Havuz

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, D

Stateful execution layer for browser agents.

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact out

Automate web workflows on real browser tabs without hosting a browser farm.

Helix is ​​a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creat

5-agent AI team for Claude Code operators: Iris (design), Lyra (build), Echo (scout), Newton (research), Hypatia (critic). One-command insta

AI-powered Lead Qualification & Routing System built with n8n, Gemini and Python.

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.)

spec-builder + harness-bootstrap. Specs both you and the AI understand. An agent team tailored to your repo, derived from your contract and

Repairs predictable tool-call mistakes that often derail open weight models. Supports integration with other extensions' custom tools.

EMNLP 2026 Industry Track | A benchmark for shopping agents on long-horizon tasks with distributed hidden intent.

PikoClaw - Born from the Claude Code leak, a lightweight, Rust-based AI agent engineered for high-performance development

Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes. Wikilinks are the graph, SQLite th

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companion.

CatchBench: a benchmark for auditing agent failures across the full lifecycle.

AI for tactical cycling intelligence: Predictive mud logic, S-Scale terrain analysis, and powered GPX routing

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before t

Single-agent multi-modal system for insurance damage claim verification. #1 globally, HackerRank Orchestrate June 2026 (15,295 registrants).

Let Claude run code on your real machine — safely — from any Claude chat. Bridges Claude Cowork to Claude Code on your Mac/Linux box. One co

Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step reco

Open-source platform for internal AI agents. Your team's knowledge, rules and tools once, used in chat, workflows and your AI assistants.

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a failure by intervening on it.

Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust

Claude Code plugin that makes coding agents measurably cheaper over time: collect token costs, distill candidate rules, benchmark them on a

🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.

OR-Space: a full-lifecycle workspace benchmark for industrial optimization agents

Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.

Spectrum: a deterministic semantic encoding enabling constant-time retrieval primitives

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.

一个将现实议题、规则机制与角色关系转化为可交互多智能体仿真/演绎世界的生成与运行框架。