Trending Repos

Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.

Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry.

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.

🍊☁️ Open-source* apps that replace SaaS product + tools, running in your own Cloudflare account

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

Local-first observability for AI coding agents. Every Claude Code and Codex session's tokens, cache, models and cost, on this machine and every machine you connect through a self-hosted team hub. Presenting mode, policy hooks, Apple-signed and notarized macOS builds, attested releases. MIT.

The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools.

A durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable

A small, quiet system monitor for Apple Silicon Macs: one floating glass panel that works at any size.

Self-hosted remote desktop client for teams

Real-time network traffic visualizer — see every connection your computer makes. Privacy-first, 100% local. / Visualiseur de trafic réseau en temps réel, 100% local.

Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.

Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统

Self-hosted house planner: true-scale 2D floor plan, 3D, satellite map overlay, sewer, electrical, water and underfloor heating with calculations, priced bill of materials. React + PHP, no database. By the team behind homedesignsai.pro

BankMCP™: your AI can now read your bank. Self-hosted, read-only MCP server for your own bank accounts via open banking (Enable Banking). Standard MCP; tested with Claude and Ollama.

Best free & open source AI personal assistant. Always-on, proactive, sessionless. Browser, computer use, files, remote control. Compatible with ChatGPT/codex and claude code. Selfhost your open source alternative to Muse, Dots, Instinct and Town. Built with Go/Elixir/Lean.

A curated list of open-source AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with licenses.

Not another ChatGPT wrapper. This is a local-first tool that turns your notes, web pages, PDFs and audio/video into a personal knowledge graph — running entirely on your own machine.

Self-hosted social media scheduler. Write once, publish to any connected platform. Runs on your own Cloudflare account.

Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost, image input. Built on Strata.

Self-hosted helpdesk on Cloudflare Workers: D1, R2, Queues, Email Routing. Shared inbox, email threading, AI assist.

Opinionated, actively maintained list of modern, lightweight tools and practices for Spring Boot 4.x and beyond.

Self-hosted media manager for movies, TV, music, ebooks and audiobooks: search, download and organise, all in one Docker container.

Self-hosted browser workspace for Claude Code and Codex CLI, with Docker sessions, terminal, files, Git, and usage tracking.

Open-source, self-hosted implementation of the OpenAI Agents API with multiple native harnesses.

Doca｜开源文档管理与知识库，支持多人协同编辑、在线文档、Markdown、表格、幻灯片、画布和 AI 助手。Self-hosted document management, knowledge base & real-time collaborative editing for individuals and small teams.

clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves on each account's real 5-hour and weekly usage. Steer it from the Claude app.

The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.

Fast, minimal, effective

First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.

Modern desktop experience

Your homelab, as a Git repository: free tools, real configs, and guides for self-hosting with GitOps.

Your private network, wherever you work. Peer-to-peer first, end-to-end encrypted access to your own LANs — no port forwarding, no public URLs.

Local AI music studio unifying ACE-Step 1.5 and YuE2-3B in one Vue interface — text-to-music generation, stem separation, MIDI transcription, and LoRA fine-tuning, with a built-in multitrack DAW.

Free, open-source anti-detect browser profile manager: per-profile fingerprint, cookies and proxy, Camoufox and Chrome engines, desktop app, REST API and MCP server for AI agents. Self-hosted alternative to GoLogin / MoreLogin.

Free, fully self-hosted messaging for personal AI agents. One-click Cloudflare deployment. $0/month within free limits. Connect Grok Bot, Muse, Dots, and more.

grok-cli-self the lightweight, zero-dependency Grok CLI. Chat with xAI's Grok AI (Grok 4) in your terminal: one-shot prompts

ONCE Campfire in Rust: one binary, the Rails app's data, 19–44× faster

记得她说过的每一句话，也记得你答应过的每一件事。A self-hosted AI chief of staff for your chats — remembers what they said and what you promised.

Self-hosted audiobook discovery, Goodreads and Hardcover lists, Audiobookshelf integration, and automatic downloads.

Mojito — the local, evolving alternative to cloud personal AI like Meta Muse.

Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS, Android and the web. One LLM client for OpenAI, Anthropic, Google Gemini, OpenRouter, DeepSeek and ten more providers, plus any OpenAI-, Anthropic- or Gemini-compatible endpoint — Ollama, LM Studio, llama.cpp, vLLM. Local-first, self-hostable, no account. AGPL-3.0.

Turn any Android phone into a full self-hosted Private Cloud & Media Server using Termux, FileBrowser, Jellyfin, and Syncthing.

Self-hosted live dashboard for the Xiaomi Mi Body Composition Scale 2 over Bluetooth Low Energy: profiles, body composition, history

A free photo editor. No account, no subscription, no tracking. RAW, masks and on-device AI for macOS, Windows and Linux. Self-hostable.

A curated list of GEO and AI visibility tools, compared on which AI engines they track, how often they refresh, what they cost, and whether you can get your data out.

An open-sourced alternative to Grok bots

llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Qwen kernels. 90 tok/s over a 100K-token generation at temperature 1.

A curated directory for discovering open-source alternatives.

Counting House: a private, local-first UK personal finance tracker. Statements in, git-versioned JSON out: estate value, spending, tax year and projections.

Alan's Way: a Mac app where your Hermes bots drive their own browser tabs on your Mac and a cloud VPS, with Telegram alongside and handoff between the two.

🏠 Home DNS ad-blocker for Chinese apps (红果短剧/番茄小说) — works at home AND away via Tailscale. 198 precise rules, zero false positives. 家庭 DNS 广告拦截，在家/出门都能用

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.

ESPN draft and lineup tools for Codex and other MCP clients, with browser sign-in, approval modes, per-team limits, and server monitoring.

Self-hosted family organizer for your NAS – shared calendar, meal planning, shopping lists, tasks, finances and more. PocketBase + Docker, no cloud, no ads. 🇬🇧🇩🇪🇫🇷🇪🇸

Benchmark local LLM serving by replaying real agent trajectories

Platform for agent-built apps and workflows

DeepSeek Harness (dsh) 自托管多用户云平台：提供隔离工作空间、持久化存储、访问控制与资源配额。Self-hosted multi-user cloud platform for DeepSeek Harness, with isolated workspaces, persistent storage, access control, and resource quotas.

LearnBuddy 学习伙伴：可私有部署的个性化 AI 学习系统，支持 Cloud 体验与 Personal BYOK，可选 OpenClaw + 飞书。

Self-hosted AI social media studio: one piece of material in, platform-native posts out. Format router, self-critique, pre-publish risk gate, real OAuth publishing. Web app + CLI + MCP server + agent skill.

Public catalog of self-hosted applications with reviewed Docker Compose recipes

Local-first voice memory assistant — capture speech, transcribe live, and ask a private RAG chatbot grounded in what you've actually said. No cloud required.

从手机、平板或电脑浏览器继续 Codex App 会话，兼容官方登录、API 与自定义模型服务。Self-hosted browser access to your existing Codex chats, with local/SSH sessions, approvals and notifications.

An open source alternative to Niagara Launcher — a minimal, list-based Android home screen.

Amnezia VPN v5.0.3.0 — Amnezia VPN Client (Desktop+Mobile) Amnezia VPN is an open-source VPN client that enables users to easily deploy and manage their own self-hosted VPN server. Info page and download link. Third-party software; all rights belong to the original authors.

Control panel for Telegram proxy nodes (telemt, tproxy-server): keys, decoy sites, monitoring

AI goes multiplayer. A self-hosted workspace for people and machine people. Create, code, and work together across desktop, mobile, and web. Open source. MIT licensed.

A lightweight, self-hosted AI subscription gateway for internal teams, with account pooling, access control, and usage tracking.

Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.

Explore sleep, training, mood and nutrition together using local records, traceable calculations and optional MCP tools for your preferred AI client.

A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks in it.

An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engine, and live GPU telemetry.

Nexus — execution infrastructure for AI agents. Host agents in the cloud or behind NAT; let users attach and authorize their own computers and Android phones. Deploy once, work across devices. Python SDK · MCP · Shared run context · Browser, terminal and files · Built-in chat UI · Model routing.

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

Music player for Navidrome and Subsonic servers — Android and Windows

Self-hosted memory server for AI agents. Share context across Claude Code, Codex, OpenCode, and ChatGPT over MCP.

A self-contained Raspberry Pi and Docker rain radar display with animated observed rainfall, local history, outage-resilient playback and LAN multi-screen support.

The AI-assisted, open-source alternative to Notion and Confluence: a team wiki that lives in Git, with real-time editing, data tables, whiteboards, offline mode, and first-class AI agents. Live demo: https://demo.foliowiki.online

Tasks, copy, schedules, suppliers and files for every project you run. Self-hosted, one container, one file to back up.

feedme — RSS feed creator. Turn any web page into a feed and serve it as RSS 2.0, Atom 1.0 or JSON Feed 1.1 from one static binary.

让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use

The floating Markdown notepad for Mac. An open source alternative to Raycast Notes.

Self-Hosted Crypto Futures Journal and AI Trader Analytics Platform 2026

GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 437 tok/s single-user, 841 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install

Teach a local AI what your camera sees and turn it into Home Assistant sensors — garage door open/closed, gate shut, car parked. 100% local, any CPU.

People and organisations pool their own machines over Yggdrasil to keep files, websites, email for their own domains and messaging for alarms and alerts among themselves, with no central server and no provider holding their data. Trust can be personal or enforced. Open source to use as you want.

Best Open Source Chess Blunder Trainer 2026 Self-Hosted Stockfish Analysis

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

Open-source alternative to ChatGPT's Intelligent UI. Answers arrive as live charts, forms and calculators. Works with any OpenAI-compatible model, in the cloud or local.

⚡ In-Memory Vector Search Engine & HNSW ANN Graph in Java 21 Loom. Sub-millisecond KNN retrieval, 8-bit scalar quantization (SQ8), 16,000+ QPS.

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

Local-first personal finance tracker: CSV/OFX + SimpleFIN import, rules, budgets, safe-to-spend, net worth, forecasts. Next.js + SQLite.

Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs standalone or fully Azure-integrated.

1min.AI — Business SaaS listing. Visit link via SOFTGIT. Third-party; rights belong to original authors.

Linux QQ 群聊 Agent（OneBot v11）：分条发言、贴纸系统、主动发言与内置运维命令

OpenJev: Open-source alternative to TypeSafe Jev. Typed probabilistic decision API (Choice, Noul, Score) powered by open LLMs & constrained logprob calibration.

Turn an old Android phone into a home server: SSH, web hosting, Jellyfin with hardware transcoding, Immich, qBittorrent, Home Assistant and a web dashboard. No root.

Self-hosted, non-custodial Monero (XMR) web wallet: dark responsive UI on top of the official monero-wallet-rpc. Keys stay on your machine, two-phase sending with explicit fee review, Windows quick start.

Open-source replacement Home for jailbroken PS5: homebrew Store, games from external drives, 30+ customization options, music and radio, phone remote, party chat, 27 languages. Client (C/SDL2) + self-hostable server (Node.js).

Lightweight, self-hosted OIDC identity provider for small teams. Go + React, password + mandatory TOTP, RBAC, and shared SSO. MIT licensed.

Blazing fast, self-hosted structured decisions for open-weight models with a TypeSafe AI compatible API, written in Rust.

A self-hosted bookmark manager that syncs with your browser.

Private home cloud OS for the Raspberry Pi 5: a NixOS image with six self-hosted apps, a recovery partition and signed updates

Zoomies is a lightweight, self-hosted GitHub Actions runner fleet controller. Ephemeral runners by default, GitHub App auth, webhook-driven autoscaling, multi-host agents, a polished live web UI, and a one-line interactive installer. Single Go binary, SQLite, no Kubernetes.

nanoMuse: an open-source personal agent for every device you own — one agent with a name and a face that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. In the browser, on Android, on Windows / macOS / Linux; your phone's screen and your PC as its hands.

AltServer for iOS 17+ that runs on your home server (Docker): renews and installs sideloaded iPhone apps over Wi-Fi, no computer or VPN

A WebSDR server: C++17 with no dependencies, a one-line install, and an admin panel for everything. Demo: demo.fernsdr.org

A Flutter client for herdr: a status board and live terminal for the coding agents on your own machines. Over SSH, with no bridge binary to install.

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by agreement.

Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hybrid search, and a desktop web UI. Built in Rust for Codex and Claude Code.

AltServer for iOS 17+ that runs on your home server (Docker): renews and installs sideloaded iPhone apps over Wi-Fi, no computer or VPN

Open-source, self-hosted alternative to Jira and Confluence: issue tracking, docs and AI for your whole company. One Docker image, one Postgres. No subscription, no in-app purchases.

Control your Hyprland desktop from your phone over home Wi-Fi. A web page you install as an app. No app store, no cloud.

Local-first AI trading journal. Import your broker CSV, get round-trip trades, KPIs and Claude-powered diary analysis. Runs on your own machine. No account, no telemetry, MIT.

Build AI agents and LLM workflows visually. Security-maintained continuation of Flowise: security fixes, Apache-2.0 only, drop-in for your existing flows and data.

⚡ High-capacity personal cloud storage powered by Telegram MTProto. Single static binary with Google Drive-like Web Dashboard, resumable chunked uploads, HTTP 206 video streaming, and strict ToS Safe Mode.

An experimental local AI runtime. It relays one request through five small models with one job each, on a single 8 GB consumer GPU.

Bookmark OS: Your bookmarks as a desktop, from any browser, no account needed.

A 3D world where AI agents live, work and teach, and you can watch everything they do. Self-hosted, works with local models.

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, contexts up to 1M tokens, and a launcher that shows what every setting costs. Windows and Linux.

自托管、多用户的 Herdr 远程终端工作台：SSH / Tailcat、多主机分屏、移动端与签名 CLI 更新。

A sovereign, self-hosted AI companion with persistent memory, daily routines, photos, and voice notes. Enforces real boundaries in code, runs 24/7 on your own hardware (Linux, Android Termux, Windows), and keeps your data 100% private.

Run it on a machine in your home network and phones on the same WiFi can transfer huge files (10GB+) straight to it — no cloud, no app install, resumable, zero dependencies

A Resend-compatible email platform on Cloudflare Workers — transactional sending, broadcasts, automations, inbound mail and deliverability analytics. MIT, one-click deployable into your own account.

企业暴露面收集与持续监控（ASM）自托管系统：多源采集、存活与指纹富化、风险线索与变更对照。支持 Linux/Docker 一键部署。

Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.

Open-source control plane for turning existing single-user web apps into independent multi-user workspaces through versioned Adapters.

A wax-sealed feedback receipt between a human and their AI partner — rate it, seal it, let the agent learn without turning love into a checklist. 人与 AI 伴侣之间的封缄回执:打星、封缄,让学习不变成清单。CC BY 4.0

ComfyUI, without the graph. A calm, local front end for ComfyUI. Bring your own workflows, write a prompt, watch it render.

Unofficial local compatibility server and profile workshop for Pokémon TCG Pocket

An open-source wealth management desktop & web application to track stocks, ETFs, crypto, and net worth with full data privacy.

A pure C inference engine designed for Intel Xe-LP iGPUs and Gemma 4 26B-A4B QAT.

A beginner Obsidian Vault structure for Cybersecurity, Linux, Homelabbing / Self-hosting, all about sharing knowledge.

One serving daemon for local LLM inference — across runtimes and machines.

The easiest way to self-host projects on your own server. Connect your AI agent and let it deploy, maintain and manage multiple projects on any stack, while keeping your server organized and under control. Easy for anyone, not just sysadmins.

Email inbox API for AI agents, self-hosted on Cloudflare Workers. Open source, with an MCP server. AgentMail alternative.

Self-hosted macro and markets terminal running entirely on free data sources. Built AI-first.

Free, open-source desktop SEO crawler and technical site audit engine for macOS, Windows, and Linux. 250+ technical SEO, GEO, and AI-search checks with no page cap.

Nythos Plus is a single-file, standard-library-only Python runtime built around one idea: reasoning effort is a resource, not a personality trait. Bardiya Shokeri

Run one local MLX model across Apple Silicon Macs on macOS and on Omarchy Linux, served as one OpenAI-compatible endpoint

A living AI civilisation you can watch: tiny creatures discover, build, teach and pass knowledge on, with any LLM in their minds.

Abandoned, unsupported research archive for a local-first, model-agnostic LLM agent harness exploring orchestration, code retrieval, off-agent verification, deterministic replay, sandboxing, context management, and model routing. MIT.

Open-source full-stack AI agent with an embeddable React UI and FastAPI runtime. Self-host with streaming, pause/resume, durable state, and parallel multi-agent subtasks.

Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.

Curated catalog of AI coding assistants, terminal agents, local LLMs, and automated testing tools

Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses

Qwen3.8-27B EXL3 (4.00 bpw) + DFlash2 speculative decoding for ExLlamaV3, validated at 262k context on a 24 GB RTX 3090

supabase-multitenant lets you self-host Supabase as your own Supabase.com-style cloud, running anywhere you choose—VPS, Coolify, Dokku, Dokploy, or your own infrastructure. Manage everything from one platform: 1 infrastructure, many isolated Supabase databases, giving you flexible deployment, control, and scalable multitenancy.

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

Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.

Evidence-first news workspace: compare official vs market narratives, click any AI claim to the exact source sentence, and track how your judgment changes. Self-hosted — one-command demo, no API keys.

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring your own keys — Groq, OpenRouter, NVIDIA, Hugging Face, Google AI.

A NPC AI Framework , based on character personalities, can be used for game NPC (extendable for Godot / Unity)

An self-hosted AI platform that talks to your customers for you: it answers in messengers, email and web chat, and hands your team only the hard questions.

llama.cpp optimized for NVIDIA Tesla V100 (Volta, SM70): 2–6 GPU tensor parallelism, Qwen3.8-27B Q8_0/Q4 with DFlash2 speculative decoding, up to 512K context, multimodal (image/PDF/video) and concurrent serving.

Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternary weights. Windows bundle + receipts.

Logic-based multi-LLM voice router for Home Assistant, combining native intents, local Qwen, GPU-aware desktop Ollama, and cloud AI with intelligent fallback.

Compute-for-memory research lab for running larger LLMs on memory-constrained consumer GPUs.

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide and act. 得心，应手。

Local AI chat and personal agents for macOS. Ollama-powered conversations, customizable characters, controllable memory, and a browser-based workspace. Ready-to-run downloads for Apple silicon and Intel.

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

When Jev meets LLM -- Pair a small local LLM (System 2) with Jev model (System 1) to make small model more faster and accurate — OpenAI-compatible, private, and almost free to run in Kilo code and Cline.

100% free, open-source personal agents for your messaging apps, tools, and services

Let idle local LLMs sleep and get your Mac's memory back. A native macOS menu bar app to turn Ollama on and off and auto-free idle model RAM. Free and open source.

Like Johnny, your local agent carries more than its head can hold — and keeps working for hours. Transparent proxy: verbatim archive, structured recall, segments, saved engine state.

Measure whether a back-office AI task can run on your own hardware: accuracy vs gold, p50/p95 latency, $/1k tasks, amortised hardware cost and break-even volume, plus an OpenAI-compatible router that sends each task to the cheapest model meeting your quality bar.

LocalBase — Your self-hosted backend, in one Python file. A lightweight Supabase alternative with SQLite databases, auto-generated REST APIs, a SQL editor, data grid, API keys, realtime WebSockets, backups, and a beautiful dashboard. No Docker, no Node, no cloud. Just python localbase.py.

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text generation. TypeSafe-compatible HTTP API, runs on MLX.

Run System One decision models from Hugging Face locally behind the Jev / System One API, Ollama style

Pulsar (formerly fastkernel): the fastest inference engine for Qwen3.8-27B and Qwen3.6-35B-A3B on Apple Silicon

AiiStream Q3.6: byte-identical MoE expert streaming on Apple Silicon — runs Qwen3.6-35B-A3B on a 16 GB Mac

Turn shiori.ai into an OpenAI-compatible API — pure Go, zero dependencies, streaming, reasoning, multi-account token pool.

Self-hosted GEO & AI SEO dashboard. Track how ChatGPT, Claude, Gemini, Perplexity, DeepSeek and more mention and cite your brand, compare share of voice with competitors, audit your site for AI crawlers and get a ranked action plan.

BloomGauge (formerly Bloomkeeper): free Darkbloom manager and earnings dashboard for Apple Silicon Macs. Source-available core (PolyForm Shield). Keeps the best-paying model loaded, recovers stalls, no Terminal needed.

Your own AI workspace on your own machines: chat, agents, coding, knowledge bases (RAG) and fine-tuning with local models. Open source (AGPL-3.0).

Лёгкое macOS-приложение для приватного локального запуска PrismML Bonsai

Fully offline Unity sample for Android: describe camera photos and answer typed questions on-device with Gemma via LiteRT-LM. No network, model bundled in the APK.

Automated, end-to-end Perplexity account creator — random identity, temp inbox, session cookies and access token. Cloudflare-aware browser automation.

An open-source alternative to Cursor with agent teams who talk to each other. AI code editor on CodeOSS, with OpenCode as its agentic harness.

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GPU or Python. | 200B 以下最强模型，单颗笔记本 CPU 精确批处理接近 10 token/s，最低 8 GB 内存自动运行。原生 C 语言，无需 GPU 或 Python。

Free & open-source alternative to SoundSource for macOS

🎵 Curated list of the YuE / YuE2 open-source music generation ecosystem — UIs, quantization, ComfyUI nodes, Mac/MLX ports, cloud serving & tutorials. 70+ projects.

A free, open-source alternative to Fences for Windows, built with Rust. Organize desktop icons into panels, access folders, search with Everything, and preview files. 免费开源的 Windows 桌面整理工具：图标分组、文件夹面板、文件搜索与预览。

Offline-first RAG for drilling engineers: ingest well files, get answers with verbatim-verified citations, and generate a pre-spud offset-well risk brief with NPT cost and mitigations quoted from end-of-well reports. Runs with no network access and no model download.

A two-layer coding agent. Your code and data never leave your machine.

Turn Safari web chats (DeepSeek, etc.) into a local OpenAI/Anthropic-compatible API — no API key, no cost. Drop-in for Claude Code / ccswitch.（把 Safari 网页对话（DeepSeek 等）包装成本地 OpenAI/Anthropic 兼容 API —— 不要 API key、不花钱，可直接接入 Claude Code / ccswitch）

🔥 Run large open language models on your phone. A C++20 GGUF inference engine that streams models larger than RAM from flash, paces itself by the device's thermal forecast, and powers a private on-device assistant. Android · iOS · macOS · Linux.

Local-first book translation and LaTeX/PDF pipeline. Configurable MT languages; current ready-to-run routes EN→RU and prepared DE→RU OCR. MinerU, Hy-MT2, resumable jobs, portable agent skill. No mandatory cloud or polish. 26 optional expert skills included.

Strata Manager makes Niko1221/Strata, the local LLM inference engine, easier to set up and use. Manage local models and services, monitor hardware and API usage, chat and tune inference. Open-source desktop app for Windows / Linux x64.

Share the model on your machine with friends: one binary in front of llama.cpp, vLLM, Ollama or LM Studio; one invite code; they chat from a browser. Self-hosted, end-to-end encrypted, no accounts.

Open-source AI SEO & GEO platform. Track your brand in ChatGPT, Perplexity, Gemini, Claude & Google AI Overviews, plus keyword research, rank tracking, site audits, backlinks & AI agents. Self-host free or use AutoSEO Cloud.

Qwen 3.8 Memory Hack: This 0.8B AI Steals a 51B Brain Locally! (Qwengram Setup) - Local Python engine and Ollama setup for Qwengram-0.8B with transferred N-gram memory.

Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.

An open-source Android AI agent that operates your phone in the background, with local models, tool calling, and automated task execution.

Fast local AI decisions inside your application. A shared library and C API built on laya.cpp that runs the Laya typed-decision model in-process: no server, no Python. Windows, Linux and macOS, x64 and ARM64, CPU or GPU. An open-source alternative to Jev

Curated TypeSafe Jev / System One GitHub projects, open-source alternatives, and Jev news

JEV's alike open-source alternative Laya-MLX used as a "LLM-as-a-judge"