Havuz

A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine,

Evidence-backed growth decisions for AI-agent teams

A local resource sentinel for the multi-agent era — monitors RAM, processes & disk used by AI agent CLIs (Claude Code, Codex, MCP servers),

Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with

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.

Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI,

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle

Claudoro: Feature rich Pomodoro timer embedded into Claude Code

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

Project rails for responsible AI coding: treat agents as dumb by default, guide them with blueprints, small PRs, verification, and progress

A Socratic supervision layer for AI coding agents.

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter

Diagram→code through a deterministic rules gate: the AI proposes, 50 rules verify, only valid architecture lands. Try it: app.solarch.dev

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

A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, an

DIO PRO Vitalício Week: Agentes de IA

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

Local-first analytics dashboard for AI coding sessions. See what you built with Claude Code & Codex CLI.

Lint rules for your AI agent's discipline, not its code

A Dynamic Island for your coding agents — a native macOS notch monitor for Claude Code, Grok, Copilot and more. Monitor, approve, and jump b

A unified OpenAI / Anthropic / Responses API gateway with built-in vision model injection — let any text-only model "see" images.

Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.

A Claude Code skill to deploy and operate a web app on a single cheap, hardened VPS the levels.io way — Hetzner/DigitalOcean + Next.js + SQL

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned.

Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients

Paid APIs and supported tokenized shares for agents, funded with prepaid balance. Instinct Checkout guidance: https://vaaya.ai/llms.txt

Claude Code usage recap with narrative. ccusage tells you the bill, ccstory tells the story.

Sandboxed Python environments with the uv workflow. Registry-only installs, read-only dependencies, and deny-by-default networking. Local-fi

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Run different Claude Code providers in different terminals. 支持同时在不同终端窗口用不同 API Key 跑 Claude Code，互不影响

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

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

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

并发调用本机 Grok 4.5、Kimi K3 与 Claude Code，带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.

Organize your AI sessions, and carry what they know into the next one.

An asynchronous file-based handoff protocol for Claude Code and Codex agents sharing one project workspace

Turn your ~/.claude history into a shareable Quartz knowledge base.

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama

让你的 AI 智能体们组成一个团队：在任意宿主里把任务派给本地订阅的 Claude Code / Codex / Grok / Kimi / Antigravity，并行、不打断对话、全走已有订阅。

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

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

A multi-CLI chat frontend — render Claude Code / Codex / OpenCode / Shell sessions as chat threads, with a live terminal, markdown rendering

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