Havuz

Pi Desktop: a free, open source desktop GUI for the Pi coding agent and oh-my-pi. Chat, edit files, run a terminal, and review diffs in one

Zero-overhead, terminal-native local-LLM orchestrator. Run any engine, any model via the same proxy.

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseSt

Proxy patch for Google Antigravity that intercepts internal Cloud Code API and adds support for OpenAI, Claude, Ollama, Gemini and any custo

Open-source AI API Gateway | Serverless & VPS Self-hosted | Vercel, Cloudflare & Local | Multi-Provider, Smart Routing, Key Rotation & Failo

Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.

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

The AI-friendly binary analysis & decompilation engine — 1:1 lift, built on LLVM [WIP]

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

Paste your code and get brutally roasted by AI — then refactored into something actually worth shipping.

Interactive AI tutor built as a Claude Code skill — teaches with spaced repetition, personalized project examples, and a visual progress das

Agent Workflow Kit — Evaluation-first rules, templates, and Skill packages for AI-assisted software projects. Score risk, choose the smalles

A small operating file for keeping long-running AI agent sessions from degrading. Capable models can do useful long work. The problem is no

Token Monitor, 40'tan fazla AI coding tool için token kullanımı, maliyet ve limitleri masaüstü widget'ında takip eder.

Neden yükseliyor · 40'tan fazla araç için tek panel vaadi geniş ve güncel bir ihtiyaca karşılık geliyor. 131 günlük yaşına göre 2.400 yıldızın yanı sıra son 28 günde 177 commit ve 18 farklı yazar bulunması, yalnızca README iddiasından ibaret olmayan belirgin geliştirme aktivitesine işaret ediyor.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend

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

Token-saving companion for OpenCode — 42 compression layers, zero risk, no caveman speak

The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. I

Local LLM inference on Xbox Series S in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by def

Multi-agent memory governance demo using Caura + OpenClaw. Three agents (Sales, Legal, Admin) share one memory backend with hard fleet bound

Find and fix web-app vulnerabilities in one command — SAST + DAST + AI, for devs who aren't security experts.

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

Lightweight open-source visualiser for India admin boundaries — pick a layer, view, download parquet

macOS menu bar autocomplete app that watches accessible text fields, shows inline or mirror-window suggestions, and can use remote OpenAI-co

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

AI 每日新闻简报 · GitHub 热门 + X 热门文章 + 行情技术分析 · 23 个数据源聚合 + LLM 中文摘要 · 本地或 GitHub Actions 部署

Dynamic Intent Resolution Grounding Engine

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes age

A Claude skill that keeps your AI coding tools from contradicting each other. Generates requirements.md, design.md, and tasks.md before an

One AI agent, everywhere you work — terminal, desktop, mobile, and your chat apps. Rust core.

玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次，你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置

Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your m

Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-

A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaki

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.

OpenCode Mobile — open-source Android client for the OpenCode AI coding agent. Run AI coding sessions from your phone against your self-host

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

Convert GitHub profiles and repositories into clean, LLM-friendly Markdown. Features profile README ingestion, repository lists, and PAT sup

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.

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

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure dia

Approve Claude Code from your Mac's notch. A native SwiftUI menu-bar app that surfaces Claude Code permission prompts, questions, cost and c

Apple Silicon mlx with Zero Dependency Java

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions i