Havuz

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

Chapter-by-chapter teardown of a production coding agent — agent loop, context engineering, compaction, permissions, MCP. 13 chapters, Chine

本地 AI 订阅与 API 网关：统一管理多家服务商账号，为桌面应用和编程工具提供接口。

烽火台 — 创作者跨平台内容作战室。多平台热榜聚合、竞对监控、AI选题智囊团、一稿多平台改写、敏感词合规检测、数据看板。帮助创作者和内容团队用数据驱动内容决策，提升选题命中率与创作效率。零配置即可启动，支持接入任意 OpenAI 兼容大模型。

DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-

A simpler self-hosted alternative to Open WebUI. Bring your own API keys or local models. Native Android and iOS clients.

Your own AI-powered virtual world. 一个属于你的 AI 虚拟世界 。AI companionship.AI陪伴。AI Socializing.AI社交。

PhyAI is a high-performance framework for running Physical AI models (VLA, WAM, and beyond), supporting both cloud-based serving and on-devi

Plug-and-play AI agent skills for OKX — letting any LLM agent trade, manage portfolios, query live market data, and run grid/DCA bots throug

Privacy-focused AI conversation platform for chat, coding, research, and documents.

Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim che

⚡ Cut 60-80% token cost for DeepSeek V4 Pro on Codex CLI. token-saver + memory skills with prefix-cache optimization.

Open-source AI coding desktop app with parallel agents and persistent project memory. Local models, Ollama or cloud AI. Windows, macOS and L

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case s

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Self-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and

Your own AI workspace on your own machines: chat, agents, coding, knowledge bases (RAG) and fine-tuning with local models. Open source (AGPL

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

NEURA Office: native Word, PowerPoint and Excel for Open WebUI. LibreOffice-compatible OOXML. MS365 assistant planned.

A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Run

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

A multiplayer browser game implemented with Python, where an AI acts as the dungeon master and players type out their actions in their own w

专为 AI 玩家设计的单文件卡牌肉鸽 🌙

Open-source TypeScript framework for building operational software used by humans and AI agents.

Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS,

Grepleaks — your AI pentest environment. An AI pentest agent that lives in your terminal.

ComfyUI nodes for Strata: text, structured prompts, vision and managed local inference with GPU handoff. Publisher: t8star.

Local document Q&A in your terminal — powered by on-device LLMs.

NEXBENCH measures what an autonomous agent can actually do on-chain — execute transactions, route swaps, bridge funds, manage DeFi positions

An engineering philosophy that treats the agent as a worker: the system prompt is a JD, skills are certifications, model tiers are degrees,

A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks

A self-hosted, integration-focused IPAM, independently developed with an operation flow familiar to phpIPAM users, deeply integrated with mu

One-message Claude Code deployment on your Muse agent VM, plus dimensio, a multi-model agent workspace. 在 Muse 上一键部署 Claude Code 和多模型 agent

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.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

面向招投标场景的本地化 RAG 标书解析、资质匹配与红线提醒助手

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.

RAG knowledge-base chat app built on LangChain — FAISS vector search, FastAPI backend, Next.js WebUI, OpenAI/Gemini compatible

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

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

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

NeMo Helix: Make the agents you ship faster, more accurate, and safer.

A Claude Code skill that burns tokens on demand. Stress test, inflate metrics, or just set money on fire.