开源AI工作流:Pup 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Pup是一个开源的AI工作流,提供了200+命令,支持33+Datadog功能,帮助您更好地管理和观察您的AI系统。
开源AI工作流:Pup 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Pup是一个开源的AI工作流,提供了200+命令,支持33+Datadog功能,帮助您更好地管理和观察您的AI系统。
开源AI工作流:Pup 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:cargo install(推荐) cargo install pup # 方式二:从源码编译 git clone https://github.com/DataDog/pup cd pup cargo build --release # 二进制在 ./target/release/pup
# 查看帮助 pup --help # 基本运行 pup [options] <input> # 详细使用说明请查阅文档 # https://github.com/DataDog/pup
# pup 配置说明 # 查看配置选项 pup --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export PUP_CONFIG="/path/to/config.yml"
Every AI agent needs a loyal companion. Meet Pup — the CLI that gives your agents full access to Datadog's observability platform (because even autonomous agents need good tooling, not just tricks).
pup (Datadog commands), shell, http, datadog-workflow, confirm{{VAR_NAME}} in any field, passed via --arg KEY=VALUE_templates/ and reference them with template: <name>body, headers, content_type, and body_fileon_failure: fail|warn|ignore and optional: true per stepwhen: on_success|on_failure|alwayspoll.interval, poll.timeout, poll.until for long-running operationscapture: VAR_NAME stores stdout for use in later stepsSee docs/examples/runbooks/ for ready-to-use examples and docs/EXAMPLES.md for full reference.
pup runbooks run deploy-service --arg SERVICE=payments --arg VERSION=1.2.3
git clone https://github.com/DataDog/pup.git && cd pup
cargo build --release
cp target/release/pup /usr/local/bin/pup
```bash
rustup target add wasm32-wasip2
cargo build --target wasm32-wasip2 --no-default-features --features wasi --release ```
pup skills install
pup skills install claude pup skills install cursor pup skills install codex pup skills install opencode pup skills install pi
pup skills install all
pup skills install claude --project
pup skills install claude --name dd-monitors
For Claude Code, skills install to `~/.claude/skills/` (or `.claude/skills/` with `--project`) and agents install to `~/.claude/agents/` (native subagent format). For Cursor, Codex, and opencode, everything installs as `SKILL.md` under that tool's skills directory (e.g. `~/.cursor/skills/`, `~/.codex/skills/`, `~/.config/opencode/skills/`).
Pup ships plugin manifest files for several AI coding assistants:
cargo build --release
rustup target add wasm32-wasip2 cargo build --target wasm32-wasip2 --no-default-features --features wasi
cargo run -- monitors list ```
pup auth login --site datadoghq.eu DD_SITE=datadoghq.eu pup monitors list
DD_ACCESS_TOKEN: Bearer token for stateless auth (highest priority)DD_API_KEY: Datadog API key (optional if using OAuth2 or DD_ACCESS_TOKEN)DD_APP_KEY: Datadog Application key (optional if using OAuth2 or DD_ACCESS_TOKEN)DD_SITE: Datadog site (default: datadoghq.com)DD_AUTO_APPROVE: Auto-approve destructive operations (true/false)DD_TOKEN_STORAGE: Token storage backend (keychain or file, default: auto-detect)FORCE_AGENT_MODE=1 pup monitors list ```
If you are integrating pup into an AI agent workflow, make sure the appropriate environment variable is set so responses are optimized for your agent. Without it, pup defaults to human-friendly output.
DD_ACCESS_TOKEN="your-token" DD_SITE="datadoghq.com" wasmtime run target/wasm32-wasip2/release/pup.wasm -- monitors list
DD_API_KEY="your-api-key" DD_APP_KEY="your-app-key" wasmtime run target/wasm32-wasip2/release/pup.wasm -- monitors list ```
The pup auth status command works in WASM and reports which credentials are configured. The login, logout, and refresh subcommands return guidance to use DD_ACCESS_TOKEN.
Pup covers most major Datadog product surfaces. See docs/COMMANDS.md for the canonical command reference, or run pup --help (or pup agent schema for machine-readable output) for the live list of commands as built.
💡 Tip: Use Ctrl/Cmd+F to search for specific APIs. Request features via GitHub Issues.
---
<details> <summary><b>📊 Core Observability</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Metrics | ✅ | metrics search, metrics query, metrics list, metrics get | V1 and V2 APIs supported |
| Logs | ✅ | logs search, logs list, logs aggregate | V1 and V2 APIs supported |
| Events | ✅ | events list, events search, events get | Infrastructure event management |
| RUM | ✅ | rum apps, rum sessions, rum metrics, rum retention-filters, rum playlists, rum heatmaps | Apps, sessions, metrics, retention filters, replay playlists, heatmaps |
| APM Services | ✅ | apm services, apm entities, apm dependencies, apm flow-map | Services stats, operations, resources; entity queries; dependencies; flow visualization |
| Traces | ✅ | traces search, traces aggregate, traces metrics | Span search/aggregation and span-based metric definitions |
| Profiling | ⏳ | profiling | Not supported in pup yet. Use the Datadog MCP server: https://docs.datadoghq.com/bits_ai/mcp_server. Enable with: https://mcp.datadoghq.com/api/unstable/mcp-server/mcp?toolsets=core,profiling |
| Database Monitoring | ✅ | dbm samples search | DBM query sample search |
| Session Replay | ❌ | - | Not yet implemented |
</details>
<details> <summary><b>🔔 Monitoring & Alerting</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Monitors | ✅ | monitors list, monitors get, monitors delete, monitors search | Full CRUD support with advanced search |
| Dashboards | ✅ | dashboards list, dashboards get, dashboards delete, dashboards url | Full management capabilities |
| SLOs | ✅ | slos list, slos get, slos delete, slos status | Full CRUD plus V2 status query |
| Synthetics | ✅ | synthetics tests, synthetics locations, synthetics suites | Tests, locations, and V2 suites management |
| Downtimes | ✅ | downtime list, downtime get, downtime cancel | Full downtime management |
| Notebooks | ✅ | notebooks list, notebooks get, notebooks delete | Investigation notebooks supported |
| Status Pages | ✅ | status-pages pages, status-pages components, status-pages degradations | **New** — Pages, components, and degradation management |
| Powerpacks | ❌ | - | Not yet implemented |
| Workflow Automation | ✅ | workflows get, workflows create, workflows update, workflows delete, workflows run, workflows instances | Full CRUD plus run and instance management (list, get, cancel) |
| Local Runbooks | ✅ | runbooks list, runbooks describe, runbooks run, runbooks import, runbooks validate | **New** — YAML-defined multi-step runbooks with pup/shell/http/workflow step types, variable interpolation, and reusable templates |
</details>
<details> <summary><b>🔒 Security & Compliance</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Security Monitoring | ✅ | security rules, security signals, security findings, security content-packs, security risk-scores | Rules, signals, findings, content packs, entity risk scores |
| Cloud Security | ✅ | security findings analyze, security findings schema | DDSQL analytics for misconfigurations, identity risks, and all Cloud Security finding types |
| Application Security | ✅ | security findings analyze, security asm-custom-rules, security asm-exclusions | API findings via DDSQL, WAF custom rules and exclusion filters |
| Static Analysis | ✅ | static-analysis ast, static-analysis custom-rulesets, static-analysis sca, static-analysis coverage | Code security analysis |
| Audit Logs | ✅ | audit-logs list, audit-logs search | Full audit log search and listing |
| Data Governance | ✅ | data-governance scanner-rules list | Sensitive data scanner rules |
| CSM Threats | ✅ | csm-threats | Cloud Security Management threat rules and agent rules |
| Sensitive Data Scanner | ✅ | data-governance scanner-rules list | Listed via Data Governance row above |
| Agentless Scanning | ✅ | agentless-scanning aws list/get/create/update/delete, agentless-scanning gcp list, agentless-scanning azure list | Cloud agentless scanning configuration for AWS, GCP, and Azure |
| Logs Restriction | ✅ | logs-restriction list, logs-restriction get, logs-restriction create, logs-restriction update, logs-restriction delete | Log restriction queries for fine-grained log access control |
| Data Deletion | ✅ | data-deletion requests list, data-deletion requests create, data-deletion requests cancel | GDPR/compliance data deletion request management |
</details>
<details> <summary><b>☁️ Infrastructure & Cloud</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Infrastructure | ✅ | infrastructure hosts list, infrastructure hosts get | Host inventory management |
| Tags | ✅ | tags list, tags get, tags add, tags update, tags delete | Host tag operations |
| Network | ✅ | network flows list, network devices, network interfaces | Network flows, device inventory, interface tags |
| Cloud (AWS) | ✅ | cloud aws list, cloud aws cloud-auth persona-mappings | AWS integration management with persona mapping CRUD |
| Cloud (GCP) | ✅ | cloud gcp list | GCP integration management |
| Cloud (Azure) | ✅ | cloud azure list | Azure integration management |
| Cloud (OCI) | ✅ | cloud oci | Oracle Cloud tenancy configs and products |
| Containers | ✅ | containers list, containers images list | Containers |
| Processes | ✅ | processes list | Process inventory query |
</details>
<details> <summary><b>🚨 Incident & Operations</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Incidents | ✅ | incidents list, incidents get, incidents attachments, incidents settings, incidents handles, incidents postmortem-templates | Incident management with settings, handles, and postmortem templates |
| On-Call (Teams) | ✅ | on-call teams (CRUD, memberships with roles) | Full team management system with admin/member roles |
| Case Management | ✅ | cases (create, search, assign, archive, projects, jira, servicenow, move) | Complete case management with Jira/ServiceNow linking |
| Error Tracking | ✅ | error-tracking issues search, error-tracking issues get | Error issue search and details |
| Service Catalog | ✅ | service-catalog list, service-catalog get | Service registry management |
| Scorecards | ✅ | scorecards list, scorecards get | Service quality scores |
| Fleet Automation | ✅ | fleet agents, fleet deployments, fleet schedules | Agent management, deployments, schedules (Preview) |
| HAMR | ✅ | hamr connections get, hamr connections create | **New** — High Availability Multi-Region connections |
| Investigations | ✅ | investigations list, investigations get, investigations trigger | Bits AI SRE investigation management |
| Change Management | ✅ | change-management create, change-management get, change-management update, change-management create-branch, change-management decisions | Change request management with decisions and branching |
| Incident Services/Teams | ✅ | incidents services, incidents teams | Service and team CRUD scoped to incident management |
| Live Debugger | ✅ | debugger probes list, debugger probes get, debugger probes create, debugger probes delete, debugger probes watch | Remote log probe management for Live Debugger |
| Software Catalog | ✅ | software-catalog entities list, software-catalog entities upsert, software-catalog kinds list, software-catalog relations list | Software Catalog entity and kind management (next-gen catalog) |
</details>
<details> <summary><b>🔧 CI/CD & Development</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| CI Visibility | ✅ | cicd pipelines list, cicd events list | CI/CD pipeline visibility and events |
| Test Optimization | ✅ | cicd tests, cicd flaky-tests, test-optimization | Test events, flaky test management, and Test Optimization API |
| DORA Metrics | ✅ | cicd dora | DORA deployment patching |
| Code Coverage | ✅ | code-coverage branch-summary, code-coverage commit-summary | Branch and commit-level coverage summaries |
| Deployment Gates | ✅ | deployment-gates gates, deployment-gates evaluations, deployment-gates rules | Deployment gate CRUD, evaluation triggers, and rule management |
</details>
<details> <summary><b>👥 Organization & Access</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Users | ✅ | users list, users get, users roles, users seats | User and role management with seat assignment |
| Organizations | ✅ | organizations get, organizations list | Organization settings management |
| API Keys | ✅ | api-keys list, api-keys get, api-keys create, api-keys delete | Full API key CRUD |
| App Keys | ✅ | app-keys list, app-keys get, app-keys create, app-keys update, app-keys delete | Full application key CRUD |
| Service Accounts | ✅ | - | Managed via users commands |
| Roles | ❌ | - | Only list via users |
| AuthN Mappings | ✅ | authn-mappings list, authn-mappings get, authn-mappings create, authn-mappings update, authn-mappings delete | SAML/IdP attribute-to-role authentication mappings |
</details>
<details> <summary><b>⚙️ Platform & Configuration</b></summary>
| API Domain | Status | Pup Commands | Notes |
|---|---|---|---|
| Usage Metering | ✅ | usage summary, usage hourly | Usage and billing metrics |
| Cost Management | ✅ | costs datadog projected, costs datadog attribution, costs datadog by-org, costs datadog aws-config, costs datadog azure-config, costs datadog gcp-config, costs ccm custom-costs, costs ccm tag-descriptions, costs ccm tag-metadata, costs ccm tags, costs ccm tag-keys, costs ccm budgets, costs ccm commitments | Cost attribution, cloud cost configs (AWS/Azure/GCP), and Cloud Cost Management (custom costs, tag descriptions, budgets, commitment programs) |
| Product Analytics | ✅ | product-analytics events send, product-analytics query | Server-side product analytics events and queries |
| Integrations | ✅ | integrations slack, integrations pagerduty, integrations webhooks, integrations jira, integrations servicenow, integrations google-chat, integrations ms-teams | Third-party integrations including Jira, ServiceNow, Google Chat, and Microsoft Teams |
| Feature Flags | ✅ | feature-flags flags, feature-flags environments, feature-flags allocations, feature-flags exposure, feature-flags enable, feature-flags disable | Feature flag management with environment, allocation, and exposure control |
| Data Streams (Kafka) | ✅ | kafka topic-configs, kafka broker-configs, kafka client-configs, kafka read-messages | **Experimental** — Kafka cluster inspection via Datadog |
| Restricted Datasets | ✅ | datasets list, datasets get, datasets create, datasets update, datasets delete | Restricted dataset management for data access control |
| Observability Pipelines | ✅ | obs-pipelines list, obs-pipelines get, obs-pipelines create, obs-pipelines update, obs-pipelines delete, obs-pipelines validate | Full pipeline CRUD and validation |
| LLM Observability | ✅ | llm-obs projects, llm-obs experiments, llm-obs datasets | **New** — LLM Obs projects, experiments, and dataset management |
| Reference Tables | ✅ | reference-tables list, reference-tables get, reference-tables create, reference-tables batch-query | **New** — Reference table management for log enrichment |
| Miscellaneous | ✅ | misc ip-ranges, misc status | IP ranges and status |
| App Builder | ✅ | app-builder list, app-builder get, app-builder create, app-builder update, app-builder delete, app-builder publish | Low-code app management with publish/unpublish and batch delete |
| Key Management | ✅ | api-keys, app-keys | API key and application key CRUD (listed in Organization & Access above) |
| IP Allowlist | ❌ | - | Not yet implemented |
</details>
If OAuth2 tokens are not available, Pup automatically falls back to API key authentication.
```bash export DD_API_KEY="your-datadog-api-key" export DD_APP_KEY="your-datadog-application-key" export DD_SITE="datadoghq.com" # Optional, defaults to datadoghq.com
pup monitors list ```
pup metrics search --query="avg:system.cpu.user{*}" --from="1h"
pup metrics query --query="avg:system.cpu.user{*}" --from="1h"
wasmtime run --env DD_API_KEY="key" --env DD_APP_KEY="key" target/wasm32-wasip2/release/pup.wasm -- --help ```
```
Pup是一个非常有用的AI工作流工具,提供了丰富的命令和功能,帮助开发者更好地管理和观察AI系统。然而,需要进一步优化和完善。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,开源AI工作流:Pup 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | pup |
| Topics | workflowcliclientdatadogobservability |
| GitHub | https://github.com/DataDog/pup |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-23 · 更新时间:2026-05-23 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端