Havuz

一套经过生产验证的 OpenClaw + Claude Code 实战知识库：涵盖生产部署、IM 接入、模型配置、安全加固，以及一系列可落地的 AI Agent 业务流项目（小红书发布 / 财务票据 / 智能早报 / CRM / 量化投研 / 密钥巡检自愈）。

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地运行的 Rust TUI/CLI，审计 AI 编程 Agen

Plataforma de trading gratis y de código abierto para Mac (con guía para portarla a Windows con Claude): footprint, DOM, backtesting anti-so

Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with

智能体 = 大模型 + Harness。深入剖析 Harness 工程原理、设计、实现与实践！

Free, open-source antidetect browser with its own open-source Firefox engine, Chromium support, unlimited profiles, Local mode, Cloud sync,

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local proj

Local MCP server that lets AI assistants automate Origin/OriginPro for data and image processing.

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

MCP server that watches video footage and returns license-safe BGM matches, hook windows, and ffmpeg ducking specs for agents.

Official Nexscope guides for AI product video workflows, ecommerce Data APIs and free product listings. Compare workflows, watch examples an

A production-grade agent runtime engineered from the Harness Engineering philosophy.

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

Understand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for human

Free, open-source SEO audits inside OpenAI Codex CLI. Port of claude-seo: 26 skills, 19 specialist roles, technical SEO / schema / GEO / loc

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

A Claude skill for pro motion design with correct Persian (Farsi) typography: no slideshows, no broken letters. 8 techniques, HarfBuzz tooli

An extension of Karpathy's LLM Wiki pattern: atom layer, topic-branches, two-layer Lint. Distilled from running the pattern end-to-end.

Moved to github.com/davidondrej/cloudroom

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

Learn how to get started using the GitHub Copilot app!

Claude Code skill: 5 AI agents analyze crypto, stocks, forex & commodities in parallel, adapt to your risk profile, and render an interactiv

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injectio

A Unified Memory Benchmark Suite for Memory-Augmented Agents

The practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

A boat journey through a Japanese river valley, in four seasons and at any hour, rendered live in the browser with three.js.

Open-source alternative to Claude Co-Work built by Claude. with BYOK

CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, 38 lang

Agent control panel for Claude Code, Codex, OpenCode, Pi and 40+ agents with articles and boards supported

Local-first image prompt library for generating images, saving prompts, tags, and collections.

Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed.

Protocol-agnostic CesiumJS AI control runtime for MCP, WebMCP, function calling, and browser agents.

The full LibreChat experience, rebuilt natively for Android and iOS, and it works with whichever LibreChat version your server runs.

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Codex skill for analyzing still images and writing restrained, image-specific motion prompts.

Give Claude a video input. /watch downloads from YouTube/Instagram/X/Vimeo/any yt-dlp site, extracts frames, and transcribes locally with ml

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,

Custom output voices for ChatGPT, Codex, and Grok Bot — local and near real time.

Turn Fable or Opus into your agent orchestrator: plan coding work, assign capable Claude, Codex, or Grok agents, and personally verify the r

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и провер

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

Local companion launcher and maintenance toolkit for the Codex desktop app.

HTTP bridge powering OpenClaw's AI agents via Claude Code CLI — manages persistent sessions, auto-resume, extended thinking, and provides a

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember

OpenAI Codex 源码深度研究 (Rust + TS + Python)：2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图