meerkat

<p align="center">
  <img src=".github/meerkat-logo.png" alt="Meerkat" width="280">
</p>

<h1 align="center">Meerkat</h1>

<p align="center">
<strong>A modular, high-performance agent harness built in Rust.</strong>
</p>

<p align="center">
  <a href="#quick-start">Quick Start</a> &bull;
  <a href="#capabilities">Capabilities</a> &bull;
  <a href="#surfaces">Surfaces</a> &bull;
  <a href="#examples">Examples</a> &bull;
  <a href="https://docs.rkat.ai">Docs</a>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/Rust-1.94+-orange?logo=rust" alt="Rust 1.89+">
  <img src="https://img.shields.io/badge/License-MIT%2FApache--2.0-blue" alt="License">
</p>

---

## Why Meerkat?

Meerkat is a **library-first, modular agent harness** -- composable Rust crates that handle the hard parts of building agentic systems: state machines, retries, budgets, streaming, tool execution, MCP integration, and multi-agent coordination.

It is designed to be **stable** (deterministic state machine, typed errors, compile-time guarantees) and **fast** (<10ms cold start, ~20MB memory, single 5MB binary).

The library comes first; surfaces come second. The CLI, REST API, JSON-RPC server, MCP server, Python SDK, and TypeScript SDK are all thin layers over the same engine. Pick the entry point that fits your architecture.

### How it compares

| | Meerkat | Claude Code / Codex CLI / Gemini CLI |
|---|---|---|
| **Design** | Library-first -- embed in your service | CLI-first -- interactive terminal tool |
| **Providers** | Anthropic, OpenAI, Gemini + self-hosted (Ollama, vLLM, LM Studio) | Single provider |
| **Modularity** | Opt-in subsystems, from bare agent loop to full harness | All-or-nothing |
| **Surfaces** | CLI, REST, JSON-RPC, MCP server, Rust/Python/TS SDKs | CLI + SDK |
| **Agent infra** | Hooks, skills, semantic memory across sessions | File-based context |
| **Multi-agent** | Sub-agents, peer-to-peer comms, mob orchestration | Single agent |
| **Portable deployment** | Si