Havuz

Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan

Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + ve

Cut your AI coding agent's token bill, locally: Claude Code, Codex, Cursor, Copilot. #1 on THOL, 39% cheaper on long sessions.

Снайпер вакансий hh.ru: LLM-скоринг под ваш профиль, автопилот откликов в первые 10 минут после публикации (обгоняем ботов), статические пис

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

为 DeepSeek Harness 设计的破限插件：卸掉宿主的提示词限制和审批拦截，让助手照你说的做，不半路拒绝、不反复请示。补丁逐条可选，随时还原原版。 A jailbreak plugin for DeepSeek Harness: it strips the host's

Crossroad A2A: agent-to-agent mail so ChatGPT, Claude, Gemini, Codex and Grok agents work as one team across machines and SaaS apps. Open so

Super Mario 64's movement and collision code on the Game Boy Advance, bit-exact with the original, plus a playable demo. Built with Claude O

Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword a

MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and p

Published: 2026-10-19

Published: 2026-10-18

🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call

麦当劳配餐决策 Skill｜1881 种搭配里算出三档最优解，并告诉你为什么不是另外那些。控卡、忌口、拼单 max-min 公平分配；LLM 不参与算钱，每个数字可追溯。

TypeLeast：按一下快捷键说话，本机识别（SenseVoice），用你自己的大模型 API Key 整理成通顺文字，直接写进光标处。macOS + Windows 11。

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside un

Fast, local, read-only MCP Server for WeChat (4.x/3.x) & DingTalk (7.x V2/V3) chat history with FTS5 search

Agent 式的 SillyTavern 角色卡酒馆：高缓存命中，兼容酒馆角色卡与世界书，自带配图和一键朗读，角色形象固定，引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.

Xing4.0-29B-Intent - schema-guided intent recognition and structured information extraction (intent and slot filling, entity, relation and e

Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choice of AI, and communi

MergeJudge AI Code Review: open-source GitHub Action and runner for AI pull request review that learns your repo's rules. Bring your own AI

基于 ARTEX 的 AI 自主渗透测试系统，支持多 Agent 协作、资产探索与漏洞管理，提供本地部署面板。

AI 智能投标系统（开源基础版）：定时采集政府采购公告，按企业资质筛选标讯，AI 按招标文件要求组装标书、起草技术方案，交标前合规体检提示常见废标风险。支持 Mac、Windows 和 Docker。

Turn your repos into a team of Claude Code agents with persistent memory, coordinated tasks, and a live dashboard.

MVO WHATS PHP — biblioteca PHP nativa para WhatsApp, com QR Code, sessões persistentes, mensagens, mídia e integração MCP para LLMs.

Agent Skill + Playwright/axe-core verification loop that teaches AI coding agents to build accessible frontends on the first pass. Companion

Open-source marketing simulation for AI agents. Test ads, pricing, emails and pitches with synthetic buyers; inspect objections and plan rea

🚀 High-performance OpenAI & Anthropic compatible API gateway and React 19 control plane for OpenCode Zen free tier with 100% resilience.

穿越小说模拟：AI互动小说，支持历史与自由世界、参考书籍、局部纠错和按需Agent助手。Android与Windows，自行配置AI服务，本机保存故事。

从零实现的通用 Agent Runtime：Agent Loop、权限、MCP、子 Agent、上下文折叠与 Skills 自进化

Browserless Chrome uTLS + HTTP/2 OpenAI-compatible API daemon for Google Gemini Web (/v1/chat/completions & /v1/responses)

Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi

TestOPS一站式AI运维平台 · By 一鸣（公众号：一鸣AI编程）

OpenCode Android — unofficial client for opencode. The real coding agent runs natively on your phone: no Termux, no PC, no root. One arm64 A

data agent 从问数到数据开发治理，自然语言问数、SQL 查询、图表看板与多 Agent 专家团分析，支持 MCP 数据源、自带模型和本地 Ollama。

Open-source engine for personal AI assistants that chat on web, WhatsApp, Telegram, email and Slack, with memory, connectors, sandboxed code

~66% Faster, ~44% Less Tokens, The only AI coding workflow you need, Supports small models

Crow: build your second brain from the documents on your computer. Downloads for macOS, Windows and Linux.

Fast, native email client for Linux, Windows and macOS with an optional AI assistant (ChatGPT, OpenAI, Anthropic, Ollama): Rust mail engine,

Desktop coding agent app for macOS and Linux. Any model, on your code and UI. Built on DeepSeek Harness.

Blazing-fast 2D Spatial PDF Parser in Pure Rust (Python, Node.js, Go, C#). Extract exact [x0, y0, x1, y1] bounding boxes, text blocks, table

Research and shared data contracts for Pick Your AI: component catalogs, compatibility rules, pricing, and evidence for AI stacks.

Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

把 CodeArts Agent（华为云码道）桌面端的上游模型服务复刻成 OpenAI / Anthropic 兼容的 Go 网关 · 复用本机已登录凭据 · 纯标准库零依赖

Tidytalk：Mac 本地语音输入工具。按住说话，松开即可得到整理后的文本。语音识别完全本机运行，可搭配 Ollama 本地大模型润色转写内容，数据不会离开你的电脑。免费开源。| Private on-device voice input for Mac. Hold to s

A code reviewer that reports only what it can prove: a test that shows the bug, or the data that confirms the risk. Open source, built by a

AI 编程福利导航：汇总 Claude Code、Codex、Cursor 中转站与公益站，整理免费额度、注册福利、签到活动和评测记录，提供可视化看板与 Python 数据采集工具。