A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Sandbox any AI agent in seconds - zero setup, zero latency.

Desription for lab1

Evaluation of Multi-Agent Systems on Cloud Run with the GenAI Client in Vertex AI SDK

🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

An interactive web visualizer for Antigravity AI agent JSONL execution transcripts.

Native macOS app: drop a long video → auto-cut viral shorts, captioned for TikTok/Reels/YouTube, reframed to vertical, and scheduled. 100% on-device (Gemma 4 12B + WhisperKit + MLX).

An open source distributed agent runtime

Python tool for converting files and office documents to Markdown.

An (experimental) CLI for the Gemini API

A Python library for building AI agents that leverage the full power of Google Antigravity.

Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal.

antigravity skills for marketing

🛠️ Awesome tools & guides for harness engineering.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.

Agent Skills for Google products and technologies

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

A rugged, high-quality configuration suite for AI Agents on Gemini CLI.

The agent that grows with you

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

An agentic skills framework & software development methodology that works.

OpenAgents - AI Agent Networks for Open Collaboration

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

An obsidian plugin to interact with Google Gemini

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.