# Teraace Agentic Tracker
A comprehensive Python library for tracking AI agent events across 20 major agentic frameworks and sending them to the Teraace API for monitoring and analysis.
## 🚀 Features
- **20 Framework Support**: LangChain, CrewAI, AutoGPT, Swarm, LlamaIndex, AutoGen, Phidata, BabyAGI, MetaGPT, TaskWeaver, CAMEL, AgentGPT, SuperAGI, Semantic Kernel, Haystack, Rasa, PydanticAI, DSPy, Mirascope, Instructor
- **Unified Tracking**: Consistent event tracking across all frameworks
- **Production Ready**: Buffered delivery, async API client, graceful shutdown
- **Thread-Safe**: Safe for multi-threaded applications
- **Extensible**: Easy to add new framework integrations
## 📦 Installation
```bash
pip install teraace-tracker
```
## 🔧 Configuration
| Environment Variable | Default | Description |
|---------------------|---------|-------------|
| `TERAACE_API_KEY` | Required | Your Teraace API key |
| `TERAACE_BUFFER_SIZE` | 20 | Events to buffer before sending |
| `TERAACE_API_ENDPOINT` | `https://api.teraace.com/agent-events` | API endpoint |
## ⚡ Quick Start
### 1. Set Environment Variables
Create a `.env` file:
```env
TERAACE_API_KEY=your_api_key_here
```
### 2. Basic Usage
```python
from teraace_tracker import LangChainTracker
# Initialize tracker
tracker = LangChainTracker()
# Use with your LangChain agent
agent = initialize_agent(
tools=your_tools,
llm=llm,
callbacks=[tracker] # Add tracker as callback
)
# Use agent normally - events are tracked automatically
result = agent.run("What is 2 + 2?")
```
### 3. Other Frameworks
```python
# CrewAI
from teraace_tracker import CrewAITracker
tracker = CrewAITracker()
# OpenAI Swarm
from teraace_tracker import SwarmTracker
tracker = SwarmTracker()
# LlamaIndex
from teraace_tracker import LlamaIndexTracker
tracker = LlamaIndexTracker()
# AutoGen
from teraace_tracker import AutoGenTracker
tracker = AutoGenTracker()
# And 11 more frameworks...
```
## 🎯 Supported Frameworks
| Framework | Status | Use Case |
|-----------|--------|----------|
| **LangChain** | ✅ | General-purpose agent framework |
| **CrewAI** | ✅ | Multi-agent collaboration |
| **AutoGPT** | ✅ | Autonomous task execution |
| **OpenAI Swarm** | ✅ | Multi-agent orchestration |
| **LlamaIndex** | ✅ | Data-centric agents & RAG |
| **AutoGen** | ✅ | Multi-agent conversations |
| **Phidata** | ✅ | Production AI assistants |
| **BabyAGI** | ✅ | Autonomous task prioritization |
| **MetaGPT** | ✅ | Software development teams |
| **TaskWeaver** | ✅ | Code-first stateful agents |
| **CAMEL** | ✅ | Communicative agent societies |
| **AgentGPT** | ✅ | Web-based autonomous agents |
| **SuperAGI** | ✅ | Open-source agent infrastructure |
| **Semantic Kernel** | ✅ | Microsoft AI orchestration |
| **Haystack** | ✅ | NLP/RAG with agents |
| **Rasa** | ✅ | Conversational AI |
| **PydanticAI** | ✅ | Production-grade AI applications |
| **DSPy** | ✅ | Prompt optimization framework |
| **Mirascope** | ✅ | Type-safe LLM toolkit |
| **Instructor** | ✅ | Structured data extraction |
## 📊 What Gets Tracked
- **Agent Lifecycle**: Start, end, and error events with execution duration
- **Tool Usage**: Tool calls with names and timestamps
- **Memory Operations**: Read, write, update operations with keys and timestamps
- **Framework Metadata**: Agent framework, model used, runtime environment
- **Session Management**: Unique session IDs for tracking agent runs
- **Error Handling**: Exception types and failure tracking
## 📚 Documentation
- **[AGENTS.md](AGENTS.md)** - Comprehensive examples for all 16 frameworks
- **[API Reference](docs/api.md)** - Detailed API documentation
- **[Configuration Guide](docs/config.md)** - Advanced configuration options
## 🛠️ Development
```bash
git clone https://github.com/hyepartners-gmail/teraace-tracker
cd teraace-tracker
pip install -e .[dev]
pytest
```
## 🤝 Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
## 📄 License
MIT License - see [LICENSE](LICENSE) file for details.
## 🆘 Support
- **Documentation**: [docs.teraace.com](https://docs.teraace.com)
- **Email**: support@teraace.com
- **Issues**: [GitHub Issues](https://github.com/hyepartners-gmail/teraace-tracker/issues)
Raw data
{
"_id": null,
"home_page": null,
"name": "teraace-tracker",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "Teraace Team <dev@teraace.com>",
"keywords": "ai, agents, tracking, monitoring, observability, langchain, crewai, autogpt, llm, machine-learning, analytics, telemetry, agentic, autonomous",
"author": null,
"author_email": "Teraace <support@teraace.com>",
"download_url": "https://files.pythonhosted.org/packages/48/f3/f0ff28a6edf86701f88ee8633e12b56c931d2aa54d2549c545d85b7f8481/teraace_tracker-1.1.1.tar.gz",
"platform": null,
"description": "# Teraace Agentic Tracker\n\nA comprehensive Python library for tracking AI agent events across 20 major agentic frameworks and sending them to the Teraace API for monitoring and analysis.\n\n## \ud83d\ude80 Features\n\n- **20 Framework Support**: LangChain, CrewAI, AutoGPT, Swarm, LlamaIndex, AutoGen, Phidata, BabyAGI, MetaGPT, TaskWeaver, CAMEL, AgentGPT, SuperAGI, Semantic Kernel, Haystack, Rasa, PydanticAI, DSPy, Mirascope, Instructor\n- **Unified Tracking**: Consistent event tracking across all frameworks\n- **Production Ready**: Buffered delivery, async API client, graceful shutdown\n- **Thread-Safe**: Safe for multi-threaded applications\n- **Extensible**: Easy to add new framework integrations\n\n## \ud83d\udce6 Installation\n\n```bash\npip install teraace-tracker\n```\n\n## \ud83d\udd27 Configuration\n\n| Environment Variable | Default | Description |\n|---------------------|---------|-------------|\n| `TERAACE_API_KEY` | Required | Your Teraace API key |\n| `TERAACE_BUFFER_SIZE` | 20 | Events to buffer before sending |\n| `TERAACE_API_ENDPOINT` | `https://api.teraace.com/agent-events` | API endpoint |\n\n## \u26a1 Quick Start\n\n### 1. Set Environment Variables\n\nCreate a `.env` file:\n\n```env\nTERAACE_API_KEY=your_api_key_here\n```\n\n### 2. Basic Usage\n\n```python\nfrom teraace_tracker import LangChainTracker\n\n# Initialize tracker\ntracker = LangChainTracker()\n\n# Use with your LangChain agent\nagent = initialize_agent(\n tools=your_tools,\n llm=llm,\n callbacks=[tracker] # Add tracker as callback\n)\n\n# Use agent normally - events are tracked automatically\nresult = agent.run(\"What is 2 + 2?\")\n```\n\n### 3. Other Frameworks\n\n```python\n# CrewAI\nfrom teraace_tracker import CrewAITracker\ntracker = CrewAITracker()\n\n# OpenAI Swarm\nfrom teraace_tracker import SwarmTracker\ntracker = SwarmTracker()\n\n# LlamaIndex\nfrom teraace_tracker import LlamaIndexTracker\ntracker = LlamaIndexTracker()\n\n# AutoGen\nfrom teraace_tracker import AutoGenTracker\ntracker = AutoGenTracker()\n\n# And 11 more frameworks...\n```\n\n## \ud83c\udfaf Supported Frameworks\n\n| Framework | Status | Use Case |\n|-----------|--------|----------|\n| **LangChain** | \u2705 | General-purpose agent framework |\n| **CrewAI** | \u2705 | Multi-agent collaboration |\n| **AutoGPT** | \u2705 | Autonomous task execution |\n| **OpenAI Swarm** | \u2705 | Multi-agent orchestration |\n| **LlamaIndex** | \u2705 | Data-centric agents & RAG |\n| **AutoGen** | \u2705 | Multi-agent conversations |\n| **Phidata** | \u2705 | Production AI assistants |\n| **BabyAGI** | \u2705 | Autonomous task prioritization |\n| **MetaGPT** | \u2705 | Software development teams |\n| **TaskWeaver** | \u2705 | Code-first stateful agents |\n| **CAMEL** | \u2705 | Communicative agent societies |\n| **AgentGPT** | \u2705 | Web-based autonomous agents |\n| **SuperAGI** | \u2705 | Open-source agent infrastructure |\n| **Semantic Kernel** | \u2705 | Microsoft AI orchestration |\n| **Haystack** | \u2705 | NLP/RAG with agents |\n| **Rasa** | \u2705 | Conversational AI |\n| **PydanticAI** | \u2705 | Production-grade AI applications |\n| **DSPy** | \u2705 | Prompt optimization framework |\n| **Mirascope** | \u2705 | Type-safe LLM toolkit |\n| **Instructor** | \u2705 | Structured data extraction |\n\n## \ud83d\udcca What Gets Tracked\n\n- **Agent Lifecycle**: Start, end, and error events with execution duration\n- **Tool Usage**: Tool calls with names and timestamps\n- **Memory Operations**: Read, write, update operations with keys and timestamps\n- **Framework Metadata**: Agent framework, model used, runtime environment\n- **Session Management**: Unique session IDs for tracking agent runs\n- **Error Handling**: Exception types and failure tracking\n\n## \ud83d\udcda Documentation\n\n- **[AGENTS.md](AGENTS.md)** - Comprehensive examples for all 16 frameworks\n- **[API Reference](docs/api.md)** - Detailed API documentation\n- **[Configuration Guide](docs/config.md)** - Advanced configuration options\n\n## \ud83d\udee0\ufe0f Development\n\n```bash\ngit clone https://github.com/hyepartners-gmail/teraace-tracker\ncd teraace-tracker\npip install -e .[dev]\npytest\n```\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n## \ud83d\udcc4 License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n## \ud83c\udd98 Support\n\n- **Documentation**: [docs.teraace.com](https://docs.teraace.com)\n- **Email**: support@teraace.com\n- **Issues**: [GitHub Issues](https://github.com/hyepartners-gmail/teraace-tracker/issues)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A comprehensive Python library for tracking AI agent events across LangChain, CrewAI, and AutoGPT frameworks",
"version": "1.1.1",
"project_urls": {
"Bug Tracker": "https://github.com/teraace/teraace-tracker/issues",
"Documentation": "https://docs.teraace.com/tracker",
"Homepage": "https://github.com/teraace/teraace-tracker",
"Repository": "https://github.com/teraace/teraace-tracker"
},
"split_keywords": [
"ai",
" agents",
" tracking",
" monitoring",
" observability",
" langchain",
" crewai",
" autogpt",
" llm",
" machine-learning",
" analytics",
" telemetry",
" agentic",
" autonomous"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "5aa8d00184e89dee4282e0f99039c924810873797382b17bdd702e5d65afc221",
"md5": "f31bdf5e798748d3242ec5b36a5a07c4",
"sha256": "73d13cb28b5793eeb7af0ce06c0e48c146e5b591cc1f3abbe4e98e1e2ed7d2a6"
},
"downloads": -1,
"filename": "teraace_tracker-1.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f31bdf5e798748d3242ec5b36a5a07c4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 86213,
"upload_time": "2025-07-25T17:17:46",
"upload_time_iso_8601": "2025-07-25T17:17:46.044673Z",
"url": "https://files.pythonhosted.org/packages/5a/a8/d00184e89dee4282e0f99039c924810873797382b17bdd702e5d65afc221/teraace_tracker-1.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "48f3f0ff28a6edf86701f88ee8633e12b56c931d2aa54d2549c545d85b7f8481",
"md5": "aa4736c270a9a2e72968caeaf45b53c0",
"sha256": "e4e7a9ed98330ab2925811b65cb7d75ac25d4fe7b7b2d45b0283f48c619232fa"
},
"downloads": -1,
"filename": "teraace_tracker-1.1.1.tar.gz",
"has_sig": false,
"md5_digest": "aa4736c270a9a2e72968caeaf45b53c0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 73919,
"upload_time": "2025-07-25T17:17:47",
"upload_time_iso_8601": "2025-07-25T17:17:47.513161Z",
"url": "https://files.pythonhosted.org/packages/48/f3/f0ff28a6edf86701f88ee8633e12b56c931d2aa54d2549c545d85b7f8481/teraace_tracker-1.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-25 17:17:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "teraace",
"github_project": "teraace-tracker",
"github_not_found": true,
"lcname": "teraace-tracker"
}
JSON
