Havuz

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are auto

A terminal that gives AI a body and a living space.

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi

241 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical,

玄机 XuanJi · Claude 客户端 + Claude Code Agent · 国内直连 Claude Sonnet 4.6 / Opus 4.7 / DeepSeek v4 · Claude 防封不退款, Claude Code 国产替代首选

Hosted MCP server and 12 marketing skills for Claude and Codex. Give your agent live web analytics, A/B tests, funnels, heatmaps and paid-ad

A research workspace where an agent works beside you: chat, PDFs, notebooks and files in one dock, plus custom panes the agent builds on req

A Claude skill that teaches your AI to watch videos. Use it to learn, absorb, copy, or give visual feedback like you would to a real person.

Oil Git: a read-only Git GUI and diff viewer for macOS & Windows. 帮你看清 AI 改了什么。

Zero-dep agent workflows with structured approval gates and adversarial review.

A Claude Code skill where learning is the goal and building is the test — AI writes the code, you build the mental model.

Continue unfinished work across coding agents with portable handoff bundles.

用 git 命令点麦当劳：add 放购物车，rebase 凑最省，push 确认后才下单；card 生成 1024 吃麦贡献图（3D 汉堡天际线 / 年度小票）。基于麦当劳 MCP Server，附 --demo 无 Token 试玩和 Agent Skill。非官方参赛作品。

Compliance-first AI gateway for Kiro: connect OpenAI, Anthropic, ACP, Claude Code, Cursor, OpenCode, and MCP through the official kiro-cli b

CRM local con IA que se personaliza a tu negocio. 100% local, open-source, powered by Claude Code. | AI-powered local CRM that customizes it

Cross-platform compatibility layer for AI agent skills — pre-flight dependency checks, MCP-native, works with Claude Code, Cursor, Codex CLI

All of your agents, shells, and TUIs in one durable terminal workspace

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KV

A tmux environment built for running coding agents in parallel — with a persistent sidebar that shows every session, what's running, and wha

Practical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.

Agent Skills for competitive GTM work - battlecards, win-loss, positioning, pricing, launches, deal prep and sales enablement. Installs into

Skills de Claude Code da Visant: auditoria de UI anti-slop, motion, frontend, copy. Com detectores executáveis.

MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology

A stock picking tool that has 21 legendary investors like Warren Buffet, Peter Lynch, Michael Burry etc debate every stock pick and show you

把聊天记录画成K线图，看你和TA的关系曲线

Self-hosted dashboard for all your AI plans. Track limits, resets and spend across Claude, Codex, Cursor, Copilot, Grok and more.

Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query righ

All-in-one AI 研究工作台：把 Codex / Claude Code / Cursor 变成有长期记忆的研究系统。wiki 摄入、研究闭环、快速筛选、假设追踪、播客、日报六大能力，零 API key 可跑基座。

让医疗机构所有大模型流量：PHI 不外泄 · 模型走白名单 · 全量可审计 · 成本可控。

Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifies and merges

Omnia Vault - the all-in-one project brain: an Obsidian LLM wiki, Graphify code graphs, a living plan that triages new videos against itself

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

Lightweight Claude Code alternative: ~1.8% lines, ~90% capability

Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB,

Local-first memory engine for coding agents (Claude Code/Cursor/Codex): SQLite+FTS5 retrieval, versioned bi-temporal memories, full-session

Token efficient IDs for AI agents. UUID alternative for the agentic era.

Illusion-Agent: Where fantasy meets functionality — an AI agent platform for terminal, browser, any model, any OS.

Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls

Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP se

CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically que

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

Audit and fix your Mac's security in one command. No agent, no signup, open source.

Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP an

One Hermes conductor. Many coding CLIs. Zero trust in self-reports. Production multi-harness orchestration patterns: worktree lanes, verific

Nirvana-OS engine: ready-to-run agentic operations. One sentence in, finished work out. Source-available engine for companies, squads and mi

A map of your codebase for Claude Code: an on-device code graph with an MCP server, a CLI, a Mac app and a VS Code extension.

Open-source starter demos for HarnessRouter: run agent harnesses such as Codex and Claude Code as your product backend through one API.

Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (

Long-term memory for AI coding agents — remembers project rules across sessions at $0 AI cost (MCP server, SQLite/PostgreSQL). 90.26% on Sna