Havuz

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE

What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.

An AI desktop app that runs on your own keys. Chat with any model, let always-on Workers take jobs off your plate, and run every coding agen

A lightweight Rust process supervisor for local stacks, homelabs, and small servers.

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

Terminal UI for Tilt.dev, inspired by lazygit

AI launch-video generator — films your real web app with a cinematic camera, motion blur, and music. A CLI alternative to Screen Studio for

GitDeclutter — safely analyze and clean stale local Git branches. Classifies branches as SAFE, REVIEW, KEEP or PROTECTED.

Tends your codebase while you're away. An always-on AI engineer that reviews your logs, implements your tickets and keeps your pull requests

Zerus is an ADE for working with a fleet of AI coding agents across your machines. Bring your own agents and subscriptions. Follow conversat

The engineering trust layer for AI-generated code — independent review, evidence, and acceptance after your AI coding tool writes the code

Control Kiro CLI from Telegram over the Agent Client Protocol (ACP): switch projects, resume & attach to live coding sessions, streamed resp

Chromium (Chrome/Edge) DevTools panel for debugging SSE / EventSource / NDJSON streaming responses. Inspect, filter, search, and export stre

Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by

Git repository activity at a glance. Contributors, heatmap, trends, branch comparison and changelog. Zero dependencies.

Local-first Python CLI for safer log sharing: redact secrets, tokens, emails, and local paths before posting to GitHub issues, tickets, or A

Desktop dashboard that keeps every git repository you care about on one screen — so nothing you're working on quietly drifts out of sync, go

MCP server for AWS infrastructure analysis — DynamoDB, Lambda, SQS, SNS, S3, API Gateway, PostgreSQL, MySQL, MongoDB, Kafka & IaC drift. Wor

A Git-native dependency admission controller. Evaluates trust signals on every dependency change and blocks commits or builds when packages

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everythi

Drive your real, logged-in Chrome from an AI agent (Claude Code / Codex) over MCP - 55 tools for browsing, DevTools-grade network capture, a

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

Semantic cache strategy bench: replay recorded request traces through candidate caching policies and measure which one actually pays off.

📱 Simulateur mobile local (iPhone/Android/iPad) pour tester tes apps web dans le navigateur, sans installation. Open-source, vanilla JS + PH

Give AI coding agents product, spec, task, QA, and release workflows in one command.

Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.

Claude/Grokbot plugin and scripts: long-running controller pattern to chunk and delegate code work to cli-agents, with embedded adversarial

把 AI 接入你的真实开发环境。CodePier 让 ChatGPT / MCP 安全连接本地项目、Pi / Codex、Shell、浏览器与桌面能力。

Скилл для Claude Code: превращает сервис без API в CLI-инструмент, которым управляет агент. Режим разработчика браузера → скрытый API → CLI

Back up your dev environment — language runtimes & global CLI tools — and restore it on a new machine. Backups live in your own GitHub repo.

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

Live inspection and tuning for React Native & Reanimated. Web and DevTools panels, MCP integration, and source write-back.

A Symfony Web Profiler-inspired toolkit for NestJS — profile every request with a rich panel UI. Powered & maintained by Eleven Labs.

AI-powered codebase architecture visualizer for exploring modules, dependencies, dead code, impact analysis, and project health in real tim

Chrome extension (MV3) that scans live Elementor pages and reconstructs full section/widget structure into an import-ready JSON template — n

Your localhost, accessible from anywhere. Simple, secure, and open source.

The Search Engineer's Toolkit — open source CLI tools for Elasticsearch, OpenSearch

Vite 运行时遥测插件：为 AI agent 提供结构化日志、错误快照、本地 Cookie 修复与提交前检查。 / Vite telemetry plugin for AI agents with structured logs, error snapshots, local

One-command Cloudflare Tunnel Zero Trust CLI

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel e

Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state

DevTools extension for mocking fetch/XHR responses/requests in Chrome and Firefox

Fix the Google Antigravity 2.0 bug that splits one project into duplicate numbered Projects-panel entries (MyApp, MyApp 2, MyApp 3...). Scan

EasyQueue is a desktop application for inspecting, publishing, and managing messages across multiple message brokers from a single interface

⚡ The zero-config, all-in-one in-app debugger for React Native & Expo. Inspect Network (fetch/axios), Console logs, Stack Traces, Redux Stat

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

Patches fetch/XHR to catch duplicate and needlessly sequential network requests during development, with call-site console warnings.

Terminal side pane for Claude Code that shows a session's agents as a live tree. Stop a running sub-agent, send it new instructions mid-task

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

StellarFoundry DevKit: developer infrastructure toolkit for Stellar and Soroban (RPC, XDR/SCVal inspection, fixtures, analysis, CLI).