Skip to main content
Vision: To build the ultimate lightweight, secure, and fully autonomous AI Agent infrastructure. Automate the mundane, unleash your creativity.

1. Core Optimization: Extreme Lightweight

Our defining characteristic. We fight software bloat to ensure PicoClaw runs smoothly on the smallest embedded devices.

Memory Footprint Reduction

Goal

Run smoothly on 64MB RAM embedded boards (e.g., low-end RISC-V SBCs) with the core process consuming < 20MB
Context: RAM is expensive and scarce on edge devices. Memory optimization takes precedence over storage size. Action Items:
  • Analyze memory growth between releases
  • Remove redundant dependencies
  • Optimize data structures
See GitHub Issue #346 for details

2. Security Hardening: Defense in Depth

Paying off early technical debt. We invite security experts to help build a “Secure-by-Default” agent.

Input Defense & Permission Control

Harden JSON extraction logic to prevent LLM manipulation
Strict parameter validation to ensure generated commands stay within safe boundaries
Built-in blocklists for network tools to prevent accessing internal IPs (LAN/Metadata services)

Sandboxing & Isolation

  • Filesystem Sandbox: Restrict file R/W operations to specific directories only
  • Context Isolation: Prevent data leakage between different user sessions or channels
  • Privacy Redaction: Auto-redact sensitive info (API Keys, PII) from logs and standard outputs

Authentication & Secrets

  • Crypto Upgrade: Adopt modern algorithms like ChaCha20-Poly1305 for secret storage
  • OAuth 2.0 Flow: Deprecate hardcoded API keys in the CLI; move to secure OAuth flows

3. Connectivity: Protocol-First Architecture

Connect every model, reach every platform.

Provider Architecture Upgrade

Protocol-Based Classification

Refactor from “Vendor-based” to “Protocol-based” classification (e.g., OpenAI-compatible, Ollama-compatible)
Status: In progress by @Daming, ETA 5 days Local Models:
  • Deep integration with Ollama
  • Support for vLLM
  • Integration with LM Studio
  • Mistral local inference
Online Models:
  • Continued support for frontier closed-source models
See GitHub Issue #283 for details

Channel Expansion

IM Matrix Support:
  • QQ
  • WeChat (Work)
  • DingTalk
  • Feishu (Lark)
  • Telegram
  • Discord
  • WhatsApp
  • LINE
  • Slack
  • Email
  • KOOK
  • Signal
Standards:
  • Support for the OneBot protocol
  • Native handling of images, audio, and video attachments
See GitHub Issue #348 for attachment support

Skill Marketplace

Discovery Skills

Implement find_skill to automatically discover and install skills from registries
See GitHub Issue #287 for details

4. Advanced Capabilities: From Chatbot to Agentic AI

Beyond conversation—focusing on action and collaboration.

Operations

MCP Support

Native support for the Model Context Protocol (MCP)

Browser Automation

Headless browser control via CDP (Chrome DevTools Protocol) or ActionBook

Mobile Operation

Android device control (similar to BotDrop)

Multi-Agent Collaboration

1

Basic Multi-Agent

Implement basic multi-agent coordination Issue #294
2

Model Routing

Smart routing — dispatch simple tasks to small/local models (fast/cheap) and complex tasks to SOTA models (smart) Issue #295
3

Swarm Mode

Collaboration between multiple PicoClaw instances on the same network Issue #284
4

AIEOS

Exploring AI-Native Operating System interaction paradigms Issue #296

5. Developer Experience (DevEx) & Documentation

Lowering the barrier to entry so anyone can deploy in minutes.

QuickGuide (Zero-Config Start)

Interactive CLI Wizard

If launched without config, automatically detect the environment and guide the user through Token/Network setup step-by-step
See GitHub Issue #350 for details

Comprehensive Documentation

Platform Guides:
  • Windows
  • macOS
  • Linux
  • Android
Step-by-Step Tutorials:
  • “Babysitter-level” guides for configuring Providers and Channels
AI-Assisted Docs:
  • Using AI to auto-generate API references and code comments (with human verification to prevent hallucinations)

6. Engineering: AI-Powered Open Source

Born from Vibe Coding, we continue to use AI to accelerate development.

AI-Enhanced CI/CD

Integrate AI for automated linting and code quality checks
Automatic labeling and categorization of pull requests
Optimize bot interactions to keep PR timelines clean
AI agents to analyze incoming issues and suggest preliminary fixes

7. Brand & Community

Logo Design

Mantis Shrimp Logo

We are looking for a Mantis Shrimp (Stomatopoda) logo design!
Concept: Needs to reflect “Small but Mighty” and “Lightning Fast Strikes”

Call for Contributions

We welcome community contributions to any item on this roadmap! Please comment on the relevant Issue or submit a PR. Let’s build the best Edge AI Agent together!

GitHub Issues

Browse open issues and pick one to work on

Contributing Guide

Read our contribution guidelines

Build docs developers (and LLMs) love