Havuz

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

MIRROW：本地 AI 伴侣核心与独立应用｜聊天、记忆认知、漫想、共域与共享耳蜗

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

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

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

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?

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

Android AI agent app. Kotlin + Rust via UniFFI.

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

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

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

Open-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ

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

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

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

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

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

Open-source multi-agent AI marketing team with personas, shared memory, 130+ skills, and Docker deploys for Railway and DigitalOcean

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers pe

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

Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code

a LLM inference engine to run on consumer hardware

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

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

Self-hosted AI marketing platform. Like Google Pomelli, but open source, model-agnostic, and actually ships to your social media.

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

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

把蓝湖设计稿整理成让 AI 生成代码还原页面的上下文

Turn dense long-form ideas into immersive Reading Editions.

Open-source AI social media post generator — production-ready Next.js SaaS with live platform mockups for LinkedIn, Twitter/X, Instagram, Fa

Small, independent TypeScript packages for LLM plumbing — token budgets, streaming JSON repair, cost accounting, retries, embedding caches.

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional

Ollama Model Test - Figure out the best model for the task

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

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.

Rust inference engine for a 28.9M-parameter PLE TinyLM on the ESP32-S3 — 9.4 tok/s, faster than the C implementation it was ported from

The most powerful open-source TradingView AI agent. 50 tools, 15 models (Claude, GPT, Gemini, Qwen, DeepSeek, MiniMax), Pine Script v6, quan

All-in-one open-source framework & middleware for enterprise-grade multi-tenant and multi-tier XaaS Services development

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the me

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes