Havuz

Open-source multi-agent AI marketing team with personas, shared memory, 130+ skills, and Docker deploys for Railway and DigitalOcean

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

The Conifer SDK — one gateway for cloud, local, and BYOK inference, with exact per-call cost receipts. TypeScript + Python + MCP.

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers pe

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the me

A statistical code analyzer built from your repository's history.

Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code

A high-throughput training framework for Speculative decoding models.

Find the best AI models you can run

a LLM inference engine to run on consumer hardware

Floating traffic light for AI coding agents (know when your agent is idle, thinking, or writing)

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

Self-hosted AI marketing platform. Like Google Pomelli, but open source, model-agnostic, and actually ships to your social media.

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

把蓝湖设计稿整理成让 AI 生成代码还原页面的上下文

Turn dense long-form ideas into immersive Reading Editions.

Open-source AI social media post generator — production-ready Next.js SaaS with live platform mockups for LinkedIn, Twitter/X, Instagram, Fa

Small, independent TypeScript packages for LLM plumbing — token budgets, streaming JSON repair, cost accounting, retries, embedding caches.

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

Ollama Model Test - Figure out the best model for the task

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

Rust inference engine for a 28.9M-parameter PLE TinyLM on the ESP32-S3 — 9.4 tok/s, faster than the C implementation it was ported from

The most powerful open-source TradingView AI agent. 50 tools, 15 models (Claude, GPT, Gemini, Qwen, DeepSeek, MiniMax), Pine Script v6, quan

All-in-one open-source framework & middleware for enterprise-grade multi-tenant and multi-tier XaaS Services development

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Private AI that works with your files.

核弹，椅子，瘫坐！DSH新预设模式“工程模式”，只需要你说出“请帮我完成一个机械臂”，你的AI模型靠内部的工作流，按照要求完成对应机械的设计，完全实现“AI设计机械，无需人工干预”的场景！(测试版本：SW ：2025 DSH:0.2.2 rc1 ）（如果您对此项目感兴趣，请加

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes

面向 LLM 训练数据生产的可信工作台：AI 提供证据、人类裁决，append-only 账本、可复现导出、评测关卡与 MCP Server。

Инженерный skill для проектирования, реализации, отладки и оценки AI-агентов в Codex и Claude Code по книге Bojie Li.

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request,

Advertising prompt agent for Image2: turns business briefs and reference images into debranded, production-ready image prompts.

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Browse, search, and export your Antigravity AI conversations — VS Code Extension

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

Protokół dla polskiej inteligencji.

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

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional

A Socratic supervision layer for AI coding agents.

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c

Local-first reading workspace for technical papers — select an equation, figure, or passage and get grounded, step-by-step walkthroughs (wit

A terminal coding interface that brings the DeepSeek Harness kernel's full capability set — special modes, plugins, model & subagent managem

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

Longitudinal relational modeling for reflective agents: behavioral signals, evolving subject profiles, inspectable runtime governance.

Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid se