Spaces:
Running
Running
Commit
Β·
8dccf7d
1
Parent(s):
e7b14e6
docs: Add open source foundation section to README and app.py
Browse filesAdd comprehensive documentation about the foundational open-source projects:
- TraceVerde (genai_otel_instrument) - OTEL instrumentation
- SMOLTRACE - Agent evaluation engine
This provides important context about the complete ecosystem that powers
TraceMind-AI and gives proper credit to the underlying projects.
README.md
CHANGED
|
@@ -24,6 +24,24 @@ Agent Evaluation Platform with MCP-Powered Intelligence
|
|
| 24 |
|
| 25 |
TraceMind-AI is a comprehensive platform for evaluating AI agent performance across different models, providers, and configurations. It provides real-time insights, cost analysis, and detailed trace visualization powered by the Model Context Protocol (MCP).
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## Features
|
| 28 |
|
| 29 |
- **π Real-time Leaderboard**: Live evaluation data from HuggingFace datasets
|
|
|
|
| 24 |
|
| 25 |
TraceMind-AI is a comprehensive platform for evaluating AI agent performance across different models, providers, and configurations. It provides real-time insights, cost analysis, and detailed trace visualization powered by the Model Context Protocol (MCP).
|
| 26 |
|
| 27 |
+
### ποΈ **Built on Open Source Foundation**
|
| 28 |
+
|
| 29 |
+
This platform is part of a complete agent evaluation ecosystem built on two foundational open-source projects:
|
| 30 |
+
|
| 31 |
+
**π TraceVerde (genai_otel_instrument)** - Automatic OpenTelemetry Instrumentation
|
| 32 |
+
- **What**: Zero-code OTEL instrumentation for LLM frameworks (LiteLLM, Transformers, LangChain, etc.)
|
| 33 |
+
- **Why**: Captures every LLM call, tool usage, and agent step automatically
|
| 34 |
+
- **Links**: [GitHub](https://github.com/Mandark-droid/genai_otel_instrument) | [PyPI](https://pypi.org/project/genai-otel-instrument)
|
| 35 |
+
|
| 36 |
+
**π SMOLTRACE** - Agent Evaluation Engine
|
| 37 |
+
- **What**: Lightweight, production-ready evaluation framework with OTEL tracing built-in
|
| 38 |
+
- **Why**: Generates structured datasets (leaderboard, results, traces, metrics) displayed in this UI
|
| 39 |
+
- **Links**: [GitHub](https://github.com/Mandark-droid/SMOLTRACE) | [PyPI](https://pypi.org/project/smoltrace/)
|
| 40 |
+
|
| 41 |
+
**The Flow**: `TraceVerde` instruments your agents β `SMOLTRACE` evaluates them β `TraceMind-AI` visualizes results with MCP-powered intelligence
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
## Features
|
| 46 |
|
| 47 |
- **π Real-time Leaderboard**: Live evaluation data from HuggingFace datasets
|
app.py
CHANGED
|
@@ -1,6 +1,23 @@
|
|
| 1 |
"""
|
| 2 |
TraceMind-AI - Agent Evaluation Platform
|
| 3 |
Enterprise-grade AI agent evaluation with MCP integration
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"""
|
| 5 |
|
| 6 |
import os
|
|
|
|
| 1 |
"""
|
| 2 |
TraceMind-AI - Agent Evaluation Platform
|
| 3 |
Enterprise-grade AI agent evaluation with MCP integration
|
| 4 |
+
|
| 5 |
+
Built on Open Source Foundation:
|
| 6 |
+
π TraceVerde (genai_otel_instrument) - Automatic OpenTelemetry instrumentation
|
| 7 |
+
for LLM frameworks (LiteLLM, Transformers, LangChain, etc.)
|
| 8 |
+
GitHub: https://github.com/Mandark-droid/genai_otel_instrument
|
| 9 |
+
PyPI: https://pypi.org/project/genai-otel-instrument
|
| 10 |
+
|
| 11 |
+
π SMOLTRACE - Agent evaluation engine with OTEL tracing built-in
|
| 12 |
+
Generates structured datasets (leaderboard, results, traces, metrics)
|
| 13 |
+
GitHub: https://github.com/Mandark-droid/SMOLTRACE
|
| 14 |
+
PyPI: https://pypi.org/project/smoltrace/
|
| 15 |
+
|
| 16 |
+
The Flow: TraceVerde instruments β SMOLTRACE evaluates β TraceMind-AI visualizes
|
| 17 |
+
with MCP-powered intelligence
|
| 18 |
+
|
| 19 |
+
Track 2 Submission: MCP in Action - Enterprise Category
|
| 20 |
+
https://huggingface.co/MCP-1st-Birthday
|
| 21 |
"""
|
| 22 |
|
| 23 |
import os
|