Agent skill · data analytics · aradotso
future-agi-platform
Expert skill for using Future AGI — the open-source end-to-end platform for evaluating, observing, and improving LLM and AI agent applications with tracing, evals, simulations, datasets, gateway, and guardrails.
Why this skill is useful
Adds multiple executable scripts and configuration patterns for self-hosting and instrumenting AI agents with Future AGI, which are not commonly available in public documentation.
What it needs
Requires docker, npm, python installed locally. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
Future AGI Platform Skill by ara.so — Daily 2026 Skills collection. Future AGI is an open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. It provides tracing (OpenTelemetry-native), 50+ evaluation metrics, multi-turn simulations, guardrails/protect, an OpenAI-compatible gateway, and prompt optimization — all in one self-hostable platform with a closed feedback loop. --- Installation Python SDK TypeScript/Node SDK Self-Host via Docker Compose Self-Host via Kubernetes --- Configuration Environment Variables SDK Configuration in Code --- Core Feature 1: Tracing / Observability Python — OpenAI Instrumentation Python — LangChain Instrumentation Python — LlamaIndex Instrumentation Python — Manual Span Creation TypeScript — OpenAI Instrumentation --- Core Feature 2: Evaluations Basic Evaluation Multiple Metrics at Once Batch Evaluation on a Dataset Custom Rubric / LLM-as-Judge Evaluation with Tool Calls --- Core Feature 3: Simulations --- Core Feature 4: Guardrails / Protect Inline with OpenAI via Gateway --- Core Feature 5: Agent Command Center (Gateway) --- Core Feature 6: Prompt Optimization --- Common Patterns Pattern 1: Full Agent Pipeline with Tracing + Evals Pattern 2: RAG Pipeline with Full Observability Pattern 3: Async Agent with CrewAI Pattern 4: Evaluate a Dataset and Log Results --- Troubleshooting Traces not appearing in dashboard Self-hosted: Services not starting Evaluation returning unexpected results Gateway connection issues SDK version compatibility `bash Check installed versions pip show ai-evaluation fi-instrumentation traceai-openai Update all Future AGI packages pip install --up
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/future-agi-platform