Havuz

We test whether self-hosted LLMs can run agents

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

An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.

Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.

Local-LLM alert triage for self-hosted SOCs.

Portable offline AI assistant powered by llama.cpp and GGUF models. Run a private local chatbot directly from a USB drive on Windows with no

KamehaDB is a cross-platform database GUI - AI. Support query via human language

Toggle OpenAI Codex between a local model (Ollama / OpenAI-compatible) and the native cloud model — interactive menu, surgical config edits,

A context-aware AI terminal with SSH, SFTP, and local/remote LLM support.

Open-source, Local-first AI (SI) Second Brain.

方寸智匣 LocalBrain：本地大模型、文件与媒体工作台。Apple Silicon Mac 2.3.0，Windows/Linux 2.2.9；Drama 3 本人克隆、长稿配音与分段修改，按平台维护运行环境。

AI-assisted toolbox for work auditing (LaTeX, Scopus validation, paper/thesis/report auditing), software design, CAD design, PCB design, loc

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene

A standalone terminal agent in a single C file. Model agnostic (13 providers + local hako), skill-driven, tool permission gated. No node, no

The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory

Self-hosted, local-LLM news reader that ranks, de-duplicates, and summarizes your RSS/Atom feeds privately, on your own hardware.

Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account

Make your own private AI bot on your own computer. Say what bot you want; BuildBot finds apps, books and live info, shows one plan, and buil

Run Qwen3.8-Flash-Next on ONE RTX 3090 (24 GB) + 64 GB RAM: 128K context, up to 2,100 tok/s prefill, 43–51 tok/s decode. vLLM runtime with h

Arcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and s

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's refe

A blazing-fast, local-first AI agent ecosystem. Orchestrate local LLMs with Python, run them in a native Rust terminal, or integrate directl

Unofficial .NET bindings for Google's LiteRT-LM — on-device LLM inference (Gemma) for Windows, Linux, Android, macOS & MAUI

Qwen3.6 vLLM Toolkit — Launcher + Templates, Optimized for 2×24 GB. vLLM launcher with an optimized hybrid chat template drawing from the be

Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖

MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.

🟢 A private, local AI assistant for macOS — voice, vision, and automation powered by local LLMs via Ollama. 100% on your machine. No cloud,

Open-source Android AI chat, on-device agent, local models, Live2D, Skills, MCP, and Vibe Coding

Knowledge graph and context manager for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, Copilot and local models. Code map with Pa

Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with ty

Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one

EchoMemory, konuşmaları cihazda yazıya döküp aranabilir belleğe kaydeden ve bu kayıtlar hakkında yerel bir RAG chatbot ile soru sormayı sağlayan bir uygulamadır.

Neden yükseliyor · 11 günde 68 yıldız ve son 28 günde 16 commit ile erken ilgi ve geliştirme hareketliliği var; ancak yalnızca 2 farklı yazar görülüyor. Yerel AI, gizlilik ve konuşma belleğini tek bir kullanıma hazır uygulamada birleştirmesi ilgi çekici olabilir; yıldız sayısı benimseme veya kalite kanıtı değil.

A harness optimized to smaller LLMs

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Local AI for Omarchy: the model validated for your GPU, one button on the bar. Start serves it, any coding agent opens on it, one click shar

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and dr

All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CU

Apple’s on-device LLM, text-to-speech and speech recognition for Node.js and Python, with an OpenAI/Ollama-compatible server. macOS 26+ on A

OMA, insan onayı ve denetlenebilir çalışma kayıtlarını agent akışına dahil eden self-hosted bir TypeScript agent runtime sunuyor.

Neden yükseliyor · 180 günde 6.957 yıldızın yanı sıra son 28 günde 45 commit ve 7 farklı yazar, görünürlüğün devam eden geliştirme faaliyetiyle desteklendiğini gösteriyor. Durable approval ve offline doğrulanabilir kayıtlar, agent’ları denetlenebilir kullanma ihtiyacına doğrudan yanıt veriyor.

Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op

Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.

Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

Talk to your computer. Icebreaker transforms natural language into safe Linux actions through isolated AI brains, kernel-enforced sandboxes.

Local AI chat and personal agents for macOS. Ollama-powered conversations, customizable characters, controllable memory, and a browser-based

Atomic Agent, yerel veya cloud modellerle çalışan ve browser, dosya, onaylı shell komutları ile MCP araçlarını kullanabilen bir AI agent uygulamasıdır.

Neden yükseliyor · 159 günlük bir repoda 2.505 yıldız ve son 28 günde 648 commit dikkat çekiyor; yerel modellerle çalışan kapsamlı bir agent vaadi ve README'deki GAIA L1 karşılaştırması ilgiyi artırmış olabilir. Ancak commitlerin yalnızca 2 farklı yazardan gelmesi aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor; yükselişin kesin nedeni bilinmiyor.