#anthropic

Claude Code skills plugin for Git, GitHub, and skill authoring workflows

Опис репозиторію не опубліковано.

Unified LLM client library for Go - one API, 36 providers (Anthropic, OpenAI, Google Gemini, AWS Bedrock, Mistral, Groq, DeepSeek, +29 more), zero external dependencies.

Switch Claude Code's backend per terminal — one command, no global config.

Python SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and settlement.

Free self-hosted OSINT investigator's toolkit. Sixteen investigation tools in one interface: crypto tracing, phishing fingerprinting, domain intel, Telegram OSINT, IP reputation, email header forensics with LLM scam detection, username enumeration, HIBP breach checks, ransomware victim tracking. AGPL-3.0.

Cost tracking for Claude Code Pro & Max users

Simple tool to check AI sub limits

Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.

Опис репозиторію не опубліковано.

Autonomous coding-agent task runner — queue work and Lea runs it headlessly with Claude Code or Codex the moment your limit resets. Menu-bar app on macOS, a real windowed app on Windows/Linux. MIT.

Go port of pxpipe core - cut Claude Code token usage by rendering text context as images

Опис репозиторію не опубліковано.

⚡ Turn your Kiro subscription (Amazon Q Developer / AWS CodeWhisperer) into OpenAI- and Anthropic-compatible APIs. Use Claude, GPT, Qwen and GLM models from Cursor, Claude Code, Cline, Zed and Aider. One static Go binary, zero dependencies.

Local MCP server + Claude plugin for read-only Codex code reviews on your machine — an edit → review → edit loop from Claude Desktop.

n8n node for Claude Code SDK integration with MCP support

TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and settlement.

Опис репозиторію не опубліковано.

An AI agent that builds, validates & secures Terraform — with a policy-as-code guard it can't bypass. Built from scratch on the Anthropic API.

top, for coding agents — a live terminal dashboard for Claude Code sessions: spend, tool activity, risk detectors, and opt-in pause/kill. 100% local.

Give Claude Code sessions human-memorable aliases — cross-project list and one-shot resume, single Go binary.

This CleanCodeJN package streamlines the development of web APIs in .NET applications by providing a robust framework for CRUD operations and facilitating the implementation of complex business logic in a clean and maintainable manner.

The agent harness you can read, replay, and rewind. One Effect boundary, five superpowers: deterministic replay, fork-at-any-turn, bisect, free CI tests, cost accounting.

Felix — single-binary AI agent gateway. Multi-provider LLM, persistent memory, MCP client, runs entirely on your hardware

Python port of pi-mono: fully-aligned coding agent with TUI, ai, agent, and coding-agent packages

Опис репозиторію не опубліковано.

🧬 ModelMix - Unified API for Diverse AI Language Models.

Capability-driven autonomous project execution engine. Iterates an Operator loop over a goal, dispatching modular capabilities (Architect, CodeGenerator, TestRunner, BugFixer, etc.) until the project reaches a desired artifact state. No LangGraph dependency — designed as a standalone Layer 2 that antcrew (Layer 1) builds on top of.

Regression tests and quality gates for LLM/RAG pipelines — catch answer quality drops, latency regressions, and cost jumps in CI. Single Go binary.

llm-route