Havuz

Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powere

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types

ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.

A desktop workspace for crafting vivid AI personas and exploring what emerges when different personalities fuse.

让旧款小爱音箱直连 DeepSeek 等大模型，家电仍由小爱原生控制，支持免唤醒追问。Hack a Xiaomi AI speaker to talk to LLMs while keeping native XiaoAI controls.

Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to

Android keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)

【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Angles Code CLI — 2MB coding agent with 2GB powers

An open source, Native AI Gateway and LLM proxy built in Rust

Bring your own key (BYOK) relay to enable lightweight frontend-only apps to use LLMs using the user's API keys without hitting CORS.

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant S

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embe

AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

Multi-Provider AI Gateway, "Because we have LiteLLM at home" No personal logs by design. Model autodiscovery, Failover groups, High availabi

Smart inference engine that adapts to your hardware to run models faster, even when they don’t fit in memory

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

A collection of Claude Skill to mirror https://mgifford.github.io/ACCESSIBILITY.md

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, con

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Wiki built using Karpathy method containing information about TPU performance optimizations and hooking it up to autoresearch optimization e

GoAgent · 围棋智能体: AI-editor-style KataGo + multimodal LLM desktop Go agent

Serve clean Markdown from your Next.js site to AI agents, crawlers, and LLMs. Humans get HTML, agents get clean Markdown of the same pages.

Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. O

MCP Server for SketchUp

macOS AI 会议纪要助手，支持麦克风与系统音频录制、实时转录和选择预设提示词生成会议纪要。

AI-native video editor driven as a local MCP server. Linux + Windows: ingest, transcribe, edit graph, melt/ffmpeg render, QC.

Local-first CLI video producer: cuts silence and fillers, word-timed captions, face-aware framing, and LLM-planned code-rendered graphics

AI 生成原生可编辑 PPTX 的 Skill：Claude Code/Codex/Cursor 一句话出 PPT，形状文字都能直接改｜AI PowerPoint generator (editable .pptx)

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kern

llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

Browser-based model and inference management for NVIDIA DGX Spark - inventory local and Hugging Face models, manage Ollama and LiteLLM, gene

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

Open-source SEO audit agent — real-browser checks, backlink scoring, and multi-engine AI citation tracking (Claude, ChatGPT, Gemini, Perplex

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

One GUI for native Claude Code, Codex, Cursor and more agents — manage them in one place, connect across devices. 一个 GUI，接入原生 Claude Code、Co

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением

Official Implementation of "GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models"

Git-Native Coding Agent for Mac

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

Chat with local and cloud AI

Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.

Multi-round AI roundtable with 161 great thinkers. They debate each other, not just answer you ｜ 与历史上最伟大的思想家进行圆桌会议

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality ev

Best Open Source NLP LLM Fine-Tuning Trainer Framework 2026

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every c