Havuz

An AI Agent tool to automate Android devices reliably

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring you

Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

Claude Code skill & open-source wisdom companion (v6.6.0, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Curso

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

CLAUDE.md / AGENTS.md 规则模板：放进项目根目录，让 Claude Code、Codex、Cursor 少返工（附前后对比）｜Drop-in rules for AI coding agents

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re

OpenAI/Anthropic-compatible AI router that keeps apps online with provider failover, key rotation, caching, analytics, and local-model fallb

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routin

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the A

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 dat

The open, machine-readable standard for the Somali language — orthography, grammar, terminology, translation, and AI/benchmark resources, as

Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with cloud AI (DeepSeek, Mistral, NVIDIA

The agent harness you can fork. A working agent loop with compaction, sessions, approvals, a terminal REPL, a local dashboard and ACP, where

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

🧠 Brain-inspired cognitive architecture plugin for AI agents — persistent memory, evolving personality, neurochemistry-driven mood, learning

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transfor

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure

Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code

self-extending sandboxed agentic harness. a loop, two tools and an llm

Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see y

CLI tool for LLM agents to build and maintain personal knowledge bases

Bring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code naviga

SkillAdam: Better Skills for Your AI Agent🚀 Claude Code/Codex/Cursor 插件，一键进化你的skill

MCP server for reading and writing HWP/HWPX (Korean Hangul) documents — built on rhwp. 34 tools, Claude/Cursor/ChatGPT compatible.

Agent Harness Platform — shareable workspaces, MCP tools, skills, memory, and cron/webhook automations. Self-hosted and transparent.

基于 Spring AI 2.0 的生产级 ERP 智能助手｜Production-ready ERP AI assistant with RAG, Tool Calling, chat memory, dynamic SQL tools, multi-tenancy and E

The context intelligence layer for AI coding agents. Compressing noise, routing content to the right strategy, preserving session state acro

Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud,

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

知归是一个面向个人使用的 AI 知识归档工具。把内容链接（微信公众号、稀土掘金、GitHub、小红书、抖音、B站）发送给飞书机器人，知归会自动完成内容提取、AI 分类与总结，并将结果沉淀到飞书多维表格中。Send WeChat Article / Douyin / Xiaohon

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

A trustworthy context layer for AI that remembers, plans and acts — free text into typed commitments, decisions and memories, each with its

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

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

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU

Web UI for Claude Code CLI - token streaming, tool visualization, checkpoint, multi-session management