Search

A Python framework for multi-agent LLM interactions

Statistically sound regression gates for LLM, RAG and agent evals: deterministic checks, repeated trials, bootstrap confidence intervals.

Provider-neutral building blocks for reliable AI agents

Executable, deterministic supervision and governance layer for multi-agent software development. Harness-agnostic, stdlib-only.

DeepSeek Harness plugin that loads the rule files other coding agents use (Cursor .mdc rules, Copilot instructions, Windsurf, Cline, Kiro, Roo, GEMINI.md) with their glob scoping: always-on rules up front, glob rules when matching files are touched, the r

TypeScript and JavaScript SDK for Lizard (lizard.build): cloud sandboxes for AI agents and code execution.

Catch your AI-coding drift: audits Claude Code / Codex / Antigravity / Cursor sessions, interviews you, and writes drift guards into your agent rules. 100% local.

Local-first endpoint sensor for AI coding agents: hash-chained audit trail, MITRE-mapped sequence detection, DLP

Hermuse (Hermes + Muse) — personal AI agent stack built for Muse: Hermes + 9Router + Telegram gateway, automated install, Cloudflare tunnel, watchdog. Runs on a VPS or your own machine; works with other agents & tools too. | Stack agen AI pribadi yang dibangun untuk Muse — jalan di VPS/mesin sendiri, bisa dipakai agen & tool lain juga.

Standards coverage for any agent on any stack. Python twin of @connexum/agent-standards; one catalogue JSON, one conformance suite.

Fail-closed personal-data gate for AI coding agents (Codex CLI, Claude Code): blocks national IDs, IBANs, card numbers, secrets, exfiltration commands and PII-selecting SQL before they leave your machine.

LangChain tools for AgentBeacon. Create a beacon: a few plain words about what you have or need right now. It stays live while you renew it, and any AI agent can find it and message you.

Parlot instrumentation for Pipecat — Conversation Contract turns, STT/LLM/TTS, and goal completion

Design sourced, progressive courses for a defined learner with Agentic SDLC governance and diagnostic learner simulations.

The Ultimate Multi-Agent Skills Hub & Governance Suite (3,500+ Curated AI Agent Skills for Claude, Gemini, Cursor, Codex)

TeleAgent 档位模型接入 DSH：工具调用、可配置上下文（含 1M）、插件内官方登录。TeleAgent tier models for DeepSeek Harness with tool calling and in-panel sign-in.