow.

    GitHub · Python · 48 stars · 9 forks · +3 stars in 24 hours · Trending score 1.00

  19. 19
    chirpz-ai/pandaprobe

    open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.

    GitHub · Python · 808 stars · 122 forks · 0 stars in 24 hours · Trending score 0.97

  20. 20
    dosu-ai/decant

    See where your coding agents spend tokens, money, and time. A local-first, searchable archive of Claude Code, Codex, Gemini CLI, OpenCode, Cursor CLI, and GitHub Copilot sessions, with ATIF import and export. Built by Dosu.

    GitHub · TypeScript · 77 stars · 6 forks · +2 stars in 24 hours · Trending score 0.91

  21. 21
    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 0.91

  22. 22
    aa2246740/dsh-watcher

    Read-only Agent work-path observer for DeepSeek Harness

    GitHub · JavaScript · 126 stars · 6 forks · +2 stars in 24 hours · Trending score 0.91

  23. 23
    duqaXxX/seedeep

    What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.

    GitHub · TypeScript · 49 stars · 3 forks · +3 stars in 24 hours · Trending score 0.91

  24. 24
    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 0.85