Future AGI
- 186 followers
- United States of America
- https://futureagi.com
- company/futureagi
- @futureagi_
- @Future_AGI
Future AGI is an open-source e2e agent engineering and optimization platform that helps you ship self-improving AI agents.
Try Cloud · Self-host · Docs · Blog · Discord
Most AI agents fail in production, and teams end up stitching together evals, observability, and guardrails that never close the loop. Future AGI collapses all of it into one platform: simulate edge cases before launch, evaluate what happens in production, protect users in real time, and feed every trace back into the next version.
- 🧪 Simulate: thousands of multi-turn text + voice conversations against realistic personas and adversarial inputs
- 📊 Evaluate: 50+ metrics under one evaluate() call (groundedness, tool-use, PII, custom rubrics)
- 🛡️ Protect: 18 built-in guardrails + 15 vendor adapters, inline or standalone
- 👁️ Monitor: OpenTelemetry-native tracing across 50+ frameworks (LangChain, LlamaIndex, CrewAI, DSPy…)
- 🎛️ Agent Command Center: OpenAI-compatible gateway, 100+ providers, 15 routing strategies
- 🔁 Optimize: 6 prompt-optimization algorithms (GEPA, PromptWizard, ProTeGi…) that learn from production
| Repo | Install | Purpose |
|---|---|---|
| future-agi | docker compose up -d | Main monorepo, full self-hostable platform |
| traceAI | pip install fi-instrumentation-otel | Zero-config OTel tracing for 50+ AI frameworks |
| ai-evaluation | pip install ai-evaluation | 50+ evaluation metrics + guardrail scanners |
| agent-opt | pip install agent-opt | 6 prompt-optimization algorithms |
| simulate-sdk | pip install agent-simulate | Voice-agent simulation (LiveKit + Silero VAD) |
| agentcc | pip install agentcc | Gateway client, 100+ LLM providers |
See all repos →
- 💬 Discord · 🗨️ Discussions · 📝 Blog · 📺 YouTube
- 🧑💻 We're hiring → futureagi.com/careers
- 📬 Reach us → hello@futureagi.com
Apache 2.0 · Built by the Future AGI team and contributors worldwide
Pinned Loading
Repositories
- future-agi Public
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
- docs Public
- ride-voice-agent Public
Ride-booking voice agent on LiveKit, with a local tools API and SQLite state
- traceAI Public
Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks
- futureagi-sdk Public
Production-grade AI evaluation, prompt management & observability SDK. Automated evaluations with sub-100ms guardrails. No human-in-the-loop required. Python + TypeScript.
- futureagi-sdk-test-harness Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…