# future-agi-platform

A skill that walks your coding agent through Future AGI: wiring up tracing, running eval metrics, and self-hosting the platform.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 308 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/future-agi-platform/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/future-agi-platform

## What it does

Future AGI is an open-source platform for observing and scoring LLM and agent applications. It covers OpenTelemetry-native tracing, more than 50 evaluation metrics, multi-turn simulations, datasets, an OpenAI-compatible gateway, and guardrails. The skill hands your agent working recipes for each part instead of leaving it to read the docs.

Instrumentation ships as separate packages. Python users install `fi-instrumentation` plus a framework instrumentor such as `traceai-openai`, `traceai-langchain`, `traceai-llamaindex`, or `traceai-crewai`. On the TypeScript side there are `@traceai/fi-core` and `@traceai/openai`. In code you call `register(project_name=...)`, attach the instrumentor, and later calls get traced without extra work. Evaluation lives in `fi.evals`: `Hallucination`, `Groundedness`, `ResponseRelevance`, `ToneCheck`, `PIICheck`, `ToolCallAccuracy`. You can run one metric, several at once, or a batch over a dataset.

Self-hosting means cloning the repo, copying `futureagi/.env.example` to `futureagi/.env`, filling in keys, and running `docker compose up -d`; the UI comes up at `http://localhost:3031`. The SDK registers nothing without `FI_API_KEY` and `FI_BASE_URL` in the environment, so set those before the first run. A local deployment also expects Postgres, ClickHouse, Redis, and RabbitMQ connection strings in the same `.env` file.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill future-agi-platform -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/future-agi-platform/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/future-agi-platform/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill future-agi-platform -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/future-agi-platform/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill future-agi-platform -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/future-agi-platform/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills future-agi-platform
```

2. **Manually: put the files in place**
- File: `.github/skills/future-agi-platform/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill future-agi-platform -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/future-agi-platform
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/future-agi-platform/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill future-agi-platform -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/future-agi-platform/SKILL.md

## When to use it
- instrument an OpenAI or LangChain agent for tracing
- check model answers for hallucination
- score a whole dataset instead of a single response
- run Future AGI locally with Docker Compose
- add a manual span when no instrumentor exists

## Example prompts
- Wire Future AGI tracing into my Anthropic agent
- Run Hallucination and Groundedness over my dataset responses
- Help me self-host Future AGI with docker compose and set up .env

## Similar
- [arize-instrumentation](https://affpapa.org/en/nevibecode/skills/arize-arize-instrumentation.md) — skill · 3400 installs
- [arize-instrumentation-health](https://affpapa.org/en/nevibecode/skills/arize-instrumentation-health.md) — skill · 998 installs
- [rag-observability-evals](https://affpapa.org/en/nevibecode/skills/rag-observability-evals.md) — skill · 318 installs
- [agent-observability-trace-rca](https://affpapa.org/en/nevibecode/skills/agent-observability-trace-rca.md) — skill · 552 installs
- [sentry-otel-exporter-setup](https://affpapa.org/en/nevibecode/skills/sentry-otel-exporter-setup.md) — skill · 2400 installs
- [logfire-setup](https://affpapa.org/en/nevibecode/skills/logfire-setup.md) — skill · 555 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md