LLM observability: tools for developers

Tool ranking

Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

1. 1

   agent-stack

   Skill

   ActiveLast commit 3 days ago · 2026-09-01

   Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.

   PythonLicense: MIT

   • a2a
   • agent-orchestration
   • agent-skills
   • ai-agents
   • developer-tools

   githubcreated 30 days agomeasured growthOpen source ↗

   Install git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack

   2GitHub stars+1 (+100.0 %)
2. 2

   untell

   Other

   ActiveLast commit today · 2026-09-05

   AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude…

   PythonLicense: MIT

   • ai-detection
   • ai-detector
   • benchmark
   • claude-code
   • claude-code-skill

   githubcreated 2 months agomeasured growthOpen source ↗

   18GitHub starsstable
3. 3

   opik-claude-code-plugin

   MCP

   ActiveLast commit 36 days ago · 2026-07-30

   Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

   GoLicense: Apache-2.0

   • ai-agent
   • claude-ai
   • claude-code-plugin
   • llm-observation
   • mcp-server

   githubcreated 6 months agomeasured growthOpen source ↗

   22GitHub stars+1 (+4.8 %)
4. 4

   bar-observatory

   MCP

   ActiveLast commit 8 days ago · 2026-08-27

   Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

   HTMLLicense: MIT

   • agent-monitoring
   • agentic-ai
   • ai-agents
   • ai-engineering
   • audit

   githubcreated 23 days agonewmeasured growthOpen source ↗

   22GitHub stars+2 (+10.0 %)
5. 5

   deslop-GPT

   Skill

   ActiveLast commit 1 day ago · 2026-09-04

   Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

   PythonLicense: MIT

   • agent-skills
   • claude
   • claude-ai
   • claude-code
   • claude-skills

   githubcreated 12 days agonewmeasured growthOpen source ↗

   Install git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT

   87GitHub stars+59 (+210.7 %)
6. 6

   agenttap

   Agent

   DormantLast commit 5 months ago · 2026-04-05

   Real-time debugging proxy for Agent2Agent (A2A) multi-agent systems

   License: MIT

   • a2a
   • agent2agent
   • debugging
   • debugging-tool
   • developer-tools

   githubcreated 5 months agomeasured growthOpen source ↗

   3GitHub starsstable
7. 7

   agentanvil

   Agent

   DormantLast commit 4 months ago · 2026-04-29

   Contract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.

   PythonLicense: MIT

   • a2a
   • agents
   • contracts
   • evaluation
   • llm

   githubcreated 4 months agomeasured growthOpen source ↗

   0GitHub starsstable
8. 8

   sentry-instrumentation

   Skill

   ActiveLast commit 2 months ago · 2026-06-19

   Sentry instrumentation skill for system-behavior tracking

   ShellLicense: MIT

   • agent-skills
   • claude-skills
   • codex-skill
   • instrumentation
   • monitoring

   githubcreated 4 months agomeasured growthOpen source ↗

   Install git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation

   24GitHub starsstable
9. 9

   adaptive-harness

   Skill

   DormantLast commit 5 months ago · 2026-03-16

   A self-improving harness router for Claude Code.

   PythonLicense: MIT

   • a-b-testing
   • ai-agent
   • ai-orchestration
   • ai-routing
   • ai-workflow

   githubcreated 5 months agomeasured growthOpen source ↗

   Install /plugin marketplace add SeongwoongCho/adaptive-harness

   8GitHub starsstable
10. 10

    axiom

    Skill

    ActiveLast commit 5 days ago · 2026-08-31

    Axiom is a curated marketplace of shared plugins for Claude Code and Codex.

    PythonLicense: MIT

    • agent-skills
    • anthropic
    • claude
    • claude-code
    • claude-code-marketplace

    githubcreated 3 months agomeasured growthOpen source ↗

    Install git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom

    5GitHub starsstable
11. 11

    astragraph

    Agent

    DormantLast commit 5 months ago · 2026-03-16

    Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.

    Rust

    • a2a
    • ai-agents
    • llm-security
    • mcp
    • multi-agent

    githubcreated 7 months agomeasured growthOpen source ↗

    26GitHub starsstable
12. 12

    CodeFlow

    Agent

    ActiveLast commit 2 days ago · 2026-09-03

    面向长程研发任务的 Java Agent Harness，支持 A2A 跨语言协作、可恢复执行、上下文工程与 Eval 驱动开发。

    JavaLicense: Apache-2.0

    • a2a
    • agentic-ai
    • ai-agents
    • developer-tools
    • evals

    githubcreated 9 days agonewmeasured growthOpen source ↗

    0GitHub starsstable
13. 13

    langsmith-fetch-skill

    Skill

    DormantLast commit 5 months ago · 2026-04-06

    🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

    License: MIT

    • agent-debugging
    • ai-agents
    • claude-skills
    • claude-skills-creator
    • claude-skills-hub

    githubcreated 8 months agomeasured growthOpen source ↗

    Install git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill

    27GitHub starsstable
14. 14

    mcp-smb-products

    MCP

    ActiveLast commit 2 months ago · 2026-07-03

    8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.

    PythonLicense: MIT

    • a2a-protocol
    • ai-governance
    • finops
    • guardrails
    • mcp

    githubcreated 4 months agomeasured growthOpen source ↗

    1GitHub starsstable
15. 15

    agentops

    Agent

    DormantLast commit 4 months ago · 2026-04-13

    AgentOps: Multi-agent infrastructure remediation platform. A2A protocol, agent coordination, HITL approval, auto-rollback.

    PythonLicense: MIT

    • a2a-protocol
    • ai
    • automation
    • infrastructure
    • llm

    githubcreated 6 months agomeasured growthOpen source ↗

    0GitHub starsstable
16. 16

    AgentStack

    Agent

    ActiveLast commit 1 day ago · 2026-09-04

    Provide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.

    • a2a
    • anthropic
    • claude-code
    • crewai
    • deep-learning

    githubcreated 5 months agomeasured growthOpen source ↗

    0GitHub starsstable
17. 17

    Agent-Reliability-and-Evaluation-Lab

    MCP

    ActiveLast commit 15 days ago · 2026-08-21

    Production reliability, benchmarking, and evaluation layer for MCP agent runtimes — protocol negotiation, A2A interop, circuit breakers, connection pooling, adaptive streaming, and autoscaling, with measured throughput/latency and a…

    PythonLicense: Apache-2.0

    • a2a-protocol
    • agent-to-agent
    • ai-agents
    • async-python
    • autoscaling

    githubcreated 17 days agonewmeasured growthOpen source ↗

    3GitHub starsstable
18. 18

    opus-fable-playbook

    Skill

    ActiveLast commit 2 months ago · 2026-07-03

    Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.

    ShellLicense: MIT

    • anthropic
    • claude
    • claude-code
    • claude-code-plugin
    • evals

    githubcreated 2 months agomeasured growthOpen source ↗

    Install /plugin marketplace add rennf93/opus-fable-playbook

    34GitHub stars+1 (+3.0 %)
19. 19

    adherencia-reglas

    Skill

    ActiveLast commit 35 days ago · 2026-07-31

    Mide si tu agente de IA cumple las reglas que le escribiste. Lee el historial local de Claude Code y devuelve un porcentaje por regla. Sin instalar nada, sin red, biblioteca estándar.

    PythonLicense: MIT

    • agent-evaluation
    • ai-agents
    • claude-code
    • claude-code-skill
    • claude-code-skills

    githubcreated 40 days agomeasured growthOpen source ↗

    Install git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas

    1GitHub starsstable
20. 20

    claudestat

    Skill

    ActiveLast commit 3 days ago · 2026-09-02

    Real-time execution trace and cost intelligence for Claude Code

    TypeScriptLicense: MIT

    • agentic-workflow
    • ai-productivity
    • anthropic
    • anthropic-claude
    • claude

    githubcreated 4 months agomeasured growthOpen source ↗

    Install /plugin marketplace add DeibyGS/claudestat

    34GitHub starsstable
21. 21

    skill-receipts

    Skill

    ActiveLast commit 37 days ago · 2026-07-30

    Claude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published

    JavaScriptLicense: MIT

    • agent-skills
    • ai-agents
    • anthropic
    • benchmark
    • claude

    githubcreated 45 days agomeasured growthOpen source ↗

    Install git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts

    2GitHub starsstable
22. 22

    green-agent

    Agent

    ActiveLast commit 2 months ago · 2026-07-01

    A2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK

    Python

    • a2a-protocol
    • agentbeats
    • appworld
    • evaluation
    • llm-agents

    githubcreated 11 months agomeasured growthOpen source ↗

    0GitHub starsstable
23. 23

    bakeoff

    Skill

    ActiveLast commit 57 days ago · 2026-07-09

    Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.

    JavaScriptLicense: MIT

    • ai-agents
    • anthropic
    • claude-code
    • claude-code-plugin
    • claude-skill

    githubcreated 2 months agomeasured growthOpen source ↗

    Install /plugin marketplace add CoriChui/bakeoff

    10GitHub starsstable
24. 24

    nora

    MCP

    ActiveLast commit today · 2026-09-04

    Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

    TypeScriptLicense: Apache-2.0

    • agent-management
    • agent-ops
    • agent-orchestration
    • ai-agent-platform
    • ai-agents

    githubcreated 5 months agomeasured growthOpen source ↗

    50GitHub stars+1 (+2.0 %)
25. 25

    skill-adherencia-reglas

    Skill

    ActiveLast commit 35 days ago · 2026-07-31

    Skill instalable para Claude Code que mide si tu agente cumple las reglas establecidas. Lee el historial de sesiones de tu disco y devuelve un porcentaje por regla de cumplimiento. Sin instalar nada, sin red, biblioteca estándar.

    PythonLicense: MIT

    • ai-evaluation
    • claude
    • claude-code
    • claude-code-plugin
    • claude-code-skill

    githubcreated 39 days agomeasured growthOpen source ↗

    Install /plugin marketplace add jleonceo/skill-adherencia-reglas

    1GitHub starsstable