Future AGI
by Future AGI
Evaluate, observe, and improve LLM and agent applications from one self-hostable platform — tracing, evals, simulations, datasets, guardrails, and a model gateway under Apache 2.0.
Skills
Evaluation Suite
Scores outputs for hallucination, relevance, and task success using configurable evaluators across datasets.
Agent Simulations
Runs simulated multi-turn conversations against an agent to surface failure paths before real users hit them.
Runtime Guardrails
Applies input and output checks in production to block unsafe or off-policy responses as they are generated.
Related Agents
Laminar
Trace, evaluate, and debug AI agents with open-source observability — captures LLM calls, tool calls, and sub-agent spa…
Opik
Traces LLM and agent runs, scores them with LLM-as-a-judge and heuristic metrics, and monitors production quality via P…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Proliferate
Open-source, self-hostable coding agent platform for running cloud coding sessions on your own infrastructure.