Havuz

Agent Harness or sum

CLI to organize temporary agent knowledge into scratchpads, with a read-only visual viewer.

One workflow methodology across 10 AI coding tools (Cursor, Claude Code, Opencode, Aider, Windsurf, Cline, ...) in a single ~1,350 token spe

The whoburnedmore CLI — count what your AI coding agents really burned and submit to the public token leaderboard. Source of the npm package

Scan a codebase for AI SDKs, MCP servers and agent tools; map risks to NIST AI RMF, ISO 42001, EU AI Act and the OWASP LLM and Agentic Top 1

Forge production-ready MCP servers from databases or OpenAPI specs.

The IDE for your coding agents. Use Claude Code, Codex, or any CLI agent in a real workspace; files, editor, browser, and git, all agent-awa

多 AI 协作开发的项目治理引擎：Scene→Spec→Task 文件化追溯 + 结构门禁，只引导不强制。MCP 服务 + CLI 双形态，文件即真相，零模型依赖——让 AI 会话有记忆、有依据、不打架。

NOW AVAILABLE on MICROSOFT STORE - Bulk-delete or move IMAP emails by AI Cleanup (NEW), sender, domain, or nested rules - CLI + Web GUI, std

DeSysFlow is a vibe designing tool just like vibe coding you can design your systems with clean docs

Self-hosted AI job-search toolkit: evaluates job offers, screens postings, tailors CVs, and tracks applications — all locally, inside Claude

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode,

Hosomaki, the intelligence layer for Linux

For AI enthusiasts who try every new tool and watch their skills fragment. One source of truth for AI agent skills (SKILL.md) + cross-tool s

A local-first autonomous agent harness with a web UI, live charts and buttons in its answers, sparks that keep working while you sleep, voic

Local, BYOK code review for any language. No SaaS, no telemetry.

最系统的AI全栈学习实战手册

Fake AI agent CLI simulator for making any screen look like coding agents are working.

YaClip (Yet Another AI Auto-Clipper) — AI Auto-Clipper for YouTube Shorts, Reels & TikTok

A skill for Claude Code and Codex that designs each page for its subject: decks, reports, explainers. Plus Artifold, a local library for eve

An AI-powered Git pre-commit/pre-push security gate

The terminal your agent team lives in — run coding agents in panes on a shared bus, on a fast GPU-rendered terminal for macOS and Linux.

A browser for LLMs, not humans.

Local-first dashboard for tracking Codex, Claude Code, and GitHub Copilot token usage/spend by repo, session, model, and tool.

Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remember

Agent OS in Rust — one binary, 37 agents, 26 LLM providers, 37 channels (Telegram/Discord/Slack...), MCP server, A2A protocol, 120+ API endp

🛡️ An open-source trust verification CLI to validate and verify real-world claims with @openapi®.

The open-source autonomous delivery agent for Claude Code.

Local AI model manager

Evidence-first memory for Claude Code, Codex, and the terminal. Kimetsu sits beside your AI agent, watches what actually solves problems, re

CLI coding agent powered by the MiMo large language model

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

Aweshelf - a CLI tool for managing shell session bookmarks

Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.

論 — Ask multiple AI agents, get consensus. CLI tool for multi-agent design decisions. Currently supports Kiro, Claude Code, Copilot — more c

Local semantic search, symbol graphs, secrets scanning, output filters, and CLI hooks that save 60-90% LLM tokens.

CrawClaw is a local-first personal AI assistant and gateway.