AI — independent software & tools
-
blueprint
From a brief to a shippable page — pitch, deck, archive, prototype.
-
cli
Agent-first CLI and MCP bridge for 2,000+ AI models, multimodal generation, sandboxes, and agent workflows—one command, one account.
-
Cipher
Cipher is an AI Cyber Security CLI Agent
-
contextlake
A local context layer for AI tools: mirror your repositories, index them into a knowledge graph, and serve it over MCP so agents answer from real source instead of guessing.
-
open-course-cli
A terminal AI tutor for language learning. It runs in the terminal; exercises, lessons, and answer analysis are generated by a chosen LLM provider.
-
claude-voice-system
Add self-learning voice notifications for Claude Code with edge-tts, phrase pools, priority queues, and anti-repeat handling
-
jarvis-cli
An AI-powered Task Manager CLI that breaks down complex tasks using LLMs.
-
nova
A universal Super IDE
-
brand-launchpad
One Claude Code skill that turns a single project into a complete brand launch — 12 files (positioning, hero line, 30-day calendar, content system) in one run. Built on Caleb Ralston, Harry Dry, Oren John & Brier Cochran frameworks.
-
ai-mind-map
🧠 MCP Server that reduces AI coding agent token usage by 80-99%. Knowledge graph + persistent memory + smart compression for Claude, Cursor, Copilot, and any MCP-compatible agent.
-
browser-server
Browser Server is a self-hosted personal-data service with a web app and browser extensions. It stores todos, bookmarks, browsing history, password-wallet entries, screenshots, and per-domain usage analytics in local SQLite databases.
-
opencode-rmux
Opencode plugin for RMUX terminal multiplexer - cross-platform subagent pane management
-
Promptlog
Permanent prompt memory, visual diffs, and human notes for AI apps. Track every LLM prompt change as a versioned snapshot - CLI + local dashboard + Claude Code plugin.
-
nano-claude-code
Build a lean coding agent in Python with the same performance in far less code
-
skil-lock
Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.
-
ultron
ULTRON is a local command center layered on top of the official Claude Code CLI. It lives entirely under your home folder (~/.ultron/), stores everything in plain text, and pairs the runtime with a Tauri Control Center so a multi-day project never feels like ten orphaned chat sessions stitched together.
-
dsh-desktop
轻量的deepseek-harness桌面端
-
crosscode
An OpenCode Remote Mobile Client
-
postmortemthis
Every AI coding-agent CLI (Claude Code, Codex, Gemini, Qwen, Vibe) reviews your diff in parallel, read-only, for one ship/no-ship verdict. One tiny script: no server, no MCP.
-
solo-agency
Turn your AI agent into a white-label marketing agency — daily research, ideas, leads, videos, blogs, publishing, and analytics for every client.
-
sillytavern-ai-character-chat
Roleplay with custom AI characters using local LLMs, group chats, and text-to-speech in a private, fully offline interface.
-
claude-studio
Build Claude AI apps with a unified dev stack for code, prompts, tools, tests, and local workflow
-
ailist
List of the best AI tools - List your product
-
context-generator
Switch AIs without re-explaining everything.
-
flock
-
hookstack
Claude Code hooks catalogue — production-ready hooks for Claude Code, OpenAI Codex & GitHub Copilot. Install in one npx command.
-
bonsai
Provider-independent coding agent for your terminal — fast Rust TUI + headless mode, OS-sandboxed, multi-provider
-
suitest
Self-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.
-
arxiv-reader-mcp
Search and extract research papers from arXiv using this Model Context Protocol server.
-
arka
Natural-language AI agent for your terminal — 70+ skills, voice, multi-provider LLM failover, and system automation.
-
ai-legal-assistant
Nyaya AI — AI Legal Assistant for India. Upload any Indian legal document (FIR, legal notice, agreement, court order) and get a simple explanation, risk flags, deadlines & next steps in English, Hindi and Bengali. Free 3 analyses, Pro ₹299/mo. Built by THIRDJUNE.
-
AI-System-6
A Macintosh System 6 desktop where AI work stays visible. Local-first, model-agnostic, no framework.
-
figma-relai
Your AI, on the canvas — connect Claude Code, Cursor, or any MCP client to Figma: read, edit, audit, build. The file itself carries your rules and rulings. Works on every Figma plan.
-
zaivern-code
Zaivern Code — Rust-native AI cockpit editor
-
sartor
Local-first career-corpus manager that tailors ATS-friendly résumés and cover letters to a job description.
-
rustyhand
Build an open-source Rust agent OS for autonomous Telegram agents, with one binary, APIs, and a tested Rust codebase
-
Mustatil-YOLO-AI-Model-Trainer-
An AI trainer. Detect whatever you want on maps at GIS-level standards. Archeology tool for fast detection of archeological sites with Yolo AI. For archeology and GIS tasks. Geospatial AI Workspace for annotation, training, detection and visual pipelines.
-
Repo2AI
Convert code repositories into structured, size-limited context packs for AI tools like ChatGPT, Claude, and Cursor.
-
yapui
Yap at your UI — live HTML preview with a two-way feedback loop, as a Claude Code skill
-
codex-lcm
Codex-native Lossless Context Management
-
phishlens-ai
PhishLens AI is an AI-powered phishing detection platform that analyzes suspicious emails and explains threats in plain language. Users can paste email text or upload .eml files, receive instant risk scores, and securely save analyses to a personal dashboard. Built with React, TypeScript, and Supabase.
-
RADAR
A local-first project radar — every project is a blip on a CRT scope, fed by a plain-text BLIP.md your AI agent keeps current via /blip. Electron desktop app + the radar-blip engine.
-
deep-research-skill
Deliver deep research with a 5-layer Claude skill for markets, products, competitors, regulations, and opportunities
-
kry
Tamper-evident, stranger-verifiable receipts for LLM cost-savings — anyone can recompute your caching/routing savings math offline, no trust in your dashboard required. Pure stdlib, zero-dependency.
-
chutes-build
Privacy-first, open-source coding agent for the Chutes ecosystem — no telemetry, no phone-home, no self-update
-
Lumi_Agent
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
-
centrs
Multi-protocol (REST, native API, mac-telnet, SSH) CLI and TypeScript interface to RouterOS, with rich help and validation
-
ToastMonitor
Native macOS menu-bar AI usage monitor. Aggregates token usage from Claude Code, Codex, OpenCode, Hermes, Oh My Pi, DeepSeek Harness and OpenRouter — zero third-party dependencies.
-
AgentHub
IM-native multi-agent collaboration platform — @mention Claude Code, Codex, OpenCode like teammates
-
termassist
Deutschsprachiger Terminal-Assistent für Linux-Einsteiger
-
litmux
Build unit tests for AI prompts to compare models, track performance, and prevent regressions.
-
aiup
aiup — a local catalog for AI tools on macOS.
-
truss-harness
A modular coding-agent runtime for local models with a CLI, full-screen TUI, VS Code extension, and desktop app built on the same tools, safeguards, and workspace state.
-
toolport-studio
One desktop home for Claude, Codex, Cursor, Grok, Toolport tools, and Ceiling usage intelligence.
-
App
macOS app for YouTube summaries with your own AI
-
tulipfarm
The business agent harness
-
Giro.Gtdev
AI-powered Engineering Intelligence Platform for deterministic repository understanding, hybrid retrieval, and explainable AI-assisted development.
-
partner-center-mcp
MCP server: a knowledge & codegen assistant for the Partner Center REST API (auth deprecation linter, SDK->REST migration, scenario docs). Grounded in current Microsoft docs.
-
pxml
Prompt with XML to project [ALPHA]
-
gent-ai-1
CyberSoft Gen AI 01 - OpenAI