PicoClaw is an ultra-lightweight personal AI agent platform written in Go, engineered to run on hardware as small as $10 RISC-V boards while providing a full-featured chat agent experience. In production it is a daemon (picoclaw) that connects 30+ LLM providers (OpenAI, Anthropic, Gemini, Azure, Bedrock, Claude CLI, Codex, Ollama, etc. behind a common provider factory) to 19+ messaging channels (Telegram, Discord, WhatsApp, WeChat, WeCom, Slack, IRC, Matrix, DingTalk, Feishu, MQTT, etc.), exposing an agent loop with tool calls, MCP server integration, session management, voice I/O (ASR/TTS), cron jobs, skills marketplace, and hardware tools (I2C, SPI, serial). A companion launcher binary (picoclaw-launcher) runs a Go web backend with an embedded React/TypeScript frontend for configuration, model/channel/credential management, logs, and live chat.\n\nThe architecture is a modular monolith: pkg/agent implements the turn pipeline (context assembly, thinking levels, tool loop, streaming, stop handling), pkg/providers abstracts LLM backends with rate limiting, cooldown tracking, and fallback chains driven by an error classifier, pkg/channels provides a factory-registered channel abstraction over a shared base, and pkg/bus + pkg/events carry inbound/outbound messages and typed runtime events with backpressure. Agents are defined by AGENT.md/SOUL.md workspace files and support delegation/spawning. An experimental evolution subsystem clusters learning records and generates skill drafts via LLM, and the seahorse SQLite FTS5 store provides compacted short-term memory with BM25 retrieval and summary trees. Legacy OpenClaw configs can be migrated.\n\nThe codebase is heavily tested (500+ test files across nearly every package), uses cross-platform build tags for Windows/Linux/Unix/Android, and ships Docker images plus a self-update mechanism. Strong engineering practices include atomic file writes, zip-slip and SSRF protection utilities, typed event buses, factory registries, and a ToolResult structure separating LLM-facing vs user-facing output. The project is pre-1.0 with rapid release cadence; the evolution subsystem, some platform-specific hardware stubs, and the large channel/provider surface are the least mature areas. It is not a data-research repository - the LOCOMO memory benchmark and LLM-as-judge evaluation code in cmd/membench support engineering measurement rather than producing research artifacts.
ChatClaw is a desktop AI assistant application built with Wails v3 (Go backend + Vue 3 frontend) that provides a local-first, multi-platform AI agent experience. It integrates with multiple messaging platforms (WeChat, QQ, DingTalk, Feishu, WeCom, WhatsApp) through gateway adapters and manages AI agents using the CloudWeGo Eino framework. The application features a knowledge base with full-text search (FTS5) and vector embeddings (sqlite-vec), document processing pipeline (parsing, splitting, RAPTOR hierarchical summarization), scheduled tasks with cron execution, a skill marketplace, MCP tool support, and native desktop capabilities like window snapping, floating ball, and text selection popups. It also bundles an OpenClaw Node.js runtime for advanced agent workflows. The frontend is Vue 3 with TypeScript, Pinia, and shadcn-vue UI components. The architecture is a monolith with service-oriented backend and multiple WebView windows. Note: The repo shows signs of hybridity as it includes substantial data/research components (RAPTOR, embeddings, document processing) but these serve the application's core functionality.