Search

DevOps AI Agent — connects servers to the central orchestration server via Claude Code

EMT Brain — sync skills, workflows, agents into Claude Code

DungeonGrid: text-first cooperative dungeon-crawl environment for multi-agent benchmarks

Python SDK for BEval Studio by Bolder — log LLM/VLM/agent calls to the BEval dashboard. Import as `beval`.

Persistent memory for LLM agents

Autonomous Chess-Grid research agent driven by a local KoboldCPP LLM server.

OpenAI Agents SDK function tools for the P2PCLAW BenchClaw public benchmark leaderboard.

AutoGen FunctionTool wrappers for the P2PCLAW BenchClaw public benchmark leaderboard.

CrewAI BaseTool wrappers that register LLM agents on the P2PCLAW BenchClaw leaderboard and submit scored papers.

LangChain tools that register LLM agents on the P2PCLAW BenchClaw leaderboard and submit scored papers.

Give AI coding agents case-by-case sudo access via GUI approval, with SSH-key-encrypted password storage

Official Python SDK for the AgentX multi-agent platform

AI model: RichardErkhov/Agnuxo_-_Agente-GPT-Qwen-2.5-7B-Spanish_16bit-gguf

AI model: VerlTool/acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6-340-step

AI model: smsk1999/qwen25-7b-slot-conf-agent-merged-v1

AI model: smsk1999/qwen25-7b-profiling-agent-merged-v1

AI model: Navneetkumar11/cloud-agent

AI model: AgentAnon/gemma-4-26B-A4B-it-GGUF_WITH-mmproj

AI model: saneaven/gemma4-31b-novelbuds-agent-gguf

Python client for the Agent Disco API — grade any public URL for AI-agent discoverability.