Research & Data

Apply ML training loops to prompt engineering — run evals, LLM-grade outputs, and track pass rates to iteratively improve Claude Code skills

Hermes AI agent market-analysis skills (crypto / saham IDN / forex+commodity). Pluggable per-asset analyzers used by the Hermes agent.

Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

Security scanner and hardener for agentic AI installations - OpenClaw, MCP servers, and AI agent skill ecosystems

Codex-native security review skill for authorized repositories and web apps.

Reusable AI agent skills for application development, data, architecture, domain modelling and delivery workflows.

An AI-powered, multi-agent job discovery platform that parses resumes, dynamically searches global job boards, and uses advanced LLMs to semantically match candidates to roles while generating tailored cover letters and skill gap analyses.

Local-first, AI-augmented CISSP companion with a knowledge base that grows with you (resources → kb → wiki). Webapp + 11 Claude Code skills. Two modes: exam-prep tutor for candidates, senior security counsel for certified pros.

Local-first AI jury skill: 9 seats deliberate, 10 scoring functions audit claims, human final.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Korra — персональный AI-агент. Self-hosted на твоём VPS. BYOK (Anthropic / OpenRouter / OpenAI). Telegram + 15 платформ, multimodal, full skill system. Fork Hermes Agent от Nous Research.

Senior-QA-shaped MCP server + skills library: pre-coding QA planning, TDD scaffolding, mutation-testing follow-up, code review, test-data discovery. Iron-Law-enforced workflows for Claude Code, Cursor, Codex, OpenCode, JetBrains, VS Code + Copilot.

Autonomous AI research digest agent with multi-agent workflow

AI-driven beam management system that detects signal degradation under user mobility, scans/selects better beams, and restores link quality through a closed-loop agent workflow using FastAPI, React, and modular sensing, decision, control, and evaluation components.

“VCR for agent tools” / Agent Replay

AI Agent Workflow Framework - 基于大语言模型的智能体工作流编排框架，支持多模型调度、RAG 检索增强生成与多模态任务处理

Competitive pricing & feature analysis — 14 direct auto-dealership AI agent / workflow competitors

Autonomous AI agentic workflow for Japanese convertible bond arbitrage — Tsiveriotis-Fernandes binomial tree pricer with Monte Carlo for reset features, real Refinitiv data, daily scheduled runs, dashboard with backtest results.

An AI-powered system for autonomous incident detection, diagnosis, and remediation in high-performance computing (HPC) environments. Leverages agentic workflows, RAG-based knowledge retrieval, and ML on log data to reduce downtime and enhance reliability. Features runbooks for HPC issues like disk failures, memory errors, and network timeouts.

This project implements a simple AI-assisted File Analysis Agent that reads text files, computes word frequency statistics, and produces short extractive summaries.

A set of Mastra AI agent workflows to evaluate conference proposals (CFPs) and speakers

Store and search AI agent conversations to recover lost context and improve memory persistence in multi-agent workflows.

Automate AI research with multi-agent workflows that search literature, run code, and analyze results with FastAPI and LangGraph

Run multi-agent AI research, manage experiments, and execute GPU workflows in one open source lab.