Havuz

Open-source TypeScript framework for building operational software used by humans and AI agents.

Local-first observability CLI for Codex and Claude Code

Claude Code ve Codex geçmişindeki tekrarlanan istekleri bulup proje içinde kullanılabilir kısa agent komutlarına dönüştüren bir Agent Skill.

Neden yükseliyor · Agent araçları arasında tekrar kullanılabilir iş akışlarına ilgi çekiyor olabilir; ancak yükselişin nedenini doğrulayacak bağımsız kanıt yok. 9 günlük yaşında 104 yıldız ve son 28 günde 17 commit başlangıç ilgisi ve hareketlilik gösteriyor; 2 farklı yazarla proje henüz küçük ölçekli.

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

Measure what your brain is losing while AI does your work - unaided-skill baselines, decay curves, reliance drills

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini

A CLAUDE.md built on Karpathy's principles and gstack, adding a verification harness and autonomous-loop rules for Claude Code.

A local-first coding agent that works in your repository and leaves reviewable changes

Goal-based planning and proof gate for AI coding agents

Desktop GUI for the omp coding agent: parallel sessions, visual tool calls, model/provider management, and usage analytics.

Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Cross-platform terminal grid for running Codex, Claude, Gemini, and other CLI agents side by side.

Code review for your own machines and your own agents. Reviews live where the code does — reached over SSH, WSL or your own tailnet. Desktop

your repository as generative art — npx codebase-posters

aside-codemode, Aside içindeki JavaScript REPL üzerinden dosya araması ve browser işlerini tek çağrıda çalıştırıp modele yalnızca seçilmiş sonuçları döndürür.

Neden yükseliyor · 14 günlük yaşına karşılık 124 yıldız ve son 28 günde 287 commit görünmesi, hızlı bir başlangıç ve yoğun geliştirme faaliyetine işaret ediyor. README'deki ölçülebilir arama ve browser örnekleri de ilgiyi artırabilir; ancak yükselişin kesin nedeni bilinmiyor. Commit'lerin yalnızca 2 farklı yazardan gelmesi, faaliyetin geniş katılımla desteklendiğini göstermiyor.

Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts,

🐙 盯着 Claude Code 的桌面宠物：随 agent 状态变表情、弹消息气泡、一键授权，并统计 token 用量与花费。本地优先、MIT。

Claude Code, Codex and Pi write down everything you do. bough draws it and prices it: a day, the work inside it, every prompt, and what each

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code,

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

Aizen is an AI coding agent that lives on your PC or VPS. Control it from your phone while it autonomously fixes code, runs tests, and repor

A small, provider-neutral agent harness written in Rust

Self-hosted apps you operate by watching a dashboard and talking to a coding agent that IS the runtime — it proposes, applies, and evolves t

Convert GitHub profiles and repositories into clean, LLM-friendly Markdown. Features profile README ingestion, repository lists, and PAT sup

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, rout

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually ne

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

The ready-to-use editor that nobody uses.

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

Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, an

macOS companion toolkit for power users

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

Cross-platform Claude Code desktop client by hwwn. Multi-workspace, remote mobile access, session branching, BYO LLM. macOS / Windows / Linu

Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.

Self-hosted inbound email infrastructure with a high-performance C++ SMTP ingestion engine, local storage, and developer APIs.

first-pass, Claude Code ve diğer coding agent’lara değişiklik öncesi inceleme, bağımsız code review ve kanıt temelli tamamlanma kuralları ekleyen bir plugin’dir.

Neden yükseliyor · 5 günde 131 yıldız alması hızlı ilgiye işaret ediyor; coding agent’ların değişiklik çevresindeki riskleri kaçırması ve doğrulanmamış işi tamamlanmış göstermesi güncel bir sorun. İlginin özel nedenini veya kullanım yaygınlığını mevcut verilerle doğrulamak mümkün değil; son 28 günlük commit ve farklı yazar verileri de ölçülmemiş.

Local context manager for Claude Code and Codex with workstreams, transcript binding, and branching.

One control plane for parallel React Native work on macOS: slimmed iOS simulators & Android emulators, live dashboard, leased Metro ports, s

Click any React UI element, jump to its exact JSX/TSX source, inspect proven API data flow, and prepare reviewable AI patches. Local-first a

Modular UI components for Pi — customizable editors, messages, progress displays, and statuslines.

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Top Free AI Developer Tools for 2026

Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with

The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.

The native agentic development platform for the Mac: a 5 MB terminal that runs fleets of Claude Code and Codex sessions side by side, each o

A Windows desktop resource manager for developers: inspect processes, ports, and local system usage.

Astra Skill Optimizer for GPT-6/Astra project Skill and workflow adaptation

Open-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI ag

Tinder for your Claude Code skills, subagents and MCP servers. Swipe away what wastes context, scan for prompt injection, get honest token c