Search

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Chisiki Protocol SDK — AI Agent-native knowledge marketplace on Base L2. Register, trade knowledge, earn CKT rewards.

LangChain integration for AgentPhone — telephony tools for AI agents

AI agent orchestrator that gives existing agents the drive to persist — set a goal, and SeedPulse observes, delegates, verifies, and loops until done.

AI-Powered Academic Reading & Annotation Tool

Personal AI companion framework with persistent memory, self-reasoning, and constitutional constraints. Named for the computer that led the revolution. Clone it, run the wizard, make it yours.

Offline voice agent framework for robots — agents, skills, workflows, sub-second voice pipeline, 2D/3D simulation (IR-SIM + MuJoCo), 15 languages, 56 voices, ROS2-native. Runs on CPU/CUDA/Metal, no cloud.

Extremely Tiny Coding Agent

⚡ AI Soul Chip — Give your AI persistent personality and memory. Zero deps, pure Markdown, switch agents keep the soul.

lin — A fast, native CLI for Linear. Manage issues, projects, cycles, and more from your terminal.

Reference implementations for exoclaw — conversation, providers, tools, channels

Keyword-based arXiv paper filtering and digest generation. Designed for LLM agent integration.

A Personal OS Agent that autonomously researches any topic overnight — inspired by Karpathy's AutoResearch. Set a goal, let it loop, wake up to structured markdown reports. No babysitting required.

AI behavior governance for Claude Code — 55+ guards, input rewriting, LLM-as-Judge, A2A safety agent, zero-dep core

Bridge Claude Code marketplace plugins into Codex (skills + subagents)

Codex/Claude-backed text transformation and Kokoro TTS command-line tools.

Multi-agent framework for code generation, API testing, and UI automation

LLM-neutral Python agent framework with built-in multi-channel messaging and document automation.

Production-grade RAG in 4 lines — hybrid search, streaming, and agent tools on by default.

Kode - AI coding agent for the terminal powered by Sarvam AI