Havuz

将 Wind 丰富的金融数据、专业工具、技能Skill与专家Agent能力开放给各类 Agent 和智能应用。通过 MCP、Skill、API 等标准化方式，为不同场景下的 Agent 提供股票、债券、基金、期货、期权、宏观、行业、新闻、研报、会议等全市场、全资产、全品类资讯能力

本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr，离线可用，LLM 智能润色. Open-source speech-to-text with LL

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

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

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,

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

Capri from Cyberpunk: Edgerunners 2 living on your desktop. A local AI desktop companion: talks, remembers you, DJs your music. 100% local,

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

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

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

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

AI中转站质量监控 · 模型验真 · Token成本优化 — RelayRadar 中转雷达

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

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

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

A Unified Memory Benchmark Suite for Memory-Augmented Agents

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

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

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

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deploy

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

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

Say "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. 麦当劳点餐 Skill.

A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to

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

Second yourself. One agent that remembers you, with many hands to act for you: a multi-agent harness (Claude Code, with Codex helpers), a se

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

Rust CLI that converts EPUBs into a single YAML-headed Markdown file with per-chapter byte and line offsets, giving LLM agents a navigation

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Voice for the Linux desktop: dictation, read-aloud, and voice-driven LLM commands. Wayland & X11: Hyprland, Sway, Niri, GNOME, KDE. Cloud or

The Best TypeScript framework for fine-tuning

Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with se

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hos

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a

Security scanner for Agent Skills — uncover hidden threats before deployment.

Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with

Mutual-credit coordination for contributing spare LLM subscription capacity through GitHub issues and pull requests.

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,

基于 LLM 的智能求职助手：AI 岗位匹配 + 千岗千面招呼语 + 自动投递（Edge/Chrome 扩展）

A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

AI Engineering Runtime for Professional Developers — terminal coding agent with IOSM methodology, MCP, checkpoints, orchestration, and exten

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, rout

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.