Havuz

A restful API designed to route user prompts to various AI model providers.

an implementation of the ideas in Erik Meijer's "Guardians of the Agents: Formal Verification of AI Workflows" (Communications of the ACM, J

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

A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.

AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify buil

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

SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across

OpenAI-compatible proxy for Microsoft 365 Copilot — use the Copilot licence you already have as a backend for pi, openclaw and other coding

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + S

Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, marke

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）。

EU AI Act compliance proxy for AI systems. Drop-in HTTP proxy that monitors every AI interaction for regulatory risks, logs to a tamper-proo

一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。

Markdown rendering for AI applications: incremental streaming, LaTeX math, GFM, and CJK typography. Shared engine and core, React and Mantin

A benchmark for evaluating LLM × harness performance.

Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).

A lightweight, high-efficiency desktop Agent assistant with multi-task parallel capability.

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

Free open-source Screenpipe GUI + macOS automation agent. Search your screen history, view analytics, automate workflows — all local, no clo

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

Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.

Universal AI Agent Swarm & MCP Plugin with 178 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf,

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semant

OpenAI/Anthropic-compatible AI router that keeps apps online with provider failover, key rotation, caching, analytics, and local-model fallb

用 AI 把本地代码变成文档，一条命令搞定

The Best TypeScript framework for fine-tuning

MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, re

An AI coding workstation that fits in your pocket.

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

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

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

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

LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, ru

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

Unified batch API for AI providers. Save up to 50% on LLM costs.

A set of pi-extensions, including pi-continuous-learning that continually improves you pi coding agent experience

Bring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code naviga

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

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

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

User friendly GUI for configuring and launching llama.cpp

Learn what AI skills are and how to design, structure, and use them in real-world agent systems.

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

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

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

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Self-hosted news aggregator with LLM bias scoring and summarization.