Anthropic agents

MCP server that auto-classifies prompt complexity and routes to the right Claude thinking mode

One command to configure Claude Code for any project — auto-detects your stack and installs the right MCP servers, skills, and tools via an interactive TUI.

AI-powered customer support twin for a live D2C beauty brand — built with Flask, Claude API, WATI, Instagram webhooks, Shopify, and Telegram. Handles 80% of customer DMs autonomously.

Rotate across multiple Anthropic Claude Code (Max/Pro) subscriptions — picks the account with most 5h/weekly quota headroom, writes a full-scope ~/.claude/.credentials.json, and execs the real claude. OAuth-native, alias-drop-in, no shadow dirs; Remote Control and session-scope features work out of the box.

Token-efficient context engine for AI coding agents. v2.23.0: token-killer pack — deep-forget (unlearning propagation), dangling-reference guard, MCP schemas-on-demand. 2462 tests, 43 MCP tools, Elastic-2.0.

Cognitive commitment engine with constitutional safety. Watches your messages for promises ('I'll send that Monday'), remembers them, and follows up without judgment. Goes quiet when you're depleted. Deterministic core (Patent P1) + optional Claude Opus 4.7 nuance.

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

A multi-agent equity-analysis Claude Code Dynamic Workflow — analysts → bull/bear debate → trader → risk → PM, with deterministic Markdown + HTML export. Research only, not financial advice.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

🛠 Enhance LLM prompts effortlessly with RPI, a tool for testing, improving, and managing prompts across various AI providers.

Self-hosted, provider-agnostic personal AI assistant — Web UI, CLI & messaging bots with memory, multi-agent specialists, SOPs, scheduler & live dashboard. Defaults to Claude (Opus 4.8) on your Claude Max quota via Meridian — no per-token bills.

Route Telegram topics to isolated Claude Code sessions. 107 topics, persistent memory, auto-context per conversation.

Claude Code skills I built for my own stack — Obsidian, Notion, capture/handoff, and session workflow utilities.

LLM agent pipeline that triages apartment-building maintenance messages from WhatsApp and Telegram — .NET 8, a from-scratch multi-agent orchestrator, cost-tiered Claude routing (Haiku default, Sonnet escalation), pgvector similarity search, local ONNX embeddings, and a two-layer emergency-detection guarantee.

An adversarial autonomous coding harness (GAN + anvil) — plan → generate ↔ evaluate, sprint by sprint. A Claude Code plugin.

Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buried in chat history.

Cambium turns one researcher into an institute. Forty-six named AI specialists, gathered into eleven councils, scout the ground, build the work, and verify every number, while you sign off at each of eight human gates. It assists the researcher, never replaces them. Local-first, evidence-checked, honest by design.

Reinforcement learning for multi-agent workflows — where the weights are text you can read.

Agent Skill for Claude Code & AI coding agents: a decision guide for when to delegate to subagents, parallelize agents, or orchestrate multi-agent workflows — and when to just work inline. Install via skills.sh.

Plan-first development partner for Claude Code: interview-driven plans, tier-routed agents (haiku/sonnet/opus), and an adversarial review chain that verifies through real usage.

Multi-agent orchestration CLI for Claude Code — declarative TOML workflows, autonomous agents, context-compression recovery, inter-agent mail.

CLI-based AI coding assistant using AWS Bedrock and Claude models. Features interactive mode, file context, git integration, web search, and image analysis.

Live attention router for developers running many Claude Code sessions across projects: see which one needs you now, browse history, resume, and scaffold new projects. By LaiaDesk.

MCP Server for Arvo AI Personal Trainer - Connect Claude Desktop to your training data

Comande um agente Claude pelo WhatsApp — Express + Agent SDK, fila por conversa, sessão por chat, allowlist e dedupe de webhook

AI commit messages from your staged diff in VS Code. Runs the official Claude CLI on your subscription — no API key, no telemetry.

FastMCP server for Apollo.io — 22 tools: sequences, campaign health, mailbox warmup, enrichment, CRM, credits. Includes Cloudflare bypass and undocumented API discoveries.

Automated setup script for essential development tools (Claude Code CLI, GitHub CLI, Tailscale, Doppler) - Perfect for VPS, cloud instances, Github codespaces or any new machines. Spin up new development ready machines in seconds!

A beautiful Claude Code statusline with live progress bars for context, rate limits, and cost, plus model-aware accents, rich git, PR status, and a session reminder. Single Bash script, Linux, no Nerd Font required.

MCP server for AskClaude — pay-per-query Claude AI via x402 micropayments

Battle-tested Claude Code commands, hooks, and skills forged from real-world enterprise operations. Built around hard-won expertise in high-traffic, large-scale data streaming environments — not another beginner-friendly productivity wrapper.

让 Claude Code 在科大讯飞 Anthropic 端点上正常工作的轻量透明代理(thinking 思维链 + WebSearch 网络搜索适配)

Reduce token use and enable persistent memory for Claude Code, boosting efficiency in solo or team agent setups.

Export and import browser cookies securely using AES-GCM encryption for seamless session migration across devices without third-party servers.

Write, review and improve SwiftUI: state, composition, performance, animations, accessibility and iOS 26 Liquid Glass - Agent Skill

AI-native CRM as MCP Server — 37 tools for contact management, pipeline, leads, follow-ups, health scores, revenue analytics, CSV import/export, GDPR (Art. 15/17). The only production-ready standalone MCP CRM. Free tier. OAuth 2.1. Hosted at crm.studiomeyer.io

MCP servers connecting Claude to Lawmatics, DecisionVault and WealthCounsel. Read and update your CRM, client intake and matters by asking, inside Claude Code. Runs locally so privileged client data never leaves your machine. Built by Irfad Imtiaz at My Legal Academy.

Public MCP server for Landed: search AI-native jobs, prepare applications, and get interview prep from Claude, Cursor, VS Code, and any Model Context Protocol client.

Context Layering & Engineering for Agentic Resources — Persistent memory, intelligent context, and structured project management for Claude Code

Fleet manager for Claude Code: one manager session spawns, steers, and monitors many durable headless Claude Code agent sessions in parallel across projects. Mid-turn steering, token budgets, usage-limit park/resume, journals + respawn, git-tracked knowledge loop. Single-file stdlib-only Python CLI. No daemon, no deps.

Self-healing agent runtime. PCEC engine + Gene Map persistent memory + AMP multi-agent protocol. The operating system for AI agents.

265 autonomous AI agents across 15 business domains. Full-stack SaaS framework with real model routing, RAG pipeline, guardrails, and Chrome extension. FastAPI + Next.js + K3s. Runs on any server. $0/month software cost.

Claude Code for JetBrains IDEs — a native GUI client for Anthropic's AI coding agent. Streaming chat, editable IDE diffs, MCP and a deterministic security layer. IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider. No Node.js at runtime.

MCP server that turns Claude into an Ashby ATS copilot — re-engagement campaigns, deep pipeline reports, historical narratives, and personalized outreach.

Extract specific projects from Claude.ai data exports — interactive project picker, knowledge docs, conversation history, Claude Code skill

Self-hosted MCP gateway that turns any REST, GraphQL, or MCP server into secure, governed AI tools — OpenAPI auto-discovery, per-tool guardrails, RBAC, circuit breaking, and a real admin UI.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

Free Claude Skill that rewrites any text into ElevenLabs V3-optimized scripts — audio tags, pacing, phonetic respelling & acronym/number normalization for better AI voice synthesis.

One command sets up Claude Code (and any AI coding agent) on a Laravel project: engineering rules, a quality gate (PHPStan · Pint · Pest), skills, git hooks, and stack-aware frontend tooling.

An open source AI PR reviewer built from many narrow lenses and one careful curator

MCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.

An engineering process for Claude Code projects: plan, review, record. The commit gate is a git hook, so it isn't optional.

Ralph Wiggum loop starter kit for Claude Code: a fresh-context autonomous build loop with stop conditions, guardrails, and spec/plan scaffolding.

Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a CLI or MCP server.

Claude Code skills for LibreChat administration and configuration

AI assistant that answers Instagram DMs in your own voice, qualifies leads, and quotes from your rate card. Built on the Instagram Messaging API and Claude.

Run your own agent org: talk to an orchestrator, it hires & supervises worker agents you can watch and steer. Self-hosted; pluggable surfaces (Telegram, Web, VS Code) and agent backends (Claude Code, Codex).

Three hooks that fix Claude Code's attention drift. Cited research, one-line install.

Some Skills for Claudius

Handoff-first protocol for coordinating Codex, Claude Code, Gemini/Antigravity CLI & Grok Build agents on shared repos. AGENT_HANDOFF.md as source of truth, with file ownership, anti-overwrite guardrails and validation scripts. For multi-agent teams and single-agent sessions across runs.

Proactive context synthesis for AI coding agents. Build the right context before the first token.

Drop-in MCP server that records real per-session agent cost/token/tool metrics and renders a Context Window Explorer over an actual MCP handshake

Governance harness for decision-making systems with structured review, epistemic honesty, and retrospective calibration.

A cross-harness, pure-skill implementation of the Fable 5 orchestrator pattern proposed by Anthropic — your agent as the boss; Codex, Cursor, and any headless coding agent as the crew.

A small, hackable multi-agent dashboard built directly on Anthropic's Claude Agent SDK. Educational reference, not a product.

Run Claude Code agents on your own VPS. A web manager spins up sandboxed Docker sessions with Remote Control, a built-in web terminal and GitHub OAuth, backed by Claude, DeepSeek or any Anthropic-compatible model.

One-command interactive switcher for Claude Code between Ollama Cloud (Free + Pro/Max), Claude, GLM Coding Plan (z.ai), Kimi Code (Moonshot), MiniMax, Xiaomi MiMo, DeepSeek API, and Amazon Bedrock. Auto-detects dependencies, prompts for API keys, launches Claude Code with the selected provider.

Aegis — Self-healing incident-response agent (LangGraph, sandboxed fault-replay verification, deterministic policy gate, HITL, evals)

A Windows 11 computer-control agent that gets its own desktop and its own cursor — so it works while you keep using yours. Claude computer-use + PySide6.

Skills that know your codebase. Repo-grounded, contract-validated, agent-routable.

Graph engineering for Claude Code: /graph turns any goal into a DAG of specialist subagents with JSON-schema hand-offs, executed, adversarially verified, and replayable as a persistent goal graph.

A self-improving harness for any LLM, in one Rust binary. Persistent Lua REPL as the single tool, three-level memory, persistent sub-agents, enforced budgets, external verification, per-process sandbox, and post-run reflection over its own store. Built from the YC Harness Club talks.

Personal always-on macOS AI assistant in the shape of the Iron Man HUD — native Swift brain, R3F particle-ring face, voice-first, locally-grounded.

Six patterns for working with AI agents: multi-agent, agentic workflows, Claude Code. Traps and cost of each. ES + EN · Seis patrones para trabajar con agentes de IA

Parallel multi-agent skills for Claude Code — review, research, investigate, and implement with concurrent specialized agents

Multi-agent fleet fabric on top of Hermes — A2A protocol + NATS event bus + Temporal durable workflows + Tier 2 VPS spawning. Run a fleet of specialist agents from one Telegram bot.

面向应用开发的声明式 agent 服务开发框架：装饰器 + DI 声明四类能力，主 agent 编排执行；每次 run 产出结构化结果与可观测调用树（trace、成本、指标），交付可直接上线的服务。

A self-hosted AI assistant that can rewrite its own code — Claude Code CLI behind a chat UI, with crons, webhooks, connectors and generated apps.

Claude Code skill — guided interview that recommends AI skills for your repo or team. Install with one prompt.

Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment

Benchmark AI code generation speed and cost across 13 programming languages using Claude Code for clear, data-driven language comparison.

An automated AI research-code writer and AI research-paper writer implementation through a skills+ autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

Build Claude senior engineer skills for debugging, refactoring, optimization, hardening, and code review in Claude Code workflows

Plan-first AI agent orchestration with persistent memory, parallel DAG execution, and an extensible skills system. Small enough to audit. Powerful enough to orchestrate.

LaunchIQ: AI-powered product launch intelligence with a multi-agent pipeline (market intel, personas, strategy, content).

Multi-agent research pipeline for Claude Code — web crawl, knowledge graph, synthesis, and citation-rich reports via slash commands.

Opinionated Claude Code setup for managing 10+ apps with multi-agent orchestration

Seven AI agents argue about your strategic question until they converge on an answer no single agent could reach.

Orchestrate multiple agents to execute Claude Code workflows with cross-model verification for reliable AI code automation.

Cognitive infrastructure for AI agents

v4.1 Opus 4.7 native prompt meta-compiler — skill-level meta-refinement, automatic ROSETTA via 5 hooks, Jarvis v3.0 overhaul (3-obs threshold, awareness cards), micro-task methodology. dual-layer memory, Buffer-of-Thoughts + Meta-Reasoner bandit, 125+ scientific papers. Claude Code plugin.

🧠 Enhance Claude AI context retention by optimizing prompt efficiency and enabling seamless session handoff for consistent memory across interactions

YAML-driven multi-agent orchestration with cross-pollination across AI providers. Built to pair with Claude Code.

Telegram-first All-in-One Unraid container for NanoClaw. Runs Claude-powered agents in isolated Docker containers using the official Telegram fork and native credential proxy patch, with persistent runtime state under /appdata and safer upgrades than mounting the full project tree.

Production multi-agent system running real marketing operations — 6 specialized AI agents for daily intelligence gathering, content creation, and publishing. Includes scheduling engine, scan pipelines, knowledge base, and operational dashboard. 16k lines, zero external dependencies.

Per-agent diff review for Claude Code parallel subagent workflows. Each subagent worktree captured automatically, tabbed TUI to approve, revert, or merge each one independently.

🧩 Orchestrate multi-agent research with parallel execution and audits for efficient, structured investigations and seamless workflow planning.

Portable multi-chat sprint orchestration skill for Claude Code. Validated in 17+ production sprints.

Project-agnostic Claude Code / multi-agent skills, slash commands, and CLAUDE.md template — extracted from a real Next.js + Supabase production codebase.