#local-llm

Secure AI Engineering Framework 2026: Data-Boundary Security for Frontier Models

Agentic Runtime

Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Windows GUI for llmfit — find, download, and benchmark local LLMs that fit your hardware

基于 llama.cpp 的跨平台本地大模型客户端：一键调优 GGUF 模型，多模型共享一个 OpenAI 兼容端点，内置模型下载、本地聊天与实时监控。Windows / Linux / Android。| A friendly cross-platform local-LLM client powered by llama.cpp — one-click GGUF auto-tuning, all your models behind one OpenAI-compatible endpoint, with built-in downloads, local chat and live monitoring. Windows / Linux / Android.

caix — native Apple Core AI inference server for Apple silicon (beta): OpenAI/Anthropic API, dashboard, streaming chat with tools/skills/MCP, MTP speculative decoding.

大肥鱼：桌面小鲸鱼，显示 LLM 余额，支持 Codex/本地/云端对话、本地委派分流、文件处理与本地生图。不绑定特定模型，可接任意 OpenAI 兼容接口。

An AI that stays with you between conversations. Keeps the threads you didn't finish, answers from your own notes with receipts you can open, and asks before it acts on your behalf. Provider-neutral: any model, local or cloud, your choice.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

An Android client for Claude Code, Codex, Gemini CLI, Grok and Copilot: chat with AI coding agents running on your own servers over SSH — or with a model running on the phone itself. No backend, no accounts, no telemetry.

Your own self-hosted AI agent OS

Your StackChan, your language model, your network — local-first firmware and server kit for the M5Stack StackChan. Voice, face, camera and MCP tools, with nothing sent to a cloud service.

Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.

A small self-learning coding agent for your own model — any OpenAI-compatible server, local (LLMTray, LM Studio, Ollama, vLLM) or cloud. Single static Go binary, plan/auto modes, skills, permissions, Claude-Code-style TUI.

Forge is a local-first, privacy-respecting AI IDE forked from VS Code. Designed to run completely offline with Ollama, LM Studio, vLLM, and local OpenAI-compatible endpoints—with telemetry completely removed and open extensions via Open VSX.

A privacy-first, self-hosted AI assistant with smart model routing and local LLM support (Ollama).

🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.

Open-source Astro MDX tech blog for AI setup guides, local LLMs, Ollama, developer tools, self-hosted tutorials, and automation workflows

A sandboxed, full-featured agent operating system in a single Go binary. Bring any model, manage local models, point it at a goal, and grant it real authority: every action is sandboxed, governed, and sealed into a verifiable, tamper-evident record an independent party can check. Runs interactive or 24/7, or embed it in your own system.

Claude Code plugin: delegate small tasks (commit messages, PR descriptions, shell/code drafts, log digests) to local Ollama models - private data stays on your machine

Self-hosted workspace for Claude Code, Codex, Kimi and LM Studio. Persistent terminals, unified settings, Telegram answers, 16 languages. Linux and macOS.

Offline meeting transcription and AI summaries for macOS. Whisper speech-to-text plus a built-in local LLM for decisions and action items. No cloud, no account, no API keys.

LangGraph web research agent for macOS with Ollama

把智力从模型搬进载体的本地 AI 助手：换模型，助手不变（记忆/人格/工具/安全边界都不丢）。用本地 4B 跑出远超参数量的效果 —— 状态在代码层真的改变行为（工具表 6→0），不是写进提示词劝它。100% 本地运行。

A local multi-model gateway for Codex & Claude Code on Apple Silicon — a Qwable-first agent runtime (planner → executor → repair → critic → judge), fully offline.

AI-powered TRPG engine — LLM as GM, streaming narrative, dice system, screenplay-driven gameplay. Vue 3 + FastAPI. 本地 LLM 驱动的 AI 跑团引擎。大语言模型担任 GM，支持流式叙事、骰子判定、剧本驱动推进。Vue 3 + FastAPI。

Docker Compose stack for serving a local, OpenAI-compatible LLM (vLLM on Intel XPU) on an Intel Arc Pro B60 GPU — reproducible config with operator and developer docs.

Run local coding agents with full tool access and browser-based monitoring using an uncensored Ollama model on your hardware.

One-Click Private Agentic Coding Launch Tool with Local llama.cpp for Developer AI in 2026

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

Claude Code plugin that delegates simple, well-scoped tasks to a locally running LLM (Ollama, LM Studio, llama.cpp, vLLM) via MCP

Offload coding-agent busywork to a local llama.cpp server; zero cloud tokens. Toolkit + Qoder/copilot/claude CLI skill/agent integration.

Terminal + Streamlit chatbot running entirely on a local LLM via Ollama - no API key, no cloud calls, with token-budget-aware conversation history.

A local-first AI companion that lives in the corner of your Windows desktop: chats, runs actions behind guardrails, and delegates coding tasks to Claude Code / Codex. Powered by Ollama, built with Rust + Tauri.

Run Qwen3.8-27B fully offline on an Apple Silicon Mac (MLX, 4/5/8-bit) and use it as the local backend for Claude Code. Uncensored/abliterated build supported. No API key, no network. Built by yempik.

An AI agent in Chrome's side panel that reads and works on your tab. Bring your own key (Claude, OpenAI, Gemini, OpenRouter) or a local model (Ollama, LM Studio). No server, MIT.

VSCode + VSCodium extension for Ollama Modelfiles. Syntax highlighting, 18-rule linter (unknown PARAMETERs, missing FROM, bad MESSAGE roles, quoting errors), hovers, autocomplete, and 26 snippets. Works in vscode.dev, Cursor, and Windsurf.

Local-first sovereign Life OS with Obsidian-compatible vault, durable AI agents, local retrieval, and Cogni-Brain integration.

Model-agnostic substrate for running small local LLMs well — code agents, chat, image/video, speech. Small capable main model + tiny fast worker.