Havuz

One-click knowledge system for documents, internal bots, and AI agents

AI 驱动的中日双语轻小说生成器：一句话生成世界观/角色/大纲/逐章正文，支持 Gemini/Claude/OpenAI 等多提供商，纯前端 localStorage 存储

Android AI agent app. Kotlin + Rust via UniFFI.

A self-hosted retrieval-augmented search API: web search, content extraction, embeddings, and answer generation.

A from-scratch, dependency-free GPT implementation in pure NumPy: byte-level tokenizer, multi-head self-attention, Adam trainer, and top-k s

An open-source travel agent that works on real websites: plan trips, book in a browser beside the chat, stop at the payment page. Desktop ap

Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板

AI-driven intelligent clipboard turns scattered content across applications into a searchable, editable AI context. It features a clean, ele

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a Re

Two source-verified AI-agent skills that turn project code into traceable business-rule documents (whole-project + single-module). Graph-gui

Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge revi

Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once and kept current —

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own mach

FileFlipper — Quick Edit for Mac & Windows. One-click Markdown: turn Word, PDF, PowerPoint and Excel into clean Markdown that AI reads with

Claude Code skills for developers who code like cats — never more effort than the problem requires.

Terminal-native AI assistant built specifically for Termux and Android development.

Open-source AI Operating System (AIOS) blueprint for Claude Code & Codex — turn any agent into your personal second brain + Chief of Staff:

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing

A Zsh plugin that turns natural-language comments into shell commands using an LLM.

Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.

AI Paper Reviewer: LLM-based tool for academic paper review

Low-code templating for LLM prompts: Jinja2 templates, token accounting, and cache-aware truncation.

Agent-driven SAP/ABAP knowledge base engine that turns S/4HANA custom objects into citable Markdown/Obsidian context for humans and AI agent

千笔一文 Novel — 人 AI 共写的长篇网文创作台：条目化世界书 · 正则 must 契约（确定性复检，违规拦住锁定）· 三层审校（引证验真 + 投票）· 同人文外部导入可整批撤销 · 升级不动书稿 · BYOK 全本地 · MIT。A long-form fiction

一个面向 AI Agent 与 LLM 集成的轻量级 Java 框架，提供统一抽象、OpenAI 兼容对话支持，以及流式响应、工具调用、记忆窗口和 Agent 编排的模块化结构。

TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out of

Claude Code with the model slot left open. The full workflow, open source, on any model or provider.

A serverless proxy that serves an OpenAI-compatible API on top of Gemini.

An AI assistant whose memory belongs to you. Local-first Mac app, plain markdown workspace, bring your own model.

An interactive playground for comparing how different language models tokenize the same text.

We have caveman system prompts and skills for AI models to reduce token use, why not try bake it into the model itself with fine-tuning?

弦外之音 —— 微信聊天里的关系进展助手：读屏（无障碍树 / 截屏视觉）→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复，攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

Loop-native agent workspace — put your AI coding agents on a canvas, wired into loops that run themselves.

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, sem

Free, open-source voice assistant for macOS: ask about your screen and a pointer shows you where, dictate anywhere (offline by default), han

Bilingual AI study coach that answers only from your own course material, with citations

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im

CloakPipe is the verifiable control plane for production AI agents: evaluate a release, certify it, enforce it at runtime, and prove what ha

Felix — single-binary AI agent gateway. Multi-provider LLM, persistent memory, MCP client, runs entirely on your hardware

Spectral graph-augmented retrieval for RAG. Augments dense vector search with a weighted chunk graph and its Laplacian spectrum, graph expan

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

f(t)函数: Agent制作的动画集. 自由软件, 自由视频.

基于 LangGraph 的多 Agent 深度研究助手：可中断恢复、按依赖并行、引用治理与评测，成本降低 45%

Turn WorkBuddy / CodeBuddy (Tencent) quota into a local OpenAI + Anthropic compatible API. Zero-dependency Node.js, multi-account pool with

Open source multi-agent harness for orchestrating AI workers. Supports Claude Code, OpenAI Codex, Cursor Agent, and local models.

Marketing Studio is a self-hostable AI video ad studio for e-commerce: UGC product ads, reference-ad remakes, AI drama ads, and ad skits, po

听记 (Tingji) — 本地会议录音转写与纪要，FunASR + LLM，数据不出本机。Local meeting transcription & minutes, runs entirely offline.

Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain