Search

Chrome DevTools for AI Agents — observability SDK for LangGraph, CrewAI, AutoGen

Claude Code, overclocked — multi-account hot-swap, context-threshold handoff, instrumented statusline, and model routing for multi-agent workflows

Scan Agent Skill packages for security threats using multi-agent AI analysis

TamfisGPT Code -- standalone terminal coding agent (calls HF/NVIDIA NIM/OpenRouter/Ollama directly; --remote for the legacy TamfisGPT Remote backend)

A command-line coding agent (OpenAI-compatible API; default NVIDIA Nemotron)

AI model: huihui-ai/Huihui-gemma-4-12B-agentic-fable5-abliterated

AI model: InternScience/Agents-A1-4B

AI model: InternScience/Agents-A1-4B-Q8_0-GGUF

AI model: InternScience/Agents-A1-4B-Q4_K_M-GGUF

AI model: koshuro/qwen2.5-1.5b-tool-use-reasoning-tuned

AI model: KickItLikeShika/olmo-3-7b-think-tooluse-isdf-200steps

AI model: KickItLikeShika/olmo-3-7b-think-tooluse-isdft-500steps

AI model: KickItLikeShika/olmo-3-7b-think-tooluse-isdft-400steps

把整个浏览器交给大模型 | Hand the whole browser to an LLM — 本地开源的浏览器 Agent + 网页逆向工具。observer 架构只把浏览器最新状态暴露给模型:既能点击抓取,又能下 CDP 断点、逆向签名/token/加密、生成脱离浏览器的爬虫。A local browser agent & web reverse-engineering tool with a desktop UI.

MaaFramework-focused skills, MCP integrations, and tooling for AI-assisted automation development.

Autonomous AI agent that turns labeled GitHub issues into pull requests using headless Claude Code - a stateless Go daemon that triages, plans, codes, and ships in isolated git worktrees.

An open-source, context-aware AI Discord moderation bot and community agent. Self-hosted LLM moderator that understands sarcasm and handles automated Q&A.

Provable deletion for AI agent memory: cascade-delete a memory across raw records, embeddings, summaries and caches, then independently verify it's gone and emit a signed receipt.

Autonomous black-box pentester — bring-your-own-model, runs local. 81/113 on OWASP Juice Shop, reproducible.

Codex CLI, overclocked — cold multi-account switching, context-threshold handoff, instrumented statusline, and AGENTS.md routing policy for multi-agent workflows