Havuz

日本語 Markdown ノートのローカル検索 CLI 👀 — BM25 全文検索 (SQLite FTS5) + optional なローカル semantic/hybrid。単一バイナリ・外部 API 不使用、AI コーディングエージェント向け。

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

Mintlify Index: retrieval engine and MCP server. Install: npx mint index

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Ландшафт технологий 1С. Интерактивная карта экосистемы: 200+ инструментов, 6 осей фильтрации, граф связей, схема-постер и маршруты освоения

Yet another minimal and lightweight terminal multiplexer built for the agent era.

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional

Scan agents and auto-remediate agent reliability issues in GitHub Actions

Ollama Model Test - Figure out the best model for the task

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle

Local API simulation and test evidence for AI-assisted development.

Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic sco

DupeSweep (dsweep) — a fast duplicate-file finder and reclaimer: three-stage size/hash detection, reversible quarantine + restore, .NET 10.

Agent skills for Apache Doris

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Claudoro: Feature rich Pomodoro timer embedded into Claude Code

A TIA plugin for PHPUnit

Project rails for responsible AI coding: treat agents as dumb by default, guide them with blueprints, small PRs, verification, and progress

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

A Socratic supervision layer for AI coding agents.

Tools for AI agents to test, fix and optimise your codebase

🌸 a pastel treemap TUI that shows what's eating your disk

Sitewalk: SEO Audit & Site Crawler. 30+ technical SEO checks. Use it in ChatGPT with no install, or self-host the open-source crawler and MC

Skill for Claude Code & Codex: describe your system architecture in text → get an editable PowerPoint diagram (native shapes, not a flat ima

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP +

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

Self-hosted meeting transcription portal — speech-to-text, speaker diarization, LLM-corrected transcripts, structured summaries and Word min

Your Jira and Confluence, mirrored into one local SQLite file — macOS app, web UI, and agent SQL/MCP. Instant search, offline, one binary.

Passkey-first authentication built in Rust on SableDB.

Diagram→code through a deterministic rules gate: the AI proposes, 50 rules verify, only valid architecture lands. Try it: app.solarch.dev

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

🥷 A code-first, strongly-typed build automation system.

Agent skill that audits and cleans agent-facing markdown docs — archives completed-work history, fixes stale facts and contradictions, keeps

Agentic Runtime

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6%

One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server

Claude Code Starter Kit CLI — scaffold Claude-ready projects

Teknofest 2026 Doğal Dil Ajanları Yarışması 1. Senaryo kapsamında geliştirilen, kamu sektörü için resmi evrak analizi ve taslak üretimi yapa

A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, an

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

Claude Code-style terminal UI for DeepSeek Harness agents, as an out-of-tree dsh plugin bundle

CloneX is an open-source website template extractor designed for developers, researchers, and designers. It helps extract website templates,

真机 RPC 中继：把只能在真机/特定环境跑的函数封装成 HTTP 接口（Go + WebSocket，React 控制台，分组路由、单节点）

Generate degraded speech datasets for noise-robust ASR benchmarking

A terminal-first ADE for the coding agents you already use: real PTYs, git worktrees, diffs and pull requests in one window

Is your project as good as the best out there? sota-scan benchmarks your repo against real top projects and hands you a scorecard + to-do li

Persistent memory and operational continuity for AI coding agents — append-only event ledger (AgentBook), rolling summaries, self-model, bel

QA agent swarms. Test web apps autonomously with greater speed and accuracy. Visual navigation, real workflows, evidence-backed reports.