OpenTeddy Logo

OpenTeddy

A free, Claude-like agent

Local models + skills + a dash of commercial LLM

Python 3.11+ FastAPI Ollama Claude MIT License
⭐ Star on GitHub Learn More

Our Mission

Build a free, Claude-like experience that anyone can run at home. We achieve this by mixing three powerful layers:

🏠

Local Models

Gemma / Qwen via Ollama handle planning and execution — no per-token cost, no data leaving your machine.

⚡

Skills

Turn repeated work into Python functions, eliminating LLM calls after the second or third run.

🚀

Claude Escalation

Commercial model pulled in only when local path genuinely can't finish — timeouts, failures, low confidence.

The result: high capability at a fraction of the cost of calling a frontier model for every single step.

Key Highlights

🏠

Local-First

Planning and execution run on your machine via Ollama

🔄

Auto-Escalation

Timeouts and failures trigger Claude intervention automatically

🌱

Self-Growing Skills

Repeated tasks become reusable Python skills, cutting LLM calls

📊

Web Dashboard

Submit tasks, watch tool calls stream live, manage settings

👤

Human-in-the-Loop

High-risk shell commands pause for approval before running

🧠

Persistent Memory

ChromaDB-backed long-term memory feeds context into future plans

See It In Action

Powerful capabilities that save you money while enabling unlimited creativity

💰 Save Your Money

Track your token usage and see exactly how much you're saving compared to using GPT-4 for every task. The hybrid approach keeps costs low while maintaining high quality.

  • ✓ Real-time cost tracking
  • ✓ Compare with GPT-4 pricing
  • ✓ See savings accumulate over time
Save Money Dashboard
Sales Report Generation

📊 Generate Reports

Automatically generate comprehensive reports from your data. OpenTeddy can analyze, visualize, and create professional documents.

  • ✓ Data analysis and visualization
  • ✓ Automated report generation
  • ✓ Professional formatting

🧪 Testing & Development

Handle complex development tasks including testing, debugging, and data processing. Skills grow automatically to handle repeated workflows.

  • ✓ Automated testing workflows
  • ✓ Data processing pipelines
  • ✓ Self-improving skills
Testing Data Processing

Architecture

User Goal

🎯 Orchestrator (Gemma)

  • • Decomposes goal into ordered SubTasks
  • • Retrieves long-term memory for context
  • • Drives execution + escalation loop

⚙️ Executor (Qwen)

  • • Runs matching Skill if available
  • • Uses tools: shell, file, http, db, gcp, package
  • • Falls back to LLM inference
  • • Reports confidence (clamped on hard failures)

low confidence | timeout | failure signal | unhealthy

🚀 Escalation Agent (Claude)

  • • Resolves hard subtasks with full diagnostics
  • • Synthesises the final summary

🏭 Skill Factory (Claude)

  • • Generates new Python skills on demand
  • • Promotes skills after N successes
  • • Saves skills to disk + SQLite DB

Platform Support

✅

macOS

Intel / Apple Silicon - Fully supported

✅

Linux

Any distro with Python 3.11+ and Ollama

⚠️

Windows (native)

Partial support - WSL2 recommended

✅

Windows (WSL2)

Fully supported - behaves like Linux

Ready to Get Started?

OpenTeddy is a solo side-project trying to prove that a small open stack can get close to the big commercial agents.

⭐ Star on GitHub 📚 Quick Start Guide

⭐ Star the Repo

The single biggest encouragement for the project

🐛 Open an Issue

Report bugs or share feedback

🧠 Share a Skill

Contribute your custom skills via PR