Havuz

Unofficial ACP adapter for Meta's Muse Code — use Muse in Zed, VS Code, and other Agent Client Protocol editors with streaming, tools, sessi

Fast, local-first Git desktop client, code intelligence suite, and task workspace built with Rust (Tauri 2) and Svelte 5. 100% on-device, ze

Recipes for Look's user-declared sources. Copy one in, reload, make it yours

Thompson-mode systems discipline for AI agents. Think first, build bottom-up, brute force until measured, rewrite over patch.

A Rust crate to connect multiple harnesses under one, simple, up-to-date interface.

DSH Hub CLI, DeepSeek Harness eklentilerini ve yapılandırmalarını sürümlenmiş Profile olarak paylaşmayı ve başka ortamlara uygulamayı sağlar.

Neden yükseliyor · 33 günlük yaşına karşılık 458 yıldız dikkat çekiyor; son 28 gündeki 10 commit projede yakın dönem geliştirme olduğunu gösteriyor. Ancak 2 farklı yazar katkısı ekip genişliğine dair sınırlı kanıt sunuyor ve bu veriler yükselişin nedenini tek başına açıklamıyor.

A focused GitHub desktop workspace for notifications, issues, pull requests, Actions, repository discovery, and an optional repository-aware

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。En

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

Ready-to-use Grok Bot profiles with focused outcomes, explicit approval boundaries, and separate specification, implementation, and verifica

Caravel — a local-first workspace for AI coding agents. Delegate tasks, follow progress, and review code across projects.

A native progress bar for Codex Goals — see what’s done, what’s happening now, and what comes next.

Learn while your agent works. A Claude Code plugin that quizzes you on the concepts behind the code it just wrote — local knowledge graph, s

Press both Option keys and the window you're looking at - screenshot plus every word in it - lands in your next Claude Code message.

Multi-repo Git workspaces for the AI-agent era — group repos, operate in bulk, wire them to your coding agent.

Скажи словами, что построить — получи работающую версию, проверенную до того, как её назовут готовой. Плагин для Claude Code: сам собирает т

statically checked programming language with its own compiler, runtime and package system, built for developer tools and structured applicat

An open Agent Skill that turns technical evidence into clear, human explanations without changing meaning or operational state.

Local-first coding agent with operator-owned prompts, memory, plans, tools, and multi-agent workflows in the terminal.

Infinite scroll terminal multiplexer and agent orchestrator for macOS

Open-source platform for getting honest human feedback on things you've built.

Open-source Apollo alternative: cold-outreach engine that verifies every mailbox before sending. Email discovery, SMTP verification, bounce-

simplify-codebase, AI coding agent'larına mevcut bir codebase'deki gereksiz karmaşıklığı kanıt arayarak belirleme ve güvenli biçimde azaltma iş akışı sağlayan bir Agent Skill'dir.

Neden yükseliyor · 34 günlük yaşında 498 yıldıza ulaşmış olması dikkat çekiyor; ancak bu ilginin kaynağı veya kullanım düzeyi verilen ölçümlerden anlaşılamıyor. Son 28 günde 2 commit ve 2 farklı yazar var; kısa geçmiş nedeniyle sürdürülebilir aktivite hakkında güçlü kanıt yok.

Automatically name Herdr tabs and panes from your current work, Git branch, terminal activity, and Claude Code sessions.

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

Agent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.

🌊 34 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your

Code-quality skills by Max Kanat-Alexander.

Manage upto 1000 agents using automations and workflows

Architectural linting for Swift developers and coding agents

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Deja de usar Claude Code como venía en la caja. Semáforo de contexto, modo conciso, 4 hooks que bloquean comandos destructivos y secretos, e

Local traffic visibility and privacy controls for coding agents. See what Claude Code, Codex and Copilot send to the model; mask secrets and

Turn any local codebase into clean, structured, AI-ready data.

A graphical tool for visualizing and inspecting Bazel builds.

Mine GitHub issues for pain points — LLM semantic analysis, severity scoring, topic clustering & one-click market-research reports.

A visual UX configurator and scaffold generator for Agent frontends.

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

The all-in-one iOS workbench for macOS: mount DDIs, run pymobiledevice3/DVT diagnostics, stream Unified Logs, capture PCAPs, simulate GPX lo

Run several Claude Desktop accounts side by side on macOS, sharing Claude Code chats between them

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, mak

A terminal-native prompt composer for power users running multiple coding agents.

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

High-performance bridge proxy connecting Claude Code CLI & Anthropic SDK to ANY OpenAI-compatible LLM provider (DeepSeek, OpenRouter, Groq,

An unofficial Windows companion for ChatGPT dots and Codex: task notes, compatible local task status, original-task links, and privacy-revie

Plugins for Paseo — a skills browser, a GitHub board, and a launchd job scheduler.

Shared project knowledge and handoff for coding agents across long-running projects

Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Curs

AI-powered GitHub repository assistant with local Ollama models, repository analysis, grounded chat, and GitHub OAuth.