Havuz

潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop

DSCODE, macOS üzerinde kalıcı shell ve paylaşılan oturum runtime'ı kullanan, DeepSeek Harness tabanlı bir terminal coding agent aracıdır.

Neden yükseliyor · 16 günde 675 yıldız, kısa sürede belirgin ilgi gördüğünü gösteriyor. Oturumlar arası görev devri ve paylaşılan runtime, coding agent'larda dikkat çeken bir ihtiyaca yanıt veriyor; ancak ilginin kaynağı veya gerçek kullanım düzeyi verilen verilerden anlaşılamıyor. Son 28 günde 123 commit'e karşın tek farklı yazar, geliştirme temposunun bağımsız katkıcılarla doğrulanmadığını gösteriyor.

FuXi, terminalden kod düzenleme, komut çalıştırma ve araç kullanma sunan; ürün kaynağı bu depoda bulunmayan kapalı kaynaklı bir AI coding agent.

Neden yükseliyor · 54 günde 3366 yıldız ve son 28 günde 41 commit dikkat çekiyor; ancak aynı dönemde yalnızca 2 farklı yazar görülmesi topluluk desteği ve geliştirme tabanına dair kanıtı sınırlıyor.

dshcloud, DeepSeek Harness için kullanıcı başına izole ve kalıcı çalışma alanları sunan, self-hosted çok kullanıcılı bir platformdur.

Neden yükseliyor · 18 günde 87 yıldız ve son 28 günde 106 commit dikkat çekiyor; ancak commitlerin tek yazardan gelmesi, bu hareketliliğin geniş katkıcı desteği veya olgun benimseme anlamına gelmediğini gösteriyor.

DSH Desktop, DeepSeek Harness runtime’ını masaüstünde çalıştıran ve iPhone ile Android’den uzaktan kontrol etmeyi sağlayan bir uygulamadır.

Neden yükseliyor · 44 günde 285 yıldıza ulaşması, DeepSeek Harness’ı kurulum ve mobil erişimle birlikte daha kolay kullanma vaadinin ilgi gördüğünü düşündürüyor. Ancak yıldızlar benimsemeyi kanıtlamıyor; son 28 günde 3 commit ve 1 farklı yazar, devam eden geliştirme için sınırlı kanıt sunuyor.

Lody iOS, Lody servisindeki chat ve coding-agent oturumlarına iPhone üzerinden erişim sağlayan bağımsız bir iOS istemcisidir.

Neden yükseliyor · 22 günlük yaşına karşılık 152 yıldız ve son 28 günde 283 commit dikkat çekiyor; ancak yalnızca 3 farklı yazar görülüyor. Bu veriler yoğun geliştirme temposuna işaret etse de tek başına kullanıcı benimsemesini veya kalıcı ilgiyi kanıtlamıyor.

A harness optimized to smaller LLMs

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and e

Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team proto

macOS Dynamic Island for AI coding agents. Monitor, approve, and jump to Claude Code sessions from the notch.

OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding agent focus.

pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you

Operant Beta：以多模型分工、按需通信、分层审批和经验复用为核心设计，在本机组织可追溯的 Agent 协作，并通过模块化架构扩展能力。

DeepAgent Code: AI coding agent with persistent memory and control plane

Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts.

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound.

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

Apexo: An open-source, general-purpose coding agent for terminal (TUI), web, and desktop with autonomous goals, workflows, persistent memory

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Pl

Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testca

Exort is a coding agent for embedded devices

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts

Go implementation of AI coding agent

clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves

OpenSeek - 广度求索: open-source TUI coding agent with multi-provider routing, MCP, LSP, and Plan/Agent/YOLO modes.

Hive compute for coding agent swarms - expand your personal compute by adding on-demand agentic swarms

Control your local Codex sessions remotely through Discord on your phone or browser.

Carbon Code 是一款类似 Claude Code 的代码开发工具，也是中国第一个基于 DeepSeek 的代码开发工具，Token 成本节省 90% 以上。它可以实现自动任务拆分、自动开发、MCP 测试，以及与 Claude、Codex 等多 Agent 协作，能力接近

面向 DeepSeek Harness 的 Claude Code 风格终端界面，支持 Windows、macOS 与 Linux，兼容透明终端、VS Code 主题和自定义配色。

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,

A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work

Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.

One file. Under 200 lines. Zero dependencies. It's a coding agent.

A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to th

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

Wemux - self-hostable AI agent collaboration platform (Apache-2.0, community edition)

A local-first AI workspace : multi provider chat, a Full Harness in Hashcoder agent, 3D models, ERPs, and multi-agent swarms in one native d

RSIGame: Autonomous agentic game development with recursive self-improvement

Remote control for Antigravity — manage AI conversations, workspaces, and agents from any device. One command to set up, one URL to access.

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

Pairlet (formerly CC Pocket / cc-pocket) — Continue your local AI coding tasks from phone, tablet, or desktop.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one r

Graph Engineering, simplified — with GraphCode. #graphcode