Havuz

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Store every accomplishment. Tailor every application. Own your career data.

CLI text optimizer built on GEPA. Uses Agentic Coding CLI's as mutator and observer -- no api keys required

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence

Two source-verified AI-agent skills that turn project code into traceable business-rule documents (whole-project + single-module). Graph-gui

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

AI-driven Azure operations workbench. Chat with your tenant, investigate incidents with a team of specialist AI agents, and assess, monitor

Native Android client for the Hermes agent gateway — chat plus full management (sessions, models, cron, usage, messaging) over Tailscale, VP

Local-first AI job-application agent: it tracks every application after you apply, explains failures with per-field evidence, and answers qu

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server

Use GitHub Copilot as a local OpenAI/Anthropic-compatible API for Codex CLI, Claude Code, and Continue.

Hand it off. Walk away. Return to results.

13 prompts to control how Claude communicates — choose your style, cut the noise.

A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern

LLM-driven crypto trading bot built on CCXT plus backtesting tools. Multi-exchange, multi-provider, paper-trade first.

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, a

Private AI that works with your files.

Strips the AI tells out of prose, code, and academic writing. 152 patterns from real AI-vs-human analysis, two-pass rewrite, three-tier scor

Small, modular coding-agent harness for Node.js

AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6 AI providers (OpenAI/DeepSeek

Fastest way to scaffold your LLM powered personal knowledge base - Obsidian, Claude Code, qmd, Github

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

Animated, procedurally generated agent avatars for React Native.

Dont guess. Simulate. Multi-agent market prediction engine.

A pure frontend, backend-free third-party SillyTavern.

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by a

Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model

One command to cut token usage by up to 50%+

Generative UI for LLMs using Markdoc {% %} tag syntax

ASD-STE100 Simplified Technical English as a plugin for Claude Code, Codex & coding agents — clearer, unambiguous LLM output

RepoPilot AI is a single-page web application that uses AI to analyze GitHub repositories and provide instant insights into architecture, te

确定性取证 × 大模型定性 × Agent 反证复核的恶意代码审计智能体 · Deterministic forensics × LLM verdict × agent falsification for malicious-code audits

An AI native macOS reader. Built for professional reader.

Run AI models on Apple Silicon and Raspberry Pi

Architecture search beyond the search space: an LLM writes architecture programs, population-based evolution decides which survive. Referenc

Turn your AI coding agent into a tutor. It learns your level and adapts to you

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

Agent dashboard runs reliability scans, skills, and network access probes.

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

Behavioral testing for AI agents.

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

A minimal local coding agent built on the CloudWeGo eino framework — the framework-variant sibling of mini-coding-agent-go.

Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic sco

智能终端命令助手 — 用自然语言生成 Shell 命令，支持 OpenAI/Claude/Gemini/Ollama 等多后端