Havuz

A workbench for language model research

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

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

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无

🪼 Lagune AI is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

让 AI 像人一样说话、创作的规则集。Ruleset for making AI talk and write like a human.

Use 30+ AI models (DeepSeek, Kimi, GLM, Claude, GPT-5.5, Gemini, Grok) in GitHub Copilot Chat - free via BYOK. No Copilot Pro needed.

Free Easy AI visibility check - measure how often a brand is mentioned & cited in Claude's web-search answers. Deterministic, reproducible,

The Most Advanced MCP Server for Unity Editor with execute_code, prompts/resources, input simulation, screenshots, and play mode automation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

墨知 MoRead —— 原生 Android 本地小说阅读器 + AI 伴读（BYOK）：自绘排版引擎、连续听书、SillyTavern 角色卡、向量记忆、防剧透

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLL

让Codex向你呈递公文并接受批示圈阅

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

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

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A reusable AI learning skill for mastering almost any subject through project-driven learning, mastery checks, and authoritative sources.

gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

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

pi custom provider for the Command Code API — 18 models including Claude, GPT, DeepSeek, Kimi, GLM, MiniMax, and Qwen

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

TAgent 是一个基于 Java 17、Spring Boot、Spring AI 和 DDD 分层构建的 AI Agent 工程实践项目。 它不是只封装一次模型调用，而是覆盖了一次 Agent 请求从接入、路由、运行时装配、规划执行、RAG、记忆、MCP 工具治理、人工审批

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Open-source AI-assisted HR onboarding for Feishu/Lark: configurable workflows, document OCR and review, Bitable sync, reminders, and a zero-

繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local

針對台灣求職市場的開源多代理 AI 求職 co-pilot：自動找職缺、履歷健檢、一鍵產生客製投遞包（履歷・求職信・面試準備・公司情報）與模擬面試。本機 Claude Code／Codex CLI 免 API key，也可自備金鑰接 OpenAI 相容模型。

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna

MCP server for KiCad, connecting AI agents to schematic and PCB workflows, ERC/DRC validation, DFM checks, BOM analysis, and manufacturing p

Evidence-aware on-prem LLM inference sizing and TCO calculator

AI agent skills for production grade applications

Open-source desktop app for a local coding agent. Watch every tool call, diff, and terminal command. Bring your own models; sessions stay on

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one r

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first,

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

Cheaper and better Greptile alternative runs on your own github actions.

Your free book and audiobook laboratory. Turn the PDFs you own into chapter-marked M4B audiobooks, read-along books and bilingual editions,

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

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

MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, C

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Co

Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

MakoCode — 茉子版 Agent | Galgame 风格桌面 AI Agent，零门槛体验 Agent 的乐趣