Search

Least-privilege audit for Claude Code: see which permissions you actually use, which are dead weight, and which are dangerous - derived from your real session history.

Venom-themed AI penetration testing framework with 3D Live Avatar, 47 tools, 501 skills, SAST scanner, and brutal Playwright testing.

Autonomous AI-agent orchestration engine for job discovery with decision traces, tool adapters, and production-grade run control.

Portable agentic research stack for Claude Code — multi-agent deep research (ultradeep), best-on-market product research (market-scout), 5-advisor council, divergent ideation, + a one-command installer.

No description available

AERead: an agentic economic environment and benchmark. Multi-agent exchange arenas with welfare-based AER scoring, frozen-panel evaluation, verifiable submissions, and RL hooks

🦾 The Agent Runtime Where Every Thought Is Visible — 7 paradigms, 10 harness shells, zero black boxes.

Install the setup-agent-documents skill for GitHub Copilot.

NexusAgentX distribution of the OpenAI Codex CLI.

OpenAI- and Anthropic-compatible deterministic server for AI agent integration testing

Helllo AI Spark Chat Widget — guided navigation embed for website assistants

Tunnel relay between cloud AI agents and local machines — server relay, local agent, client SDK, JSON-RPC, HMAC signing

Isomorphic TypeScript SDK for invoking Opal agents over a Personal Access Token (PAT). Works in Node and the browser.

Swarm Engine RL — a reinforcement learning framework for training LLM agent swarms.

Microsoft AutoGen tools to charge per agent task via U.CASH (HTTP-402). Non-custodial.

Detect and fix trigger-ambiguity conflicts in agent skill libraries: whole-library LLM analysis, actionable fix suggestions, safe apply with backup, and automatic re-verification.

Agent runtime with tool calling and state management

AI-powered Python unit test generation agent with ReAct architecture

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

Python SDK for the Fire AI Inference API (L1 chat/image, L2 workflows, v2 multi-agent flows)