Havuz

Slotstream, büyük bir MoE modelini SSD’den parça parça yükleyip yoğun kullanılan expert’leri bellekte önbelleğe alarak Apple Silicon Mac’lerde çalıştıran yerel bir inference engine’dir.

Neden yükseliyor · README, 48 GB M5 Pro üzerinde belirli koşullarda 15.86 tok/s ölçümü ve prompt işleme iyileştirmeleri yayımlıyor; son 28 günde 271 commit ve 5 farklı yazar da yoğun geliştirme faaliyetine işaret ediyor. Ancak proje yalnızca 30 günlük ve mevcut sürüm için nitelikli tam yanıt hızı ölçümünün hâlâ beklediği belirtiliyor.

Memmy Agent, farklı AI agent’lar arasında ortak ve kalıcı bağlam sunan bir memory hub ile agent runtime sağlayan bir uygulamadır.

Neden yükseliyor · 73 günlük yaşına rağmen 1.987 yıldız ve son 28 günde 499 commit ile 15 farklı yazarın katkısı var; bu, yalnızca README iddialarından ibaret olmayan belirgin bir geliştirme hareketliliğine işaret ediyor. Farklı agent’lar arasında bağlamı taşıma ihtiyacı da güncel ve görünür bir kullanım alanı.

halogen-flash-server, Qwen3.8-Flash-Next modelini AMD Strix Halo (gfx1151) donanımında çalıştırmak için özelleştirilmiş bir inference server'dır.

Neden yükseliyor · 32 günlük repo için 722 yıldız ve son 28 günde 99 commit dikkat çekiyor. README, belirli donanım üzerindeki ölçümleri ve ölçüm koşullarını açıklıyor; ancak performans iddiaları proje tarafından sunulmuş ve bağımsız doğrulama bilgisi burada yok. 99 commit'in tek yazardan gelmesi geliştirme hızını gösterirken bakım kapasitesine dair kanıtı sınırlıyor.

Pentest Harness, yetkili güvenlik testleri için farklı LLM sağlayıcılarını ve pentest araçlarını yerel bir arayüzde birleştiren self-hosted bir agent çalışma alanıdır.

Neden yükseliyor · 33 günlük bir repoda 398 yıldız dikkat çekiyor; ancak README dışındaki benimseme verisi bilinmiyor ve son 28 günde 2 commit ile 2 farklı yazar görülmesi geliştirme temposu hakkında güçlü kanıt sunmuyor.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, er

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache co

在线检测：veridrop.app｜AI API 中转站检测工具：Claude 中转站检测、OpenAI 中转站检测、Gemini 中转站检测，中转站真伪检测、长上下文验证、思维签名验证、中转站红黑榜，自托管开源。

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source

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.

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, browser tools, OpenAI/Anthropic-c

Use your own DeepSeek web account through OpenAI & Anthropic-compatible APIs. FastAPI reverse proxy with tool calling, vision & streaming.

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

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

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

Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-key quotas, response cache, di

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

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

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

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

Selfhost modern LLM stacks. Run the whole fleet from your terminal

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

Free Claude API + free OpenAI API in one unified proxy. Drop-in compatible with Anthropic SDK, OpenAI SDK, Claude Code CLI, OpenCode, LangCh

Local MCP server for ChatGPT image generation.

OpenAI-compatible API proxy for ChatGPT web — expose ChatGPT as an MCP server, REST API, and OpenAI SDK endpoint via CDP-driven browser auto

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

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

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

Open-source, self-hostable social listening.

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

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

OpenAI-compatible gateway aggregating 8 free LLM providers with automatic failover, circuit breakers, and smart routing. 32+ models, zero c

Multi-Agent AI Desktop Client — 20 specialists auto-collaborate on your tasks. Visual Skill Store, PM orchestrator, streaming chat. Works wi

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

Blazing fast Go port of gemini-web2api. Convert Google Gemini web into OpenAI-compatible API. Zero cost, single static binary.

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,

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 code editor using local AI

Lightweight proxy for LLM

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

国内公募基金数据采集与AI辅助分析工具 — 全栈FastAPI+React，集成AKShare多源数据、风险评分引擎、回测验证、LLM可选分析

Telegram bot for Claude Code and Codex CLI with MCP routing, multi-agent orchestration, cron jobs, and access controls.

LLM-powered conversation summarisation service for OCTO — turns group chats and threads into structured briefs with key decisions, open ques

Idiomatic Rust client for OpenAI API — 1:1 parity with openai-python

MiMo Free API MCP: 基于官网逆向的高性能 OpenAI / HTTP MCP 代理网关。支持搜索、识图、长文本分段及 SQLite 持久化。

Modawen Agent for WordPress is a completely autonomous, AI-powered multi-agent SaaS that researches live trends, writes deep-dive SEO-optimi