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
📦 Teraace Account
Create your Teraace account at https://app.teraace.com/signup
📦 Installation
pip install teraace-tracker
⚡ Quick Start
1. Configuration
Create a .env file:
TERAACE_API_KEY=your_api_key_here
TERAACE_BUFFER_SIZE=20
TERAACE_API_ENDPOINT=https://api.teraace.com/agents
TERAACE_REQUEST_TIMEOUT=30
TERAACE_MAX_RETRIES=3
2. Basic Usage
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
- AGENTS.md - Comprehensive examples for all 20 frameworks
# CrewAI
from teraace_tracker import CrewAITracker
tracker = CrewAITracker()
tracker.track_crew_execution(crew)
# 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: Creation, execution, completion
- Tool Usage: Function calls and results
- Memory Operations: Read, write, update operations
- Multi-Agent Interactions: Handoffs and collaboration
- Code Generation: Generated code and execution
- Planning & Reasoning: Agent thought processes
- Resource Management: File and data operations
🔧 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 |
📚 Documentation
- AGENTS.md - Comprehensive examples for all 20 frameworks
- API Reference - Detailed API documentation
- Configuration Guide - Advanced configuration options
🛠️ Development
git clone https://github.com/teraace/teraace-tracker
cd teraace-tracker
pip install -e .[dev]
pytest
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
📄 License
MIT License - see LICENSE file for details.
🆘 Support
- Documentation: docs.teraace.com
- Email: support@teraace.com
- Issues: GitHub Issues
Metadata
Release files for teraace-tracker 1.1.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| teraace_tracker-1.1.8.tar.gz | 76.8 kB | Without provenance | Details for teraace_tracker-1.1.8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| teraace_tracker-1.1.8-py3-none-any.whl | Python 3 | none | any | Details for teraace_tracker-1.1.8-py3-none-any.whl |
Total release size: 165.4 kB
Release files / teraace_tracker-1.1.8.tar.gz
| Download URL | teraace_tracker-1.1.8.tar.gz |
|---|---|
| Size | 76.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3591211375ed3c3c816ccba5ceb673e0322540b81f11371f257ef2fecec32543
|
|
BLAKE2b-256 checksum How to use checksums |
120ba651174cc118a49e6108ee5b03108ab996e6afcd93f8f94bedd32c5cdf1f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.8
|
Release files / teraace_tracker-1.1.8-py3-none-any.whl
| Download URL | teraace_tracker-1.1.8-py3-none-any.whl |
|---|---|
| Size | 88.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
98ff5d986a4d04cfafddb79b083c605d707c0abf58bda7dde9b205908585efb8
|
|
BLAKE2b-256 checksum How to use checksums |
b002ddc27d09c9fa600eab6bdd211347fc937a3f636d99f9691c037fbf905ebf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.8
|
Security for teraace-tracker 1.1.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.