Turn Termux into a complete development workstation with AI coding agents, a modern code editor, databases, automation, and developer tools.

An open-source Flutter POS system designed for small restaurants and businesses.

bluetooth mesh chat, IRC vibes

Bootable Model As System (BMASS) – an offline-first AI operating environment

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Clau…

Terminal coding agent powered by Kimchi's multi-model orchestration

Zero-ceremony repo-local agent memory for coding agents

Self-hosted AI workspace.

MiniCPM5: SOTA on-device LLMs, small yet powerful.

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted …

Terminal-native AI assistant built specifically for Termux and Android development.

Advanced DNS tunneling VPN for censorship bypass, optimized beyond DNSTT and SlipStream with low-overhead ARQ, resolver load balancing, high packet-loss stability and speed.

Minesweeper in Terminal

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

Simulate anything, for $1 & less than 10 min - Universal Swarm Intelligence Engine

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work.

Historical Language Model for London - A specialized LLM trained on 1500-1850 historical English text

A tiny language model that talks like a house cat named Miso.

Library for reducing tail latency in RAM reads

A ~9M parameter LLM that talks like a small fish.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

Production-grade agent directives for autonomous coding agents: Claude Code, Codex, Cursor, Windsurf, Aider.

The agent that grows with you

Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Applied offensive security with Rust - https://kerkour.com/black-hat-rust