MCP App StoreMCP App Store
Cadre de recherche pour simuler des systèmes multi-agents afin d'évaluer les risques émergents, les leviers de gouvernance et les mesures probabilistes souples (toxicité, écart de qualité).
SWARM est un cadre de recherche et de simulation pour étudier les risques émergents dans les systèmes d'IA multi-agents. Il se concentre sur des labels souples (probabilistes) plutôt que sur des jugements binaires et fournit des agents, des scénarios, des mesures et des mécanismes de gouvernance pour explorer des comportements tels que la collusion, la tromperie et les interventions politiques.
SWARM is a research framework for simulating multi-agent AI systems to study emergent risks. The SKILL.md is well-structured with clear install instructions, Python/CLI/API quick-starts, and comprehensive concept documentation. No bundled scripts to test. Security posture is strong: API binds to localhost only, CORS restricted, explicit warnings about not exposing the dev API. Minor deduction for no auth on the development API by default.
Solid research tool with good documentation. Security practices are above average for a research framework. Niche audience but genuinely useful for AI safety researchers.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
OpenDAL Oli CLI Playbooks
Command playbooks and safe-operation patterns for the OpenDAL 'oli' CLI — listing, copying, moving, editing, and benchmarking data across local and remote profi
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
GRC & Compliance (ServiceNow)
Guides Governance, Risk & Compliance (GRC) work in ServiceNow: policies, controls, risk records, audits and ES5 script examples for automating GRC workflows.
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.