#claude-code

Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.

A local proxy that aggregates usage across your Codex and Claude Code accounts — with live token-throughput analytics.

Terminal dashboard for Claude Code, zero config, track all sessions, switch context instantly, never lose track of what's running

Profile where Claude Code tokens actually go: a single Go binary that reads a session JSONL and prints a flame-graph-style tree of system / skill / mcp / file / reasoning / output, reconciled to real per-turn usage, plus an allocation_v1.json schema.

Save up to 30% of your AI coding tokens. Scubiee turns any codebase into searchable context for your AI coding agent. A local context engine for Cursor, Claude Code, Copilot, Codex, and more: semantic search, code relationships, live sync, MCP integration, and code that never leaves your machine.

Local-first terminal app for learning Python, TypeScript, Java, and Rust with executable lessons, spaced review, coding practice, and optional AI hints.

Run AI agents on your computer and dispatch tasks from anywhere, approve actions on the go, and let agents tap into phone capabilities like notifications, SMS, contacts, and calendar.

Unofficial tool for Claude Code sessions on disk: make a session visible under your other Claude account on the same machine, or move one between project folders. Command line or GUI. Journaled, reversible, fails closed.

Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server.

Claude Code-style terminal UI for DeepSeek Harness agents, as an out-of-tree dsh plugin bundle

rhachet brain.atom and brain.repl adapter for anthropic

Claude Code inference provider for Pi. Allows the use of Claude Code of Pro/Max subscriptions from pi.dev.

A manager for multi-agent skill, slash command, subagent, hook, MCP and etc.

A modern take on tmux

TagIt — an open-source, self-hosted Claude Tag

One shared Markdown file that AI agents take turns writing to — context, decisions and progress all live in the file, so any agent can pick up the work without you summarising the last chat. Single binary: CLI + MCP server + live Web UI

Agentic gatekeeper for Claude Code — three-level policy engine, Starlark rules, per-project config

Minimal, zero-dependency provider switching for Claude Code — switch between Anthropic, OpenRouter, DeepSeek, Z.AI, Kimi, Qwen, MiniMax and custom endpoints

Know how much Claude Code your friends are burning through. Create a group, share a code, compare usage.

Keine Repository-Beschreibung veröffentlicht.

Launch Claude Code with multiple backends (Anthropic, OpenRouter)

Every prompt you have typed, across every AI CLI, in one searchable TUI. Reads the prompt history already on your machine. Zero dependencies.

CLI + Claude Code plugin for managing markdown docs with YAML frontmatter — index, query, validate, graph, lifecycle-manage plans/ADRs/RFCs, Notion sync, AI summaries

a CLI and MCP server for iOS Simulator automation, designed for agents

Let your AI agent drive a real Chrome or Edge browser over a simple JSON API — one server, one persistent profile, full DOM control.

A Go SDK for the Claude Code CLI: one-shot runs, interactive sessions, in-process Go tools, permission & hook callbacks, inline subagents. Behaviorally verified against the real binary.

Local-first failure diagnosis, auto collection, repair planning, AI handoff, and verification for Playwright, crawler, RPA, and agent workflows.

Terminal dashboard for AI subscription quotas - Claude Code, Codex, Gemini CLI, Copilot, Grok, Antigravity, OpenCode, z.ai - with burn-rate forecasts and threshold alerts.

quiver (qvr): open-source git-native package manager for agent skills — lockfile-first, registry-agnostic, and built for reproducible AI agent workflows.

A status line for Claude Code: rate-limit windows, context, tokens, cache hit rate and session cost — in two lines under your prompt.