Havuz

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land

Don Cheli — SDD Framework. The most comprehensive Specification-Driven Development framework for AI agents. 88+ commands, 51 skills, 15 reas

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canv

Web search CLI for AI agents — 13 providers rank-fused into one Rust binary. Search, extract, verify, check credits.

AI agent skills manager for Claude Code, Cursor, Codex and more — install, sync, and manage skills from one desktop app.

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue inst

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

MCP server for Google Scholar: search papers with Scholar operators, year ranges, cited-by and all-versions lookups, plus citations in five

Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools.

Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs

MCP server for Glassdoor: search job listings by keyword and location, read one posting in full with the employer rating and the salary figu

CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs

Interactive data-flow diagrams your AI agent can write. One SKILL.md — install in Claude Code, Cursor, Codex, and 11+ other clients via `npx

Hosted Google Search / SERP MCP server from HasData, no Google Cloud project. Organic results, AI Overview, People Also Ask, AI Mode, news a

Multi-agent Claude Code skill for building apps and stuff

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

A CLI that extracts the useful structure from source files: signatures, imports, types, variables, comments, and Markdown sections.

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

Adversarial LLM Reversal for hermes-agent

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, the

An Automated project operating system, called PhanOS. It Combines Phanes as the Orchestrator, Cyphor(to be released) as the Documentation, C

An open-source DSL and compiler for floor plans: write .arch source (or have an AI agent write it) and compile it to SVG, DXF or PDF with li

The best news MCP server — 150+ verified articles/day with confidence scores, Ed25519 provenance, and Ethics Engine ratings. Free, no auth.

On-device shell command generator for macOS Tahoe. Uses Apple's 3B model with dynamic few-shot retrieval from 21k tldr examples.

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing

Open-source desktop AI agent that sees what you see — one hotkey over any window, it answers, acts, or guides you step-by-step.

Mail for AI agents ( and humans). MCP server giving Claude (or any agent) safe, permission-controlled access to email (Microsoft Graph + IMA

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

Django manage.py context for coding agents — and tab completion for you

Hosted Instagram MCP server from HasData. Public profile and post-feed tools by handle, structured JSON, for Claude, Cursor and any MCP clie

Self-hosted intent radar — Reverse RAG for any input stream.

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

Local MCP server that exposes classic Outlook desktop (mail, calendar, contacts, tasks, rules) to Claude and other MCP clients via COM. No A

Windows PowerShell toolkit for AI agents: Microsoft 365 (mail, calendar, Teams, SharePoint, OneDrive) via Work IQ + Microsoft Graph, Outlook

Translate academic papers & monographs (PDF) into a single self-contained bilingual HTML — Chinese/original/side-by-side. Vendor-neutral, wo

Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.

cn金融数据 MCP 服务器 — 工具包覆盖 A 股行情、财报、估值、板块、市场全景、新闻及宏观指标。

A local-first desktop application for AI agent workflows.

a philosophy for talking to AI agents without getting glazed. one trigger, four meanings. /meow.

Semark converts PDFs, Office files, HTML, and images into RAG-ready semantic Markdown using MinerU and VLM/LLM review, with chunks, source m

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

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.

Progressive tool discovery for DeepSeek Harness — tiny stable surface, searchable catalog, real pipeline execution, context cache intact.

TikTok MCP server by HasData: public profiles, videos, comments and keyword search as JSON, over streamable HTTP.

Real-time execution trace and cost intelligence for Claude Code

Claude skill for Betaflight: FPV drone configuration, PID tuning, log analysis, and troubleshooting.

Use Cursor CLI from Claude Code to delegate coding tasks to Composer 2.5+ and other Cursor models.