Chat-rs, yet another LLM provider
Yet another LLM SDK when async-openai and llm-chain already exist.
Your own AI assistant, speak like a cat.
Runs agents on Pi and understands OpenClaw's internals; but OpenClaw exists and this stays local.
Hobbyists, Raspberry Pi users, developers wanting to understand agent patterns without complexity
OpenClaw · LangGraph · CrewAI
Pickle is yelling for food right now. She does this 8PM everyday.
Cookie was her step-brother. The chill one. He lives somewhere else now.
So I reunited them in code - Pickle handles the chat, Cookie handles the memories. They're still together.
---
Okay, enough cat story.
I built *pickle-bot* - yet another lightweight OpenClaw alternative.
OpenClaw is incredible, but I wanted to understand how agents work. So I built my own: - Runs on Raspberry Pi - A clean and manageable codebase - Create agents, add skills, schedule crons - Chat via CLI, Telegram, Discord - Web Search, API server, all good stuff.
*Chatting with "Pickle" while Pickle yells at me? Just so much fun.*
Check the repo: [pickle-bot](https://github.com/zane-chen/pickle-bot)
Pickle is mine. Bring your own cats :)
Yet another LLM SDK when async-openai and llm-chain already exist.
Multi-wave code review with 20+ specialists reading each other's findings before final analysis.
Single binary agent with JSON-RPC extensions beats complex npm installs.
Yet another observability stack when Grafana and Honeycomb already dominate the market.
S3-backed Kafka eliminates broker state management; inspired by Warpstream but open-source.
Per-agent container isolation with separate networks beats shared-instance chaos.