Havuz

Open-source, self-hosted AI agent for terminal, Telegram and Raspberry Pi. Local Ollama or Claude/Codex workers, enforced by a deterministic

Drop-in replacement for Claude Code's built-in WebSearch and WebFetch. DuckDuckGo-powered, no API keys, works on every provider.

Caps Lock LED as a live status indicator for Claude Code — blinks while working, solid when done. Zero dependencies, no Caps Lock side effec

The framework for building stateful agents. Your agent is a folder of state, served over MCP, used from any runtime.

AI coding agent in your terminal. Works with any LLM - DeepSeek, Qwen, GPT-5, Claude, Gemini, Kimi, Ollama. 100+ models via litellm. ~1300 l

Make every model a CodeX engine through an OpenAI-compatible Responses API gateway

Terminal-native agent for clinical workflows — prior auth, coding audit, and documentation, with reviewable output

agy-mcp: Model Context Protocol (MCP) server for Google Antigravity CLI (agy) with async supervision and completion wakes.

Claude Code CLI — original source code snapshot for research. Property of Anthropic.

Run several accounts of the same Mac app at the same time

One source to rule them all: write agents, skills, rules, and hooks once, then sync them to your AI tools.

One command, 28+ top AI CLIs — an interactive launcher for terminal AI coding agents (Claude Code, Codex, Gemini, Aider…). Uzbek &

Generate GitHub Wiki from source code using Claude Code. Single Go binary, no Docker needed.

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dis

Diff filter that expands every hunk to include the enclosing function or block via tree-sitter. Pager for git, gh, or lazygit; viewer for co

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

A tiny CLI for playing the Claude FM YouTube live stream audio inside your terminal

Scan your Claude Code logs and find the habits silently burning your tokens. No LLM calls, no deps, offline.

Spec-driven development for Claude Code — author validated, ISO/IEC/IEEE 29148-aligned specs, then plan and build against them.

TypeScript core + CLI + MCP server to automate routine interactions with Chile's tax authority (SII), for Claude Code and Claude Desktop. Un

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

Free, open source website technology detection. Identify any site's full tech stack from its URL — CLI, library and MCP server for Claude, C

Local MCP switchboard for Codex, Claude Code, Gemini, Antigravity & VS Code — route tasks, run cross-model debates, and share context using

Claude Profile Manager — run multiple Claude Code accounts side-by-side with isolated credentials and zero overhead

AGI CLI ~ a meta-harness for building Agent Factories

Modern, fully customizable Claude Code statusline. Single-file bash + jq, no plugin runtime, no network calls. presets, themes, 42+ data tok

Claude Code & Codex Dashboard — local web UI for Cluade & Codex token usage and cost. npx ccgauge

Run many Codex & Claude agents in parallel without them overwriting each other. Isolated worktrees, file locks, PR-only merges. Auto-wires O

Stop being lost in a codebase. CLI + Claude Code skill that builds an import graph, runs PageRank to find the files holding a repo together,

AI-powered terminal workspace manager (tmux + Claude Code)

Mine reusable skills from your coding agents' transcripts (Claude Code, Codex CLI, or any agent) with outcome-weighted scoring and a local r

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, ro

High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-on

A Claude Code suite for Microsoft Power Automate development — Agent Skills + a local CLI (Dataverse/Power Platform APIs, Azure CLI auth, no

Batched file operations for autonomous Claude Code runs. Collapses N reads/greps/globs into one Bash round-trip — fewer output tokens, less

Local-first second brain for your handwritten reMarkable notebooks, searched through Claude Desktop.

Spec-driven software engineering for AI coding agents - a Python CLI that drives brainstorm, spec, plan, and execute phases over markdown ar

A live, local dashboard to browse, search, resume & manage every Claude Code session on your machine — full conversation transcripts, an art

A local-first, LLM-agnostic memory layer for AI assistants

(개요) 국가법령정보센터와 알리오의 공공기관 내부규정을 검색·비교·분석하는 MCP. (도구) 법제처 87 + ALIO 공공기관 규정 23 = 110개 MCP 도구. (데이터) 1,600 법률, 10,000 행정규칙, 수만건 판례, 344개 공공기관 3

A grid of real terminals in one browser window — run a Claude in every box; when one needs you, it glows, dings, and jumps to the top bar.

Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automati

AI Video Engine — Turn structured data into videos. JSON timeline → Scene components → HTML/MP4.

It falls out of your notch. Hotkey, repo, Return: your terminal opens with Claude Code, Codex or any agent already running. Free, MIT, local

Release Doctor: check Expo, React Native and Unity release risks before connecting app stores. CLI + MCP for Claude Code and Codex.

Deobfuscated source code of @anthropic-ai/claude-code v2.1.76 | 1,902 TypeScript files reverse-engineered from the official npm package

Suckless-style PTY proxy in Zig that drops an LLM exec dialog, atuin autosuggest, and guardrail - eBPF LSM, tiered classification (regex + S

Karpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you de

Automatic model+effort routing for Claude Code: tiered subagents, escalation ladder, independent verifier

Queue research questions all day. Wake up to answers. Puts your idle Claude Code quota to work while you sleep.