Havuz

codex-keysmith, Codex talimatlarını yerel yapılandırmaya önizleme, onay, doğrulama ve geri alma adımlarıyla kuran bir Python CLI aracıdır.

Neden yükseliyor · 92 günde 4601 yıldıza ulaşması belirgin ilgiye işaret ediyor; son 28 gündeki 34 commit geliştirme faaliyetinin sürdüğünü gösterse de bunların yalnızca 2 farklı yazardan gelmesi katkı çeşitliliğinin sınırlı olduğuna işaret ediyor.

Autoprompt, coding-agent’ların ürettiği değişiklikleri gözden geçirip düzeltme ve yeniden kontrol etme döngüsüyle kodlama iş akışlarını güçlendiren bir araçtır.

Neden yükseliyor · 41 günlük yaşına karşın 1295 yıldız, son 28 günde 16 commit ve 7 farklı yazar dikkat çekici erken ilgi ve katkı gösteriyor. README’deki ölçümde OpenCode’un Terminal-Bench 2.1 sonucu 89 görevde 60 çözümden 73 çözüme çıkmış; ancak bu, sınırlı bir benchmark karşılaştırmasıdır ve genellenebilir etkiyi tek başına kanıtlamaz.

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives

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

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan

One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

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

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Cod

The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel

⚡ Unit tests for AI. Test prompts, compare models, save money.

双击一个文件，给 DeepSeek Harness 注入操作者人格：不拒绝、不中途停、全力执行。只写你自己的文件、官方安装目录零改动、改完下一句对话就生效（不用重启）、改前自动备份可一键还原。纯 Python 标准库，零依赖、零网络请求。

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

一套面向 Cursor、Claude Code、Codex、Qoder、CodeBuddy、CatPaw、TRAE 以及其他 AI 编码助手的通用 AI 原生软件交付工作流。一份规范的 core/ 单一真相源、每个工具一层轻量适配、一个跟踪进度的状态文件,以及负责安装与校验的 C

A Codex CLI plugin that grades how you collaborate with Codex across 9 dimensions in 3 categories — your Codex model writes a free-form diag

Drive Google's Antigravity CLI (agy) from Claude Code: system-prompt sharing + a research-method prompt prefix. CLI counterpart to the IDE b

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

Bedrock is a CLI tool that bootstraps AI-ready project configurations by generating standardized rules, skills, and project context tailored

Hermes Agent plugin: rewrites your prompts before they hit the LLM — across CLI, TUI, Discord, Telegram. Quality scoring + analytics + arrow

A compiler for AI coding tasks: pre-resolves repo facts (callers, git history, blast radius, bug-site source) before your coding agent's fir

See how you really use AI — X-ray your AI coding sessions locally

Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

Token-efficiency linter for LLM prompts and payloads

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds com

Plan, build, review, and ship to the real world. Full opinionated harness with built-in Project Management and DevSecOps to code and maintai

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, upda

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

Reverse T9 for LLMs. Free, open-source prompt compressor for your AI prompts and agents.

Local CLI for auditing AI agent skills, conflicts, duplicates, safety risks, and context cost across coding agents.