Overview
Feenion is an open-source, self-hosted observability and debugging platform designed for LLM applications, RAG pipelines, and autonomous multi-agent tool loops. It captures the full causal execution graph, including exact prompts, completions, tokens, calculated costs, tool arguments, and retrieval scores, to help developers debug AI systems. The platform runs as a single lightweight container with embedded SQLite WAL storage and includes a Python SDK for instrumentation. It supports auto-instrumentation for OpenAI, Google Gemini, Anthropic Claude, LangChain, and custom RAG pipelines. Feenion provides a waterfall timeline, D3 execution DAG mind map, real-time cost tracking, and multi-tenant workspace isolation. It is released under the Apache 2.0 license and can be self-hosted on local hardware.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use Feenion to debug AI systems by inspecting every prompt, retrieval chunk, tool call, and token cost.
- Developers use Feenion to identify slow vector lookups and model latencies along the critical path.
- Teams use Feenion to visualize complex parent-child causality graphs across agents, tools, and retrievers.
- Organizations use Feenion to calculate exact token expenditures per model and workspace in real time.
- Teams use Feenion to instrument retrieval spans and capture similarity scores, chunk IDs, and query text.
- Developers use Feenion to track multi-turn reasoning loops, tool call arguments, execution outputs, and error recovery.
- Teams use Feenion to compare two traces side-by-side to determine why a regression occurred.
Features
AI assistant
Natural language interface
Workflow automation
Reviews
No reviews yet. Be the first to share your experience!