Engineering teams shipping AI agents can self-host this testing and tracing platform free, or pay by usage on the hosted version.
Kenning's take
What it does
Future AGI helps teams find and fix problems in AI agents before and after launch. It runs simulated conversations, including voice, scores outputs with evaluations, traces what agents do in production and applies guardrails. The platform is open source under Apache 2.0, with a hosted version billed by usage after a free tier.
- Text and voice agent simulations
- Evaluations and error feed
- Tracing, dashboards and alerts
- Built-in guardrails
- AI gateway with caching
- Open source under Apache 2.0
Who it suits. Engineering teams building and running AI agents and LLM apps.
Key facts
- Category
- Developer tools
- Made by
- Future AGI
- How to get it
- Free hosted sign-up, or self-host the open-source version
- Works on
- Web, API, SDK
- Free plan
- 50 GB tracing, 2K AI credits, 100K gateway requests, 1M simulation tokens a month
- API price
- storage from $2/GB; AI credits from $10 per 1K; gateway from $5 per 100K requests; voice simulation from $0.08/min
Pricing
| Plan | Price | Billed |
|---|---|---|
| Pay-as-you-go | $usage | month |
FAQ
Is Future AGI free?
It has a monthly free tier and an open-source version under Apache 2.0.
What does Future AGI do?
Simulates, evaluates, traces and guards AI agents to catch errors and hallucinations.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.
AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.