Havuz

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted,

Self-hosted, distributed, multi-model LLM inference

C2 server fingerprinter — Cobalt Strike, Sliver, Mythic, Havoc, Brute Ratel

OpenXiv is an AT Protocol preprint server with source-based submissions, public provenance, typed endorsements, OAI-PMH, and Bluesky federat

CLI for audio, video, and text transcription with ASR providers and LLM-powered summarization via local or cloud backends.

Discord CLI for AI agents. Manage servers, messages, reactions, threads and monitor events from the terminal.

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

Open a KeePass vault in your browser — no install, no signup. Try the demo in 10 seconds at keewebx.app/app?demo=1. Modern web-only KeePass

BoringOS is the open-source operating system for AI agents - it ships with a shell portal plus installable modules, powered by agentic CLIs.

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM tr

Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind

RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS

并发调用本机 Grok 4.5、Kimi K3 与 Claude Code，带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.

A blog you host yourself, on a small server or on Cloudflare, and an AI agent can run it for you. No algorithm, no ads, no platform in betwe

Organize your AI sessions, and carry what they know into the next one.

Self-hosted PaaS for private infrastructure. Deploy 200+ services on any server in one click. GPU monitoring, AI model management, VRAM c

A self-hosted, privacy-first personal finance app for accounts, budgets, cashflow, goals, and CSV imports.

Kimi for Claude Code, Codex, and DeepSeek Harness: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and

🧑‍💻 CBTI - 程序员行为类型测试 | 你是 SUDO 还是 NULL？30 道题测出你的编程人格。27 种程序员人格类型，融合 Vibe Coding / AI 编程 / 996 / 删库跑路等热梗。Next.js + TypeScript 开发，纯前端无后端。

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

A modern, self-hosted infrastructure management dashboard. Track servers, VMs, disks, IPs, and network connections with a visual 2D work

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

Skill repository to enforce Engineering disclipline in coding assistants

Open-source AI coding agent. Desktop app, bring your own model. Writes code, browses the web, verifies its work. Apache 2.0.

Agent Interface Compiler — One command. Every agent speaks your product. Transform OpenAPI specs into MCP Servers, Skills, CLAUDE.md, AGENTS

Multi-agent architecture for Opencode — cost-optimized model routing, parallel specialist execution, dev tools, and a self-maintaining proje

Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

A cargo subcommand that handles code signing, notarization, and update signatures for Rust binaries across macOS, Windows and Linux

Snowflake AI Kit: Cortex Code plugin for automatic Snowflake routing, envelope-based permission policy, and one-command installers for Snowf

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

Cloak your Claude. Switch identities in seconds.

Turn your ~/.claude history into a shareable Quartz knowledge base.

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

The open-source management system built to stay alive, not rot after the audit. AI-first; documents in git, collaboration in PostgreSQL, shi

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama

Real-time data streaming pipeline built with modern data engineering tools for scalable ingestion, processing, transformation, and analytics

Self-hosted web app for managing art on your Samsung Frame TV. Upload your own images, schedule rotations, browse free sources & control eve

The bedrock layer for AI coding agents. One governance.md. Any project. Never stale. Universal skills + cross-agent compilation (Claude, Cur

让你的 AI 智能体们组成一个团队：在任意宿主里把任务派给本地订阅的 Claude Code / Codex / Grok / Kimi / Antigravity，并行、不打断对话、全走已有订阅。

Multi-provider Web Search & Fetch for DeepSeek Harness — 8 deeply adapted providers, SearchHints, resilient fallback, and native X / Xiaohon

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

Memory-safe, zero-C-dependency Rust Blu-ray disc analyzer — a drop-in BDInfo report tool for BDMV folders and .iso images.

Turn any codebase into an AGENTS.md playbook AI coding agents can actually follow.

Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation

我们的港湾

Grammarly for your terminal — underlines typos in Claude Code, Codex, Aider & any other terminal app

Deja de usar Claude Code como venía en la caja. Semáforo de contexto, modo conciso, 4 hooks que bloquean comandos destructivos y secretos, e

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

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