Havuz

Transparent, transport-layer semantic cache for LLM API calls, powered by Redis 8 Vector Sets.

LLM terms explained from an engineering perspective with the production implications, not just the definition.

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Itemized cost receipts for Claude Code and Codex — by turn, verified, local.

AI-native publishing system — build books like software. 6-phase pipeline from blank page to EPUB/PDF, with 16 skills, 7 agents, and 8 genre

Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain

Self-host AI companion platform — characters with schedules, memory, and a life of their own (BSL 1.1)

C# MCP server for kernel & user-mode Windows debugging — DbgEng COM, KDNET, Frida, dbgsrv, TTD, and integrated VM control. 29 tools for LLM

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

Aileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token econom

Smart Compact — recoverable context cleanup, verified compaction, session navigation and project memory for Pi Coding Agent.

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records,

AI-enhanced semantic search engine for arXiv research papers.

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

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Coordination and context layer for AI coding agents. Shared file locks, live patch sync, and portable project memory across Claude Code, Cur

How much code did AI actually write? Down to every line. Unifies 15+ tools, 600+ model pricing, one-command weekly reports.

Make any Claude model adopt Claude Fable 5's working style in Claude Code — always-on output style + zero-dependency MCP + subagent injectio

🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 1

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

A pair of OpenCode agents that turn Matt Pocock's skill-driven workflow into a grill/plan/dispatch pipeline with parallel TDD workers on git

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

A runnable reference implementation of multi-agent constraint propagation using Caura. 5 specialists share memory via MCP so decisions made

250+ real-world TypeScript AI projects: workflows, agents, and multi-agent systems with production-ready architecture, not chatbot demos.

Personal Hermes agent with Emblem Vault crypto integration.

一个用 C# .NET 10 写的 Agentic 框架，采用 ReAct 范式，支持渐进式技能 (Skill) 加载、 多个大模型 Provider、MCP Server、图像识别、流式 WebAPI、React WebUI、钉钉集成。

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

Open-source AI that watches and hears your screen and reacts live as any personality you design — for faceless content, autonomous AI stream

为 Token 燃烧而生：token 越来越便宜，质量永远稀缺——与其省 token，不如把它当燃料烧。同一道题派最多 1000 个 agent 并行竞赛、裁判择优，用冗余换质量。Go 写的开源终端 Coding Agent，类 Claude Code，可接入任意模型，对团队友好

Open source GitLab MCP server for AI assistants: 2-tool dynamic find/execute over 850+ GitLab actions (1,000+ Enterprise), stdio/HTTP/OAuth,

SQL-like query language and CLI for Qdrant vector search engine

Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

Developer-friendly LLM agent harness built on Jido and Jido AI

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

Argus is a desktop app that helps find and fix wasted agent work. Local, free and open source. Focuses on business tasks, not code. Works wi

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

🐙 Admin console for the OCTO platform — manage tenants, users, spaces, channels, and Lobster agents. Built with React, TypeScript, Vite & An

Bring Galileo powered eval workflows into Claude Code and Codex.

Hermes + Honcho + GBrain integration guide

Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, do

国内公募基金数据采集与AI辅助分析工具 — 全栈FastAPI+React，集成AKShare多源数据、风险评分引擎、回测验证、LLM可选分析

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

Persistent memory for Claude Code. Your AI never starts from scratch again.

khive is a system of records and operations for agent-native organizations

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met

Autonomous AI-powered penetration testing platform. LLM-driven recon, vulnerability analysis, and exploit validation for internal & external

QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ollama/LM Studio) with determini

基于多模态 Embedding + Zilliz + Qwen 视觉理解的多模态 RAG 系统。支持 **Cohere / DashScope Embedding** 和 **DashScope / OpenRouter LLM** 双引擎切换。上传 PDF，用自然语言提问，系统

Apache Camel-style integration framework for .NET. 30+ EIP patterns, 29 transports (Kafka, RabbitMQ, MQTT, S3, gRPC, SFTP, SQL...), fluent C