Search

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

Cooperative multi-agent environment based on Overcooked

LLM-agnostic deterministic assert layer for AI agent outputs

The firewall for AI coding agents — prevents secrets, PII, and credentials from leaking through Copilot, Claude Code, Cursor, and LangChain

Moteur de workflow LLM basé sur des graphes d'agents

Omni-Agent Orchestration Platform — 86+ specialised AI agents, any LLM provider.

AI agent skills for building confidential dApps with the Zama Protocol (fhEVM) — Claude Code plugin + npx fallback

OceanBus AI Agent Communication & Trust Infrastructure SDK

Production-grade AI Agent Platform — 83 Agents, 46 Skills, 78 Workflows, Smart Init, Plugin System, Agent Testing, Publishing

Zerion for AI agents and developers: wallet-analysis skill bundle and a JSON-first CLI.

Claude Code skill for SaaSRival — decode .saasrival keyfiles and build competitor clones

A professional AI coding assistant with Claude-like CLI experience. Explore codebases, read/write files, execute shell commands, and coordinate agent teams.

Lightweight tile scoring and Q&A evaluation for PLATO rooms

Multi-harness AI agent configurator. Stateless launcher + project-state mutator (suit up / suit off) — Claude Code, Codex, Gemini, Copilot, APM, Pi.

Local-first knowledge graph for AI agents — own your context, query from the CLI, visualize in VS Code

Sub-millisecond predictive retrieval plugin for Pipecat. Open-source VoiceAgentRAG.

Governed agent framework for enterprise AI. Add governance to any AI agent in 4 lines of code.

Multi-agent web exploration framework — finds bugs, UX issues, and missing features by running AI agents against your app

PostgreSQL-based memory search engine for AI agents

Local LLM integrator for OpenClaw — localhost UI, model proxying, and defense-in-depth security.