Turnkey observability for AI coding agents - captures sessions and exports to Datadog LLM Observability
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Trajectory is Datadog's observability tooling for AI coding agents.
This repository contains:
bash <(curl -fsSL https://raw.githubusercontent.com/datadog-labs/trajectory/main/install.sh)
The installer downloads the latest Trajectory release asset for your platform, installs it under ~/.trajectory/bin/trajectory, runs trajectory setup, and registers detected coding-agent plugins.
To upgrade an install from this repository, rerun the installer.
Release assets are expected to use this naming convention:
trajectory-darwin-amd64
trajectory-darwin-arm64
trajectory-darwin-universal
trajectory-linux-amd64
trajectory-linux-arm64
trajectory-windows-amd64.exe
trajectory-windows-arm64.exe
Trajectory supports:
See docs/SUPPORTED-CLIENTS.md for version requirements and docs/CLIENT-INSTRUMENTATION.md for the per-client hook, MCP, watcher, and backfill surfaces.
.agents/plugins/ Codex marketplace metadata
.claude-plugin/ Claude marketplace metadata
commands/ Gemini command assets
docs/ Public user documentation
plugin/trajectory/ Claude Code plugin
plugin/trajectory-codex/ Codex plugin
plugin/trajectory-gemini/ Gemini context assets
plugin/trajectory-pi/ Pi extension
plugin/trajectory-opencode/ OpenCode plugin
skills/ Shared skill assets
RELEASES.json Release-channel selector
install.sh Installer
This repository accepts changes to public docs, marketplace metadata, plugin assets, and installer scaffolding.
Run the scaffold validation before opening a PR:
bash scripts/validate-scaffold.sh
Apache-2.0. See LICENSE, NOTICE, and LICENSE-3rdparty.csv.
npx claudepluginhub datadog-labs/trajectory --plugin trajectoryUse Datadog directly in Claude Code through a preconfigured Datadog MCP server. Query logs, metrics, traces, dashboards, and more through natural conversation. This plugin is in preview.
datadog-labsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
JeffallanIntelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
markus41Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
OthmanAdiAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
fFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
anthropicsProduction-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
addyosmani