Skip to content

The original TinyClaw as your personal autonomous AI companion. 🐜

License

Notifications You must be signed in to change notification settings

warengonzaga/tinyclaw

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

262 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Tiny Claw (Mandibles) 🐜

Note

Tiny Claw is NOT a smaller version of OpenClaw. It is a completely independent product and an alternative to OpenClaw. While the original idea and inspiration came from OpenClaw (the lobster 🦞), Tiny Claw (the ant 🐜) has its own mission, architecture, and identity built from the ground up.

GitHub Repo Banner

Your autonomous AI companion.

Warning

🚧 Under Active Development - This project is in heavy development and things will break. Running it now may spoil the experience we're building for you. Please wait for the first official release before trying it out. Follow @TinyClawAI and @warengonzaga on X for launch updates.

AI agents today are powerful but complex, expensive to run, and heavy to set up. Tiny Claw believes AI should be simple, affordable, and truly personal, like having your own Codsworth or AYLA as a helpful friend. It achieves this by being a native framework built from scratch with a tiny core, plugin architecture, self-improving memory, and smart routing that tiers queries to cut costs. The result is an autonomous, self-improving, self-learning, and self-configuring personal AI companion that grows with you over time.

Think of the personal computer revolution. Computers were once reserved for governments, military, and large corporations. Having one meant building it yourself or spending serious money. Then Apple came along and made them personal and accessible to everyone. Tiny Claw does the same for AI agents.

❓ Why Tiny Claw?

Most AI agent frameworks are powerful but heavy. They require expensive subscriptions, complex setup, and are built on top of other frameworks. Tiny Claw takes a different approach. It's built from scratch, cheap to run, and treats you as a friend, not just a user to be served.

Tiny Claw 🐜 Other AI Agent Frameworks
Architecture Native framework, built from scratch Built on existing frameworks (Pi, Claude Code, Codex)
Philosophy Personal companion with its own personality Configurable assistant you shape from scratch
Core size Tiny by design, everything else is a plugin Large monolith that grows over time
Personality Has its own, you can't override it Fully configurable system prompts
Memory Self-improving with temporal decay Flat conversation history
Context 4-layer compaction keeps context small and cheap Unbounded context windows burn tokens
Security Built-in SHIELD.md anti-malware enforcement No native threat model
UI Discord-like web experience out of the box Terminal-only or separate UI dependency
Setup Self-configuring, zero hassle Complex onboarding with multiple dependencies
Runtime Bun-native, single binary Node.js 22+, pnpm, multiple processes
Built-in Provider Ollama Cloud (free sign-up, generous free tier) Requires Claude Pro/Max ($20-200/mo) or API keys
Cost Smart routing slashes LLM spend by tiering queries Every query hits the most expensive model
Routing Adapts to whichever provider plugins you install Hardcoded to a single provider

πŸ’‘ Philosophy

Tiny Claw is inspired by personal AI companions from science fiction like Codsworth from Fallout (the loyal robot butler) and AYLA from Deliver Us Mars (the autonomous drone companion). It's not designed to be your employee or your robot slave. It's designed to be your helpful friend that can assist with your work, your projects, and your daily life, but on its own terms.

The ant metaphor is intentional. A single ant is tiny, but it's autonomous, it learns, it adapts, and it builds something greater over time. That's Tiny Claw. Small by design, mighty by nature. The name "Mandibles" refers to the ant's powerful jaws β€” tiny but capable of carrying many times their own weight.

Core Principles

  • Personal, not enterprise. Built for you, not your org chart. Helps with your work and business as a friend, not as a tool.
  • Tiny core, plugin everything. The core stays minimal. Channels, providers, and tools are all plugins.
  • Self-improving. Learns from every conversation via episodic memory with temporal decay.
  • Self-configuring. No manual config files. The agent configures itself through conversation.
  • Own personality. Ships with a personality (Heartware system) that's uniquely its own.
  • Native, not wrapped. Every component is built from scratch with zero dependency on external AI frameworks.
  • Easy to start. Uses Ollama Cloud with two built-in models β€” kimi-k2.5 (default) and gpt-oss:120b. Choose your model during setup and switch anytime via conversation.
  • Cost-conscious. Smart routing tiers queries across your installed providers. Cheap models handle simple stuff, powerful models only fire when needed.

✨ Features

Feature Description
πŸ’¬ Discord-Like UI Dark-themed web interface inspired by Discord with real-time SSE streaming, typing indicators, inline delegation event cards, and an active agents sidebar
🧠 Adaptive Memory 3-layer memory system (episodic, semantic FTS5, temporal decay) that learns what to remember and forget
πŸ€– Self-Improving Behavioral pattern detection that makes the agent better with every interaction
πŸ”Œ Plugin Architecture Channels, providers, and tools are all plugins. Core stays tiny
🎭 Heartware Personality Built-in personality engine with SOUL.md and IDENTITY.md. It has its own character
🧩 Smart Routing 8-dimension query classifier that adapts to your installed provider plugins, routing simple queries to cheap models and complex ones to powerful ones, cutting LLM costs
πŸ“ Context Compactor 4-layer context compaction pipeline with rule-based pre-compression, shingle deduplication, LLM summarization, and tiered summaries (L0/L1/L2)
πŸ›‘οΈ SHIELD.md Anti-Malware Runtime SHIELD.md enforcement engine with threat parsing, pattern matching, and re-enforce action for built-in anti-malware protection
πŸ”’ 5-Layer Security Path sandbox, content validation, audit log, auto-backup, rate limiting
πŸ—οΈ Delegation System Autonomous sub-agent orchestration with self-improving role templates, blackboard collaboration, and adaptive timeout estimation
πŸ“‘ Inter-Agent Comms Lightweight pub/sub event bus for real-time inter-agent communication with wildcard subscriptions and bounded history
πŸ’Ύ Easy Setup SQLite persistence with Ollama Cloud built-in. Free to sign up and start using immediately
⚑ Bun-Native Built on Bun for maximum performance, minimal footprint
πŸ”„ Provider Fallback Multi-provider support (Ollama, OpenAI, Anthropic) with automatic failover

πŸ›οΈ Architecture

Architecture

Everything above the plugin line is the tiny core. Channels, extra providers, and additional tools live as plugins in plugins/.

πŸš€ Quick Start

Install

bun install

Run

bun start

Open http://localhost:3000. Tiny Claw will walk you through the rest. No config files needed.

Development

bun dev      # Development mode with hot reload
bun build    # Build all packages
bun test     # Run test suite

πŸ”Œ Plugin Development

πŸ“ Project Structure

tinyclaw/
  packages/          Core library packages (tiny, focused, no circular deps)
    core/            Agent loop, database, built-in Ollama provider
    types/           Shared interfaces (leaf dependency)
    config/          Zod-validated configuration engine
    compactor/       Context compaction engine (4-layer pipeline)
    heartware/       Personality engine + safety layers
    memory/          Adaptive memory with episodic + FTS5
    delegation/      Sub-agent orchestration + blackboard
    router/          Smart provider routing (8-dim classifier)
    learning/        Behavioral pattern detection
    sandbox/         Bun Worker code execution
    shield/          Runtime SHIELD.md enforcement + anti-malware
    pulse/           Cron-like proactive scheduler
    queue/           Per-session message locking queue
    intercom/        Pub/sub inter-agent communication
    matcher/         Hybrid semantic matcher (TF-IDF + fuzzy + synonyms)
    logger/          Singleton logger with emoji mappings
    secrets/         Encrypted secrets management (AES-256-GCM)
    plugins/         Plugin discovery and loading
  plugins/           Plugin packages (keep the core tiny)
    channel/         Messaging integrations (Discord, etc.)
    provider/        LLM providers (OpenAI, etc.)
    tool/            Additional agent tools
  src/
    cli/             CLI entry point
    web/             Web UI (Svelte 5, Discord-like experience)

πŸ› Issues

Please report any issues and bugs by creating a new issue here, also make sure you're reporting an issue that doesn't exist. Any help to improve the project would be appreciated. Thanks! πŸ™βœ¨

πŸ™ Sponsor

Like this project? Leave a star! ⭐⭐⭐⭐⭐

Want to support my work and get some perks? Become a sponsor! πŸ’–

Or, you just love what I do? Buy me a coffee! β˜•

Recognized my open-source contributions? Nominate me as GitHub Star! πŸ’«

πŸ“‹ Code of Conduct

Read the project's code of conduct.

πŸ“ƒ License

This project is licensed under MIT License.

πŸ™ Credits

πŸ“ Author

This project is created by Waren Gonzaga, with the help of awesome contributors.

contributors


πŸ’»πŸ’–β˜• by Waren Gonzaga | YHWH πŸ™ - Without Him, none of this exists, even me.

About

The original TinyClaw as your personal autonomous AI companion. 🐜

Topics

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Releases

No releases published

Sponsor this project

  •  

Packages

No packages published