#anthropic

Validate API keys, list their models and capabilities, and make normalized calls, all through one interface.

Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse management, semantic versioning, and productivity workflows

LLM facade for the Stapel framework: provider-swappable completions & translation, prompt ledger with token accounting

Multi-account proxy for Claude Code with adaptive, rate-aware load balancing

Cyclomatic complexity, but for LLM prompts. Static analysis that finds the business logic hidden in your prompts, scores it, and gates it in CI. Python, TypeScript, JavaScript, PHP.

Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.

Scriptable, multi-provider AI agent for the terminal — pipe into it, script it, run it on any model, cloud or local

Agents that plan, don't react. The model writes a typed plan once. The runtime runs it. Tool outputs never go back through the model — so your agent can't be prompt-injected through its tools, costs a fraction, and runs the same every time.

knowmind — CLI + MCP-Server für das Gedächtnis Ihrer KI (knowmind.de). npx -y knowmind mcp

Local cockpit for Claude Code CLI sessions — schedule routines, monitor token budget, manage long-running plans

jeopi — Encode intention. Decode software. The oh-my-pi engine fused with jeo-code's spec-first discipline.

AI-powered git history CLI + GitHub Action: PR risk-scored reviews, changelogs, multi-repo digests

No repository description published.

Keyless-first MCP server — 150 tools for US federal + state/local (SLED) government contracting, spending, regulation & partner vetting. SAM.gov, USAspending, Grants.gov, OFAC, FDIC, EPA, CourtListener + 45 more. No API key. Honesty-hardened.

@codeproxy/core is a zero-dependency TypeScript library that converts upstream LLM responses in Chat Completions or Anthropic Messages format into the OpenAI Responses API format, so that AI coding agents like Codex and Claude Code can work with any language model.

Intelligent, self-configuring setup for Claude Code 👉 npx claude-code-autoconfig

No repository description published.

Audit your Claude Code token and cost spend and monitor what your agents are doing.

MindTrial: Evaluate and compare AI language models (LLMs) on text-based tasks with optional file/image attachments and tool use. Supports multiple providers (OpenAI, Google, Anthropic, DeepSeek, Mistral AI, xAI, Alibaba, Moonshot AI, OpenRouter), custom tasks in YAML, and HTML/CSV/JSON reports.

Custom Telegram MCP server + TUI auto-responder for Claude Code — 10 MCP tools, SQLite message store, access control, reaction support

All-in-one engineering workflow & knowledge engine for Claude Code. One-command install, runs standalone (Node >=18, no bun). L0-L3 task classification, 13 runtime invariants, code review, browser QA, security audit, and a deduplicated knowledge base that compounds across tasks.

PHP LLM client with support for cache, tools and async requests

Sync Claude Code sessions across devices using Cloudflare R2 with end-to-end encryption

An unofficial C#/.NET SDK for accessing the Anthropic Claude API. This package is not affiliated with, endorsed by, or sponsored by Anthropic. Anthropic and Claude are trademarks of Anthropic, PBC.

🔁 Finishes your entire backlog while you sleep. The AI orchestrator that DOES the work end-to-end on ANY LLM — discover → implement → verify → merge → 24/7 — behind safety gates, at up to 90% fewer tokens. 48 extension points. Not a chatbot. A worker.

Skills and Agents Orchestrator workflow for Software Development

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

MCP Server for YouTube API, enabling video management, Shorts creation, and advanced analytics

Identity-scoped schema selection for text-to-SQL: give the model only the tables this caller may read, and 75% fewer prompt tokens.

GCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.