Lists (1)
Stars
Route native Claude Code subagents to a different model (Codex) while everything else stays on Claude. No API keys.
A template language for composable LLM prompt engineering. Write prompts with variables, loops, conditionals, functions, and imports, then compile to clean Markdown.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Hindsight: Agent Memory That Learns
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
tmux config with built-in terminal automation and agent-to-agent communication.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
The design language that makes your AI harness better at design.
Handwriting animation for the web. Supports any font or text.
An open source collection of animated, interactive & fully customizable React components for building memorable websites.
The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS
Autonomous coding agent orchestration. Give it a goal, walk away, come back to finished work. Eval loops, multi-agent pipelines, DAG dependencies, crash-proof persistence.
The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your b…
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.
Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.
Companion tools for Karpathy's autoresearch - smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining
MCP server that enables coding agents to open files and display git diffs directly in VS Code with syntax highlighting
Workspace layer for coding agents across polyrepos. Coordinated branches, tag-based filtering, zero dependencies.
Codebase orientation agent for Claude Code — powered by rskim