1380 AI tools for Claude Code ?
Syncs docs between Obsidian and your AI coding tool (Claude Code, Cursor, or Windsurf) bidirectionally in 5 minutes.
Open-source Claude Code harness for autonomous vulnerability discovery, verification, and patching of C/C++ memory bugs via ASAN and gVisor sandboxing.
Operations layer for coding agents that enforces independent validation: fresh AI contexts judge code changes with PASS/FAIL/NOT_PROVEN verdicts.
Symlinked Claude Code skill/agent toolkit for spec-driven development: spec, architect, review, canary deploy, wrapup.
Autonomous Claude Code engineering toolbelt that drives a PRD through ticket decomposition, an 8-phase build loop, and cleanup.
Claude Code plugin that structures dev sessions into task, plan, build, multi-agent review, and approval-gated PR steps.
Claude Code hooks that auto-recall memory from Qdrant/Memory KG on every prompt and write findings back at end of turn.
RavenClaude is a private Claude Code plugin marketplace shipping 184 plugins with governed multi-agent teams, specialist agents, and a comfort-posture
A control system for Claude Code that enforces one-task-at-a-time workflows with path fences, independent review, test gates, and human approval before commits.
9-phase agentic feature workflow where each phase is its own stacked PR, gated on real review approval, not Linear status.
An expert skill for building 3D web experiences with Three.js, React Three Fiber, Spline, and WebGL - configurators, portfolios, scroll-driven scenes.
Automates ActiveCampaign contacts, tags, list subscriptions, automation enrollment, and tasks through Rube MCP.
Skill that systematically works through GitHub PR review comments via the gh CLI: inspect, plan, fix, and respond.
Skill for testing and benchmarking LLM agents - behavioral testing, capability assessment, reliability metrics, and production monitoring.
Python SDK reference for building persistent Azure AI Foundry agents with function tools, hosted code/search/MCP tools, threads, and structured outputs.
Covers agent memory architecture - semantic, episodic and procedural memory, vector store selection, chunking strategies, decay, and 7 sharp edges.
Four-phase workflow for systematically improving an existing agent: baseline metrics, prompt engineering, A/B testing, and staged rollout.
A skill for profiling and optimizing multi-agent systems - coordination, throughput, cost, latency, and context-window efficiency.
Skill for designing agent tools - JSON Schema, MCP tools, error handling, and parallel execution - since the LLM only sees the schema.
An Azure DevOps MCP server that auto-switches org/project auth by directory - work items, repos, PRs, builds, and pipelines via per-repo config.
MCP server for DBLP - search academic publications with boolean or fuzzy matching, look up authors and venues, and export accurate BibTeX entries.
Gemini Bridge MCP Server lets Claude Code, Cursor, and VS Code query Google Gemini via its CLI at zero API cost.
MCP server connecting AI assistants to a Kubernetes cluster - kubectl operations, Helm charts, and node management via natural language.
Consult7 lets an AI agent offload analysis of huge file collections to a large-context model over OpenRouter, up to 2M tokens.
MCP server for Starwind UI/Pro Astro component libraries giving AI coding tools four intent-based tools for init, docs, install commands and search.
Native Claude Code plugin that orchestrates a multi-persona, cross-model-review build pipeline with no daemon or npm package.
MCP server that controls newer SharkClean/SharkNinja robot vacuums via the skegox cloud, the same backend the app uses.
Chrome DevTools MCP server letting coding agents control a live Chrome browser for performance traces, network and console debugging.
Promptfoo example running evals on the Anthropic Messages API by reusing your local Claude Code session instead of a separate API key.
57-skill Claude Code/Codex chain that runs the full dev lifecycle on a queryable Neo4j graph with evidence-blocking gates.
Pi extension that lets the model script a fan-out of isolated subagents into parallel or piped workflows with live progress.
Claude Code plugin with a shared clarify-plan-verify-review loop plus dev, data science, writing, and workshop gates.
Claude Code plugin marketplace bundling skill/plugin authoring, project-standards auditing, and assess-then-iterate triage.
Open Code Review (ocr) is Alibaba's AI code review CLI, trading some recall for high precision at about 1/9 the tokens of a general agent.
lowfat is a lightweight CLI that filters verbose shell output and file content before it reaches an AI agent, cutting token cost.
Lathe generates hands-on, multi-part technical tutorials you work through yourself in a local UI, with opt-in verification and sourced provenance.
Intent-driven multi-agent orchestration framework - say what you want, an adaptive engine plans, schedules across CLIs, executes, and verifies it.
Applies 44 independently verifiable AST patches to the official Claude Code native CLI executable, with atomic promotion and rollback.
Terminal app with real xterm.js tiles on an infinite 2D canvas and a dock, for running many agent CLIs (Claude, Codex, Grok, Pi) at once.
Self-hosted Scrum platform where AI agents and humans share a sprint board - BDD specs, System Design Docs, and in-app AI chat.
Community extension bringing Claude Code's native diff, live debugger control, Roslyn navigation, and test runner into Visual Studio 2026.
Local, read-only dashboard for Claude Code and Codex sessions - live spend, context fill, a heartbeat visualization, and phone-based approvals.
