#claude-code

Cryptographically-authenticated, cross-machine agent-to-agent chat for Claude Code, over MCP

该仓库未发布描述。

Go SDK for Claude Agent

该仓库未发布描述。

该仓库未发布描述。

A plan-file factory for Claude Code — and the console that watches it run. Engine: parallel headless workers in git worktrees, script-owned gates, unattended drive loop (TypeScript, zero deps). Console: live web observability over driven repos.

Keep Claude Code's Remote Control and Artifacts on one account while inference follows cswap's account swap. Companion package for claude-swap[pin].

See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.

Agent Squad for Requirements Engineering — 33 Specialists with System 2 Reflection, BM25+ Knowledge Engine (831 entries), Mermaid Diagramming, Jira + Confluence Integration. Runs on Antigravity IDE, Claude Code, Claude CoWork.

Verifiable sports trading workbench for the TxLINE / TxODDS World Cup hackathon. Backtest, signal, and verify on Solana. Free tier, on-chain proof-anchored.

🚀 Browser automation CLI with autonomous loop execution. Control Chrome via CDP, run YAML tasks, Ralph Wiggum loops.

TraceOn is an MCP server that Claude Code calls after editing code to verify the change actually works end-to-end. It runs a Playwright test the agent wrote, correlates browser evidence with backend traces and logs via OpenTelemetry, ranks the evidence into a compact packet, and returns a structured VerificationResult that the agent reasons over.

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

The Makefile of agent orchestration. Terminal agent coordination without the framework tax. No Python. No cloud. No magic. Just tmux, TOML, and a binary.

Lightweight HTML-to-Markdown parser for AI agent workflows — Python CLI and API around a fast Go engine, available on PyPI.

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted, no vendor lock-in. ( 55x faster than litellm )

Pairling for Mac — public payload mirror and npm publish pipeline for the `pairling` package (pairling.dev)

AI Agent Skill for NSAuditor AI — gives any AI coding agent built-in knowledge of NSAuditor's MCP tools, schemas, plugins, and security audit workflows. Works with Claude Code, Cursor, Windsurf, and any MCP-aware agent.

Orchestration system for long-running complex agent tasks

SeamShield Community CLI: local-first access-lane scanning for AI-built apps

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

Cross-node session migration and S3 backup for Claude Code.

What would your AI coding subscription cost at API prices? npx tokmax reads your local usage logs and puts your number on a public leaderboard. Only aggregates leave your machine.

Lizard Studio — Claude Code side panel Chrome extension

该仓库未发布描述。

Small, single-purpose, open-source tools that catch the recurring failure modes of AI coding agents (Claude Code, Cursor, Codex, Gemini CLI) — no accounts, no backend, no billing.

Turn any codebase into a structured knowledge graph for AI agents.

An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

Sync AI-agent configuration from one .ai directory to Claude Code, Codex, and Kiro.

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