Havuz

FastAPI reference app for Statewave memory integration. Wraps every chat turn with get_context before the LLM call and record_episode after;

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy

Open-source media intelligence & social listening. A self-hostable, AI-agnostic alternative to Talkwalker and Brandwatch, built on free data

Rust port of earendil-works/pi — coding agent harness (pi-ai + pi-agent + pi CLI)

Free GPT/Claude/Mistral via duck.ai — Telegram bot + OpenAI-compatible API (no keys, no browser, pure JS)

Run local LLMs entirely in your browser, with no server, no install and no traces. A private, single-file AI chat UI and AGENT that also wor

Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, bil

Proof of concept: turn old Android phones into an LLM inference cluster. ADB zero-touch provisioning, llama.cpp on each phone, OpenAI-compat

AI-routed gateway for free LLM APIs — reads your prompt and routes it to the best free model (Gemini, Groq, Cerebras, NVIDIA NIM, Mistral, O

Native iOS DeepSeek Harness port: BYOK inference, on-device Agent tools, iSH sandbox, Cordis plugins, and trajectory.

collabosm, kullanıcının Google Colab hesabında GPU başlatıp Qwen3.8 modellerini yerel uygulama ve OpenAI uyumlu API üzerinden kullanmasını sağlar.

Neden yükseliyor · 3 günlük bir repoda 87 yıldız dikkat çekici bir başlangıç; ancak yıldızların neden geldiği ve kullanıcıların uygulamayı gerçekten çalıştırıp çalıştırmadığı mevcut verilerden anlaşılamıyor. Son 28 günlük commit ve farklı yazar ölçümleri de yok.

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLL

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

Always up-to-date open-source mirror of Claude Code (currently v2.1.152). Run from source with Claude subscription/API, ChatGPT subscription

Multi-provider, multi-account AI proxy rotator with per-model routing, quota tracking, and provider compatibility. Non-technical setup: tell

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and

Self-hosted GPT Image / OpenAI-compatible WebUI for text-to-image, image editing, reference-based generation, and multilingual creative wor

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,

Lightweight proxy for LLM

Customized New API gateway with SnowAPI UI, LinuxDO OAuth, invitation codes, usage analytics and model health monitoring.

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

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and en

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

网页版登录态 → OpenAI 兼容本地反代：DeepSeek / Qwen / Doubao 免费额度驱动 ZCode。Web login → OpenAI-compatible local API.

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

API Scraper — Hunt down leaked API keys in GitHub commits, validate them against live endpoints, and check remaining balances. Multi-service

DeepSeek Harness 模型管理插件：网关健康探测、模型目录发现与余额/配额展示。DSH plugin for LLM gateway health, model discovery and account balance monitoring.

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

感谢马斯克 让我grok自由，免费注册grok 无数个号。然后cpa自由使用

CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accu

Windows 微信群聊机器人：按设定人设回复群消息，本地运行、接入你自己的模型 API。控制台为原生桌面窗口（27 个面板），发消息/切会话/发图/发表情走后台投递——不动鼠标、不要求微信窗口可见。非官方产品，与腾讯无关。

Local MCP server for ChatGPT image generation.

OpenAI-compatible HTTP server for OmniVoice text-to-speech

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Compliance-first AI gateway for Kiro: connect OpenAI, Anthropic, ACP, Claude Code, Cursor, OpenCode, and MCP through the official kiro-cli b

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind

Advanced AI platform

OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

Understand how CLI AI agents work and use your own local CLI AI! Easy to understand, written in python, built on Ollama/OpenAI compatible AP

AI-Powered Presentation Generator — pure HTML+CSS+vanilla JS, zero frameworks