Havuz

AI inference library for mobile devices

Just my pax historia, in open for people

Free, open-source AI coding agent & multi-agent teams for macOS — runs 100% on-device via Ollama or LM Studio. Autovisor, an autonomous Supe

Fully local AI voice backend for the M5Stack StackChan robot (whisper.cpp + Silero VAD + Ollama + Piper) - replaces the xiaozhi.me cloud, no

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with determini

Tiny Rust port of Pi — a ~4 MB statically-linked coding agent CLI for old/low-resource Linux boxes. OpenAI + Anthropic providers, streaming

Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.

Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and a shell it can undo. Runs on a

Dev Log (Bitácora Dev): a local-first logbook for projects that change over time. Saves what you did and why, not just the final state. One

🦄 Forge - a local-first, multi-agent software-engineering runtime that runs Claude Code / Codex-style agentic workflows entirely on your own

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

An open library of 206 security skills for AI agents — pentest, bug bounty, CTF, reversing & defense across 23 domains, with CI-verified rou

Reference Java & Spring implementation of the Open Ingestion Standard (OIS). It provides a secure, decoupled, and vendor-neutral enterprise

Self-hosted, MIT-licensed AI-agent orchestration platform. Agents with personas, skills & tools that chat, run ~90 tools, delegate to sub-ag

J.A.R.V.I.S operations system for multi model ollama claude-code obsidian platform with home automation skills

Binders for macOS: local-first dictation, meeting notes and memory, with an MCP server for your AI tools. Private by design, free, open sour

An open-source, self-hostable AI operating system and development workspace. Powered by Electron and React 19, it features multi-agent orche

The agent loop for Python. Your harness, any model.

Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell bench

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type

Your team uses Odoo — without logging in to Odoo. Free, self-hosted AI assistant on Telegram & WhatsApp: employees apply for leave, approve

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.

A self-hosted knowledge broker for homelabs. Routes and fuses queries across Kiwix, FreshRSS, Open-Meteo, SearXNG, Uptime Kuma, and Home Ass

OpenAI-compatible proxy that keeps LLM agent context small: it injects relevant memories instead of the full chat history (−51% tokens on re

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

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Private AI WYSIWYG Markdown editor with agentic chat & voice dictation. Open source, no cloud, no tracking.

Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and expe

Local AI video dubbing studio with voice cloning, speech translation, speaker diarization and audio separation. Edit, preview and export dub

MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-c

A local-first autonomous agent harness with a web UI, live charts and buttons in its answers, sparks that keep working while you sleep, voic

Dub any video into another language and keep it in sync — no drift. Single-file Python CLI · per-speaker voices · 4 TTS + 5 translators · fu

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic

Open source AI SDR & AI sales platform. AI cold calling software, lead generation, sales automation, and a full AI sales team — all running

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

ThorOS - a voice-controlled, AI-first Linux distribution built on Debian 13. Say what you want; on-device AI plans it and permissioned agent

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

Nuts AI Reasoning Unit

Open-source, provider-agnostic AI browser agent (MV3 Chrome extension). Bring your own LLM: OpenRouter, OpenAI, Claude, Gemini, Groq, or a l

The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything.

Голосовой ИИ-ассистент для Linux/macOS: wake word, LLM + bash-агент, Telegram-бот, GUI. Бесплатно и локально.

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

Gnome extension to monitor the status of Anthropic (Claude), OpenAI (Codex) and more

QuietWriter: a calm, local writing app for books. Plan, write, revise and export without accounts or subscriptions. Multilingual and open so

Realtime TUI monitor for local LLM servers (ollama, llama.cpp). The only GPU monitor that knows what model is running and how much each toke

deepseek-harness 便携式变体 | 即插即用 U 盘 AI 助手：免安装 LLM Web UI、离线可用、适配中国网络，支持 OpenAI 兼容网关（Ollama / 阿里云百炼 / OpenRouter），Windows / Linux / macOS 三端即开即

browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspect