LLM observability: tools for developers

Monitoring, traces, evaluation and quality tracking for LLM applications. An entry can appear under several use cases when its topics or description provide several explicit signals.

Use case

Activity

Sort by

117 entries in this view.

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

    Other
    Active

    Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.

    TypeScript
    • ai-agents
    • claude-code
    • claude-code-skills
    • cli
    • evals

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  2. 2

    Agent
    Active

    The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already…

    PythonLicense: Apache-2.0
    • a2a
    • agent-framework
    • ai-agents
    • ai-governance
    • ai-safety

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  3. 3

    MCP
    Active

    Vendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.

    PythonLicense: MIT
    • a2a
    • agent2agent
    • agentic-ai
    • ai-agents
    • clean-architecture

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  4. 4

    Skill
    Active

    Agent Skill that asks: should there be an agentic system at all? Then designs, builds, audits, verifies, and ports systems—from workflows to governed teams.

    PythonLicense: Apache-2.0
    • agent-skills
    • agentic-ai
    • ai-agents
    • anthropic-skills
    • antigravity

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/ingcontartese-netizen/multi-agent-system-architect-v2 ~/.claude/skills/multi-agent-system-architect-v2

    1GitHub starsstable
  5. 5

    MCP
    Active

    Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.

    Python
    • a2a-protocol
    • agentic-ai
    • auditability
    • clean-architecture
    • credit-risk

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  6. 6

    Agent
    Dormant

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

    PythonLicense: MIT
    • a2a
    • agents
    • contracts
    • evaluation
    • llm

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  7. 7

    Agent
    Active

    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

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  8. 8

    Agent
    Active

    Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.

    PythonLicense: Apache-2.0
    • a2a-protocol
    • agentic-ai
    • ai-agents
    • fastapi
    • llmops

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  9. 9

    Agent
    Active

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

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

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  10. 10

    Other
    Active

    🔑 HomeStream · 家园·流 — 零成本自托管多Agent协作框架，通往AI世界的那把钥匙 | Zero-cost self-hosted multi-agent framework — The key to AI world

    PythonLicense: MIT
    • a2a-protocol
    • agent-framework
    • ai
    • causal-memory
    • event-stream

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  11. 11

    Agent
    Dormant

    A Python proof-of-concept for tracing multi-turn Agent-to-Agent (A2A) conversations as a single unified MLflow trace for LLM observability and evaluation.

    Python
    • a2a
    • agent-to-agent
    • ai-agents
    • conversational-ai
    • llm-evaluation

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  12. 12

    MCP
    Active

    AgentGateway — independent third-party profile of a public API surface, by API Evangelist. AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to and from AI agents, LLM providers, and…

    • agent-to-agent
    • ai-gateway
    • api-gateway
    • apis-json
    • cncf

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  13. 13

    Agent
    Dormant

    OpenTelemetry semantic conventions and instrumentation for agent provenance, derivation lineage, and acceptance criteria evaluation. Fills the Microsoft AI stack observability gap.

    Python
    • a2a-protocol
    • agentic-ai
    • ai-agents
    • observability
    • opentelemetry

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  14. 14

    MCP
    Active

    Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

    PythonLicense: MIT

      mcpmeasured growthOpen source ↗

      Install claude mcp add ai-guardian -- uvx ai-guardian-aiops

      0GitHub starsstable
    • 15

      Agent
      Dormant

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

      PythonLicense: MIT
      • a2a-protocol
      • ai
      • automation
      • infrastructure
      • llm

      githubmeasured growthOpen source ↗

      0GitHub starsstable
    • 16

      Agent
      Active

      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

      githubmeasured growthOpen source ↗

      0GitHub starsstable

    Learning resources

    Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.

    1. 1

      production-ai-engineering

      Agent
      ActiveOpen source ↗

      Handbook técnico aberto sobre engenharia de IA em produção: ML tradicional, LLMs, RAG, agentes, segurança, observabilidade, FinOps e deployment.

      Markdown
      • a2a-protocol
      • agentic-ai
      • ai
      • ai-agents
      • ai-engineering
      githubResourcemeasured growth
      1GitHub starsstable