Havuz

EKOS is an AI-native platform that continuously reconstructs, compiles, stores and serves enterprise knowledge.

Your product idea. One command. Shipped. The Hyper-Scale Solo Infrastructure(TS 7.0, Bun1.4, oRPC v2, Nix devenv)

Structured project workflows for Claude Code. Published v1.5.1: 54 skill manuals / 8 departments. Development source: 64 / 9, with peer CEO,

CLI to generate a narrative walkthrough of any diff

npx mcp-spec-check <url> — black-box readiness probe for the 2026-07-28 MCP spec release. Zero dependencies. Includes a scan of all 7,850 re

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

Itemized cost breakdown for your Claude Code sessions. Reads local logs, no network, no config

OpenABCode is a coding agent that dynamically routes development tasks to the best-suited models

Keyty - modern open-source keyboard and mouse visualizer for macOS

find and download fonts from the terminal

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents an

fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.

Reclaim the macOS menu bar icons your MacBook notch hides. Pelmet is a free, open-source, permission-free menu bar organizer: hide clutter a

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.

Mission control for every Claude Code session on your machine.

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

Native macOS sidebar terminal that reveals from the screen edge and keeps your sessions alive.

Turn your Ruby codebase into a galaxy

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

Native Windows terminal multiplexer in Rust — persistent sessions, a native GUI, embeddable & driveable browser panes, and AI sub-agent orch

A cross-tool field guide to how I build with AI, with practical workflows and portable skills from research to maintenance.

Infinite spatial canvas for terminal windows running AI coding agents. Wire agents together, pipe prompts, capture output to notes. Tauri +

A macOS CLI tool for relinking static Apple ar archives and frameworks into dynamic Mach-O binaries.

Reusable Soroban smart-contract foundations and developer tooling for the Stellar ecosystem.

Keep your decisions, projects, and context when you switch between Claude Code, Cursor, opencode, and the rest — one plain-markdown bundle i

MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library

Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dep

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

Agent skill that audits and cleans agent-facing markdown docs — archives completed-work history, fixes stale facts and contradictions, keeps

CloneX is an open-source website template extractor designed for developers, researchers, and designers. It helps extract website templates,

Separate services, ports, and Postgres databases for every git worktree. Run parallel coding agents on one machine.

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Publish Markdown documentation from GitHub to native WordPress Pages and Gutenberg blocks.

Local-first orchestrator for AI coding-agent workloads

Storybook for htmx & hypermedia. One binary points at your running app and renders your components in isolation, with an htmx-aware inspecto

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handof

The meta layer behind AI skills. Persistent behavioral overlays that make expected agent conduct explicit across changing tasks and capabili

Rancher desktop DevOps toolkit · tuned for Windows 10/11 workflows. DevOps visibility for engineers running services on Windows. Premium too

Open-source, stack-agnostic issue-to-PR workflow plugin for Claude Code: quality gates, tracker & PR-host adapters, opt-in anonymous telemet

Spec-driven software engineering for AI coding agents - a Python CLI that drives brainstorm, spec, plan, and execute phases over markdown ar

Stack traces that tell the tale — a Logback appender that turns Java errors into AI-ready reports

Memory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, blocks any structured-token drop, snapshot+rollback)

The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.

Mine your Claude Code and Codex logs into a local you.md agent profile.

macOS menu bar widget showing Claude Code & Codex usage limits as battery icons 🔋

Tuvis(兔维斯) — desktop mission control for AI coding agents: live session monitoring, remote injection, Skill/MCP management & usage ledger. O

Practical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.

Turn private work into an NDA-safe credential that shows what you can build — and companies can trust more than a CV.