Havuz

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

🦄 Forge - a local-first, multi-agent software-engineering runtime that runs Claude Code / Codex-style agentic workflows entirely on your own

An open-source AI agent platform for orchestrating, and collaborating with multiple AI agents. Connect seamlessly to GitHub Copilot CLI, Cla

AI security agent for the Python supply chain: scans packages, generates exploits, and validates them in Docker, autonomously.

Coding-agent harness for continuous contribution — discovers, implements & validates your next high-fit change as a review-ready draft PR yo

One CLI to search, provision, and manage cloud GPUs across 10 providers

Local-first AI project OS that turns coding models into reliable software agents with memory, sandboxed execution, verification, recovery, G

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).

End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, ty

🌊 The simple wrapper of leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workf

Visual debugging, execution traces, and observability for AI agents.

100 days, 100 sources: a daily public learning log of modern AI - LLMs, agents, RAG, fine-tuning, MLOps and more. Daily on Threads, X, and B

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

A simple studio to use agent

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro

Agent Skill that turns your coding agent into a keyboard firmware expert. Audits ZMK/QMK keymaps, tunes home row mods, makes trackballs laye

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

Make your specs actually comprehensive. Pair your specs with tests to make your coding agent stop improvising bad code

Python + Terraform. Cloud-ready GraphRAG solution that uncovers distant connections across data and grows incrementally as new documents arr

TSCG - Deterministic tool-schema compilation for LLM agents, including text-mode tool use without native tool calling and context-budget RAG

CareerForge — AI job-search assistant inside Claude Code. /search ranks postings from your portals; /apply tailors a CV + cover letter (post

Meow Agent is an AI companion for Android that can think, plan, and act through registered tools — helping you with notes, files, calendar,

Invarium is pytest for AI agents. Test behavior, not exact text.

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into

Autonomous offensive security agent. Plans engagements, runs recon, chains exploits, and writes reports - end to end. Native to Claude Code,

Online explainability for LangGraph agents through counterfactual planning and reasoning provenance graphs.

A curated collection of skills for AI agents to properly work with datavault4dbt.

Build AI agents using the same architecture patterns as Claude Code. Skill + 6 examples + runnable Python code. No framework.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

AIDLC × AgenticOps — plugin marketplace that extends Claude Code and Kiro with agentic operations for the AWS AI-Driven Development Lifecycl

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation,

htop for local coding agents.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model provide

Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timel

Scan a codebase for AI SDKs, MCP servers and agent tools; map risks to NIST AI RMF, ISO 42001, EU AI Act and the OWASP LLM and Agentic Top 1

SIGN — Sigil Intelligence Graph Notation. The knowledge contract layer for the agentic enterprise. Open specification · Apache 2.0 License

The meta-harness that brings real agentic collaboration as a first-class citizen

A full-stack AI assistant built on Amazon Bedrock AgentCore. This sample demonstrates how to build a feature-rich, self-hosted AI assistant

Gen AI Evaluation Toolkit on AWS is a flexible, cloud-native accelerator built on AWS serverless architecture that enables comprehensive eva

Self-hosted, agentic vulnerability research for binaries & firmware: an AI agent decompiles, fuzzes, and verifies exploits inside a sandbox,

No API keys required. Transform the native ChatGPT, Claude, and Gemini web interfaces into fully autonomous local coding agents.

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Use Gemini CLI with OpenCode through a local planner, reviewer, and session loop with self learning architrecture.

Scaffold production-ready AI agent projects in Python (ReAct, RAG, and Multi-Agent Supervisor) with one CLI command

LazyChat — an AI assistant docked inside your ERPNext desk. Chat with your data, draft reports, stage edits (Apply-gated). Bring your own LL

Enterprise-grade sovereign AI for organizations where SaaS AI isn’t an option.

Local-first Agent RL workbench for Search-R1 rollouts, reward evaluation, GRPO/verl training-data handoff, and an auxiliary private RAG work

20 runnable LLM agent design patterns in Python, benchmarked, traced, offline-compatible. ReAct, multi-agent, constitutional AI, and more.

Desktop terminal for running Claude Code, Codex and Antigravity side by side, with one Inbox for when they need you.