Havuz

One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claude/Codex/OpenCode host routing,

One TUI for every AI coding agent session — Claude Code, Codex, Cursor, and more — in sync across every device.

Official Cursor SDK to Anthropic-compatible HTTP gateway with native MCP tool continuation.

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-

Keep your Claude Code / Codex 5h rate-limit windows back-to-back — auto-pings each provider the moment its window resets. | 在 5 小时限额窗口重置的瞬间

A privacy-first, provider-neutral personal AI workbench with chat, memory, auditable tools, MCP, and isolated project plugins.

Bring your own key (BYOK) relay to enable lightweight frontend-only apps to use LLMs using the user's API keys without hitting CORS.

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one

Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip

Korea's first legally-safe (Capital Markets Act compliant) finance MCP. 15 tools (ECOS · Real Estate · DART · KRX) + 2 Korea-unique synergy

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, o

A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at th

Self-hosted mobile web chat UI for Claude Code — drive your real local claude CLI from your phone. Same CLAUDE.md, MCP, skills, login; any g

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Advanced AI platform

Give Claude Code eyes 👁️ — a camera skill so it can SEE real hardware, displays and wiring: verify a rendered panel, check wiring before pow

Claude Code 的桌宠与本地工作台 · A desktop pet & local workbench for Claude Code — 实时动画、权限卡片、Token 看板，兼容 codex-pet / cc-switch ⚓

Claude Code skills for developers who code like cats — never more effort than the problem requires.

Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff:

The native macOS & iOS app for browsing AI agent memory files — Claude Code, OpenClaw, Codex, Cursor, Gemini

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

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the me

Open-source, self-hostable platform that turns agents into co-workers. Start with Software Factory: delegate GitHub issues and review pull r

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do li

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6%

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Op

One command to cut token usage by up to 50%+

LLM spend tracking and budgets for Rails — by user, feature, or any tag, in your own database, no proxy.

Personal AI agent skills for Claude Code, Copilot, Codex, Gemini & Cursor — turn a PR or idea into marketing content, technical Slidev prese

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Spatial prompt engineering through interactive 3D concept graphs

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted,

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

Persistent memory for Claude Code. Your AI never starts from scratch again.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.