Havuz

Free, keyless coding models routed to every coding harness through one local endpoint

AI novel generation with world building, interactive choices, and persistent character state. Next.js + Go. AI 小说创作台。

Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: sha

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

Local-first desktop activity tracker — see where your hours go, with on-device AI daily summaries and optional multi-device sync

Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI appli

Open-source, local-first AI video clipper. Long video in, caption-burned speaker-tracked 9:16 clips out. Fully offline with Whisper + Ollama

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

A git hook that won't let you push code you can't explain. Quizzes you on your own diff. Works with Claude Code, Codex, Cursor.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

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

SWE-sweep, agent'ların büyük kod tabanlarındaki konumu ve türü önceden belirtilmeyen birden fazla bug'ı bulup düzeltebilmesini ölçen bir benchmark'tır.

Neden yükseliyor · 1 günlük, 33 yıldızlı yeni bir Facebook Research benchmark'ı olması ve LLM agent değerlendirmesine yönelik güncel bir soruyu ele alması dikkat çekebilir. Ancak yükselişin kesin nedeni bilinmiyor; son 28 günlük commit ve farklı yazar verisi ölçülmemiş.

Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination stra

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

Ryza Chat, kullanıcının seçtiği LLM ve TTS servislerine bağlanan, gerçek zamanlı 2D avatarlı bir AI companion istemcisidir.

Neden yükseliyor · 26 günlük repo için 55 commit ve 4 farklı yazar aktif geliştirmeye işaret ediyor; 193 yıldız da ilk dönemde dikkat çektiğini gösteriyor. Bununla birlikte yıldız ve README, kullanıcı benimsemesini veya ürün kalitesini tek başına kanıtlamaz.

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

Go implementation of AI coding agent

A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V exa

A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages

Hệ thống knowledge base cá nhân hoàn toàn tự động, vận hành bởi LLM. Dựa trên pattern LLM Wiki của Andrej Karpathy.

Code Modern. Code Legacy. Code Firmware. - open-source AI-native IDE with agentic coding, Power Mode, legacy modernization, and firmware dev

Agent Harness developed specifically for local small-parameter models.

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer,

Strata minus the bullshit. clone, rsync to prod, compile and go

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Game the LLM Reviewer, bilimsel anlamı koruduğunu hedefleyen son bir düzenleme için LLM reviewer tercihleri üzerine araştırmaları agent uyumlu bir skill'e dönüştürüyor.

Neden yükseliyor · Altı günde 188 yıldıza ulaşması, LLM reviewer önyargısı ve akademik yazımda agent kullanımı gibi güncel bir kaygıyla örtüşüyor. Son 28 günde 17 commit ve 2 farklı yazar etkinlik gösteriyor; ancak bu kadar kısa repo yaşı ve yıldız sayısı, gerçek kullanım veya etkinlik kanıtı olarak tek başına yeterli değil.

AI Developer for Unreal Engine — An autonomous AI agent that creates Blueprints, C++, levels, materials, widgets, and more inside the UE5 ed

FyAgent, Windows ve macOS’ta farklı AI araçlarının model, Skills, MCP, prompt ve bazı hesap ayarlarını yerel bir masaüstü uygulamasından yönetiyor.

Neden yükseliyor · Birden fazla AI aracının ayarlarını tek yerde yönetme ihtiyacına hitap ediyor. 62 günde 1222 yıldız ve son 28 günde 453 commit dikkat çekici ilgi ve geliştirme temposu gösteriyor; ancak aynı dönemde yalnızca 2 farklı yazar bulunması katkıların yoğunlaşmış olabileceğine işaret ediyor.

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

Local personal memory for LLM agents

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

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

The agentic memory & message gateway for deepseek-harness

AI job agent: scans 130+ careers pages nightly, scores every role against your resume with an LLM (0–100), alerts you on Telegram, and draft

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

Chiasmus is an MCP server that gives language models access to formal verification

Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MC

AI agent skills for production grade applications

一个会主动发现任务的智能体

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。