Future Agi AI Agent

by future-agi• 2.2k•• Scanned•Claim this listing•Request removal

Data Science & MLagent evaluationai agentsai evalsai gatewayai observability

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.

Future Agi is an open-source ai agent by future-agi, written mainly in Python, with 2,234 GitHub stars and the Apache-2.0 license. Its code was last updated Nov 1, 2026.

about README security reviews

<div align="center">  <a href="https://futureagi.com?utm_source=github&utm_medium=readme&utm_campaign=oss_repo&utm_content=logo"> <img alt="Future AGI — make AI agents reliable" src="frontend/public/assets/readme/Logo.png" width="100%"> </a>

AI Agents hallucinate. Fix it faster.

The open-source platform for shipping self-improving AI agents. Evaluations, tracing, simulations, guardrails, gateway, optimization. Everything runs on one platform and one feedback loop, from first prototype to live deployment.

<p> <a href="https://github.com/future-agi/future-agi/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue?style=flat-square" alt="Apache 2.0 License"></a> <a href="https://github.com/future-agi/future-agi/releases/latest"><img src="https://img.shields.io/github/v/release/future-agi/future-agi?style=flat-square&label=release&color=3fb950" alt="Latest release"></a> <a href="https://github.com/future-agi/future-agi/pulse"><img src="https://img.shields.io/github/commit-activity/m/future-agi/future-agi?style=flat-square&label=commit%20activity&color=3fb950" alt="Commit activity"></a> <a href="#-quickstart"><img src="https://img.shields.io/badge/docker-self--host%20ready-0db7ed?style=flat-square" alt="Docker self-host ready"></a> <a href="https://discord.com/invite/cBnWkd7T9v"><img src="https://img.shields.io/badge/discord-join-5865F2?style=flat-square" alt="Discord"></a> <br> <a href="https://pypi.org/project/agent-learning-kit/"><img src="https://img.shields.io/pypi/v/agent-learning-kit?style=flat-square&label=pypi%20agent-learning-kit" alt="PyPI agent-learning-kit"></a> <a href="https://www.npmjs.com/package/@traceai/fi-core"><img src="https://img.shields.io/npm/v/@traceai/fi-core?style=flat-square&label=npm%20%40traceai%2Ffi-core" alt="npm @traceai/fi-core"></a> <a href="https://pypi.org/project/agentcc/"><img src="https://img.shields.io/pypi/v/agentcc?style=flat-square&label=pypi%20agentcc" alt="PyPI agentcc"></a> <a href="https://pypi.org/project/agent-learning-kit/"><img src="https://img.shields.io/badge/python-3.10%2B-blue?style=flat-square" alt="Python 3.10+"></a> </p> <p> <a href="https://app.futureagi.com/auth/jwt/register?utm_source=github&utm_medium=readme&utm_campaign=oss_repo&utm_content=header_cta_cloud"><b>Try Cloud (Free)</b></a> · <a href="#-quickstart"><b>Self-Host</b></a> · <a href="https://discord.com/invite/cBnWkd7T9v"><b>Support</b></a> </p> <p> <sub> <a href="https://docs.futureagi.com?utm_source=github&utm_medium=readme&utm_campaign=oss_repo&utm_content=header_docs">Docs</a> · <a href="https://futureagi.com/blog?utm_source=github&utm_medium=readme&utm_campaign=oss_repo&utm_content=header_blog">Blogs</a> · <a href="https://github.com/future-agi/future-agi/issues/new/choose">Report a Bug</a> </sub> </p> </div>

<div align="center"> <a href="https://www.youtube.com/watch?v=6keOTAOUUWI"> <img alt="Watch the demo — trace an agent, run evals, simulate, and guardrail on one platform" src="frontend/public/assets/readme/demo-6keOTAOUUWI-v4.png" width="100%"> </a> </div>

Why Future AGI?

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 and one feedback loop. Simulate edge cases before launch, evaluate what happens in production, protect users in real time, and turn every trace into signal for the next version. The result: agents that don't just get monitored, they self-improve.

All-in-one

No more stitching Langfuse + Braintrust + Helicone + Guardrails AI + a custom simulator. One platform covers the lifecycle: simulate → evaluate → protect → monitor → optimize, with data flowing back as a loop.

</td> <td width="33%" valign="top">

Open & self-hostable

Apache 2.0 core. Every evaluator, every prompt, every trace is inspectable — no black-box scoring. Self-host for data sovereignty or use our managed Cloud. Drop in your own stack at any layer via OTel / OpenAI-compatible HTTP.

</td> <td width="33%" valign="top">

Built for production

Go-based gateway with ~9.9 ns weighted routing, ~29 k req/s on t3.xlarge, P99 ≤ 21 ms with guardrails on. OpenTelemetry-native traces. 50+ framework instrumentors. Every claim reproducible via the committed benchmark harness.

</td> </tr> </table>

🚀 Quickstart

You need Docker Desktop or Docker Engine with Compose v2.24 or newer, and for the default Standalone setup 2 vCPUs and 4 GB of memory given to Docker.

<table width="100%"> <tr> <th width="50%">Future AGI Cloud</th> <th width="50%">Self Host Future AGI</th> </tr> <tr valign="top"> <td width="50%">

No installation required, get started immediately.

Generous free-tier, no credit card required.

<sub>SOC 2 Type II · HIPAA · data stays in your region.</sub>

</td> <td width="50%">

One command, full stack. Published images, no source build.

git clone https://github.com/future-agi/future-agi.git
cd future-agi
./bin/install          # Windows (PowerShell): .\bin\install.ps1

</td> </tr> </table>

The installer checks your machine, writes this install's secrets to .env, downloads the images (about 800 MB) and waits until everything answers. The first boot sets up the database and takes a few minutes; http://localhost:3000 shows its progress meanwhile.

2. Sign in and copy your keys

Open http://localhost:3000, create your account (or sign in with the one the installer made), then copy the API key and secret key from Keys in the sidebar.

3. Send your first trace

pip install fi-instrumentation-otel
export FI_API_KEY="<your API key>" FI_SECRET_KEY="<your secret key>" FI_BASE_URL="http://localhost:4318"

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

tracer_provider = register(project_name="my-first-project", project_type=ProjectType.OBSERVE)
with tracer_provider.get_tracer("quickstart").start_as_current_span("hello-future-agi") as span:
    span.set_attribute("input.value", "Hello, Future AGI")
tracer_provider.force_flush()

Open Tracing in the sidebar: my-first-project holds your first span. http://localhost:4318 is this install's trace collector; it listens on this machine only.

	Standalone (default)	Distributed (at scale)
Install	`./bin/install`	`./bin/install --distributed`
Runs	one app container, Postgres, ClickHouse	one container per service, PeerDB, Kafka
Docker resources	2 vCPUs, 4 GB	4+ vCPUs, 12–16 GB
Kubernetes		Helm chart: about 4 CPUs and 8 GiB free for an evaluation

Choose before you add data: there is no supported way to move a Standalone install's data to Distributed or Helm later (Switching).

Configure: every variable in .env is described in the configuration reference. Nothing is required for a local install; add LLM provider keys, a public URL or email when you need them.
Manage: docker compose logs -f app (Distributed: backend); stop with docker compose down or ./bin/uninstall (both keep your data); upgrade with git pull && ./bin/install; remove everything, data included, with ./bin/uninstall --purge.
Develop: on a branch other than main, add --from-source to build the images from your checkout; ./bin/dev runs it with hot reload (Local development).
More: the self-hosting guide, INSTALLATION.md (every option and troubleshooting) and deploy/README.md (production).

Instrument your first agent

Swap the hand-made span for an instrumentor to trace a real app, here OpenAI (pip install traceai-openai). Against your own install, keep the FI_* variables from step 3 set.

Python

from fi_instrumentation import register
from traceai_openai import OpenAIInstrumentor

register(project_name="my-agent")
OpenAIInstrumentor().instrument()

# Your existing OpenAI code is now traced.
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": query}],
)

</td> <td width="50%">

TypeScript

import { register } from "@traceai/fi-core";
import { OpenAIInstrumentation } from "@traceai/openai";

register({ projectName: "my-agent" });
new OpenAIInstrumentation().instrument();

// Your existing OpenAI code is now traced.
const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: query }],
});

</td> </tr> </table>

<sub> Full docs → · Cookbooks → · API reference →</sub>

Core features

Six pillars. Each one replaces a tool you probably have.

🧪 Simulate

Thousands of multi-turn conversations against realistic personas, adversarial inputs, and edge cases. Text and voice (LiveKit, VAPI, Retell, Pipecat).

</td> <td width="33%" valign="top">

📊 Evaluate

50+ metrics under one evaluate() call: groundedness, hallucination, tool-use correctness, PII, tone, custom rubrics. LLM-as-judge + heuristic + ML.

</td> <td width="33%" valign="top">

🛡️ Protect

18 built-in scanners (PII, jailbreak, injection, …) + 15 vendor adapters (Lakera, Presidio, Llama Guard, …). Inline in gateway or standalone SDK.

</td> </tr> <tr> <td width="33%" valign="top">

👁️ Monitor

OpenTelemetry-native tracing across 50+ frameworks (LangChain, LlamaIndex, CrewAI, DSPy…). Span graphs, latency, token cost, live dashboards. Zero-config.

</td> <td width="33%" valign="top">

🎛️ Agent Command Center

OpenAI-compatible gateway. 100+ providers, 15 routing strategies, semantic caching, virtual keys, MCP, A2A. ~29k req/s, P99 ≤ 21ms with guardrails on.

<sub>Docs → · Benchmarks →</sub>

</td> <td width="33%" valign="top">

🔁 Optimize

Six prompt-optimization algorithms (GEPA, PromptWizard, ProTeGi, Bayesian, Meta-Prompt, Random). Production traces feed back as training data.

</td> </tr> </table>

Deployment options

Target	Status	Notes
Docker Compose: Standalone	✅	`./bin/install`: one app container next to Postgres and ClickHouse, for a laptop or a single VM
Docker Compose: Distributed	✅	`./bin/install --distributed`: one container per service, for scale on one host
Production Compose overlay	✅	`./deploy/setup.sh` on the Distributed setup: `--skip-up` writes `deploy/.env.production` (generating only the secrets you do not supply; you give every image version), then, once the databases are initialized, `--confirm-initialized` pulls the images and starts the stack (deploy/README.md)
Kubernetes / Helm	✅	Distributed on Kubernetes: `helm install futureagi oci://ghcr.io/future-agi/charts/futureagi --version X.Y.Z`, one signed chart for the open-source and Enterprise editions (chart README)
AWS / GCP / Azure	✅	Docker Compose on a VM, or the Helm chart on a Kubernetes 1.27+ cluster
AWS Marketplace	⏳	Coming soon
Air-gapped / on-prem	✅	Mirror the images, set `FUTURE_AGI_TELEMETRY_DISABLED=true` and block outbound traffic (Telemetry); on Helm, set `global.airgap=true` and mirror the images the release lists (chart README); contact sales for support

Every image, tag and size: Container images. Every setting: Configuration reference.

Architecture

Every arrow is an open, documented interface: OpenTelemetry OTLP for traces, OpenAI-compatible HTTP for the gateway, Postgres / ClickHouse SQL for storage. Drop in your own stack at any layer.

Runtime: Python 3.11+ (Django 5.1 + Channels) · Go 1.25+ (gateway), 1.24+ (trace collector) · React 18 + Vite · Node 22.18+. Data: PostgreSQL (metadata) · ClickHouse (spans + time-series) · Redis (state, live updates) · Temporal (jobs).

<details><summary>Component breakdown (per-package)</summary>

Layer	Component	Code
Edge	traceAI — OpenTelemetry instrumentation	`future-agi/traceAI`
Edge	Agent Command Center — OpenAI-compatible proxy	`agentcc-gateway/`
Platform	tracer — OTLP ingest, span graph	`futureagi/tracer/`
Platform	agentic_eval — 50+ metrics, LLM-as-judge	`futureagi/agentic_eval/`
Platform	simulate — persona-driven scenario generation	`futureagi/simulate/`
Platform	model_hub — LLM routing, embeddings, datasets	`futureagi/model_hub/`
Platform	accounts · usage · integrations — auth, orgs, metering, connectors	`futureagi/accounts/`
Data	PostgreSQL · ClickHouse · Redis · Temporal	—

</details>

SDKs & integrations

Future AGI is an open-source ecosystem — each SDK is independently usable, independently packaged, Apache/MIT-licensed.

Client libraries

Repo	Install	Languages	Purpose
traceAI	`pip install fi-instrumentation-otel`<br>`npm i @traceai/fi-core`	Python · TS · Java · C#	Zero-config OTel tracing for 50+ AI frameworks
agent-learning-kit	`pip install agent-learning-kit`	Python · TS	Local-first testing, simulation, red teaming, and optimization for AI agents
futureagi	`pip install futureagi`	Python	Platform SDK — datasets, prompts, KB, experiments
agentcc	`pip install agentcc`<br>`npm i @agentcc/client`	Python · TS (+ LangChain · LlamaIndex · React · Vercel)	Gateway client SDKs

Integrations


LLM providers (100+)	OpenAI · Anthropic · Google Gemini · Vertex AI · AWS Bedrock · Azure OpenAI · Mistral · Groq · Cohere · Together · Perplexity · OpenRouter · Fireworks · xAI · Replicate · HuggingFace · + self-hosted Ollama · vLLM · LM Studio · TGI · Llamafile
Agent frameworks	LangChain · LangGraph · LlamaIndex · CrewAI · AutoGen · Phidata · PydanticAI · Claude SDK · LiteLLM · Haystack · DSPy · Instructor · Smol-agents
Voice platforms	VAPI · Retell · LiveKit · Pipecat
Vector DBs	Pinecone · Weaviate · Chroma · Milvus · Qdrant · pgvector
Tools & infra	Vercel AI SDK · n8n · MongoDB · MCP · A2A · Guardrails AI · Langfuse · HuggingFace Smol-agents

<sub> Full integrations catalog →</sub>

How Future AGI compares

<table width="100%"> <thead> <tr> <th width="25%"></th> <th width="15%" align="center"><b>Future AGI</b></th> <th width="15%" align="center">Langfuse</th> <th width="15%" align="center">Phoenix</th> <th width="15%" align="center">Braintrust</th> <th width="15%" align="center">Helicone</th> </tr> </thead> <tbody> <tr><td>Open source</td><td align="center">✅<br><sub>Apache 2.0</sub></td><td align="center">✅<br><sub>MIT</sub></td><td align="center">✅<br><sub>Elastic v2</sub></td><td align="center">❌</td><td align="center">✅<br><sub>Apache 2.0</sub></td></tr> <tr><td>Self-host</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">❌</td><td align="center">✅</td></tr> <tr><td>LLM tracing (OpenTelemetry)</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">⚠️<br><sub>via OpenLLMetry</sub></td></tr> <tr><td>Evaluation suites</td><td align="center">✅<br><sub>50+ metrics</sub></td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">⚠️<br><sub>Limited</sub></td></tr> <tr><td><b>Agent simulation</b></td><td align="center">✅</td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td></tr> <tr><td><b>Voice agent eval</b></td><td align="center">✅</td><td align="center">❌</td><td align="center">⚠️<br><sub>Cookbook</sub></td><td align="center">❌</td><td align="center">❌</td></tr> <tr><td><b>LLM gateway built in</b></td><td align="center">✅<br><sub>100+ providers</sub></td><td align="center">❌</td><td align="center">❌</td><td align="center">✅</td><td align="center">✅</td></tr> <tr><td><b>Guardrails built in</b></td><td align="center">✅<br><sub>18 + 15 adapters</sub></td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td></tr> <tr><td><b>Prompt optimization</b></td><td align="center">✅<br><sub>6 algorithms</sub></td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td><td align="center">❌</td></tr> <tr><td>Prompt management</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td></tr> <tr><td>Datasets & experiments</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td><td align="center">✅</td></tr> <tr><td>No-code eval builder</td><td align="center">✅</td><td align="center">⚠️</td><td align="center">⚠️</td><td align="center">⚠️</td><td align="center">⚠️</td></tr> </tbody> </table>

<sub>Based on publicly-documented features as of April 2026. Corrections welcome — open a PR.</sub>

Built for every kind of agent

Customer Support: Ship support AI that customers actually trust
Voice Agents: Test, evaluate, and improve voice AI end-to-end
Internal Tools: AI copilots your whole org can rely on
RAG & Search: Every answer grounded, every citation verified
Autonomous Agents: Multi-step agents you can actually trust in production
Computer-Use Agents (CUA): Agents that click with confidence
Coding Agents: AI that writes code you can actually ship

Roadmap

Vote on the public roadmap → · GitHub Discussions · Releases · Changelog

<table> <tr> <th width="25%"> Recently shipped</th> <th width="25%"> In progress</th> <th width="25%"> Coming up</th> <th width="25%"> Exploring</th> </tr> <tr valign="top"> <td> </td> <td>

Agent Changelog & Diff View
Smart Queue Assignment
Essential Node Library for Agent Builder
Full Execution Tracing for Agents
Multi-modal Support for Agents

</td> <td>

Agent Changelog & Diff View
Smart Queue Assignment

</td> <td>

Import agents to Agent Playground
Simulating CUA agents
Simulating Coding agents
Scheduled Simulations

</td> </tr> </table>

🤝 Contributing

We love contributions — bug fixes, new evaluators, framework integrations, docs, examples, anything.

Browse good first issue
Read the Contributing Guide
Say hi on Discord or Discussions
Sign the CLA on your first PR (automatic bot)

🌍 Community & support


💬 Discord	Real-time help from the team and community
🗨️ GitHub Discussions	Ideas, questions, roadmap input
🐦 Twitter / X	Release announcements
📝 Blog	Engineering & research posts
📺 YouTube	Walkthroughs & demos
📊 Status	Cloud uptime + incident history
📧 support@futureagi.com	Cloud account / billing
🔐 security@futureagi.com	Private vulnerability disclosure (24h ack on weekdays — see SECURITY.md)

Telemetry

Self-hosted Future AGI sends deployment telemetry, on by default, so we can count installs and size release testing: one registration with the email addresses and email domains of the install's owner, admin and staff/superuser accounts, then usage counts on a schedule. No trace data, no prompts, no completions, no datasets, no API keys, ever.

To opt out, install with ./bin/install --no-telemetry, or set FUTURE_AGI_TELEMETRY_DISABLED=true in .env (deploy/.env.production for the production overlay, config.telemetry=false for Helm) and run docker compose up -d. Opting out still sends one registration, without email addresses; block api.futureagi.com to send nothing. Everything else that could leave your install (HubSpot, Slack, Mixpanel, PostHog, reCAPTCHA, Sentry, Mailgun) is off until you set its key.

Telemetry and outbound connections has the exact payloads, what the opt-out still sends, every setting, and every outbound connection, with what an install that allows no outbound traffic must also set.

⭐ Star history

📄 License

Future AGI is licensed under the Apache License 2.0. See LICENSE and NOTICE.

You own your evaluation logic and your data. Inspect every evaluator, every prompt, every trace — no black-box scoring, no vendor lock-in.

Built with ❤️ by the Future AGI team and contributors worldwide.

If Future AGI helps you ship better AI, a ⭐ helps more teams find us.

🌐 futureagi.com · 📖 docs.futureagi.com · ☁️ app.futureagi.com · 📊 status.futureagi.com

</div>

Future Agi alternatives

View more →

Similar ai agents in Data Science & ML, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

Name	Stars	Licence	Last updated	Scan
Future Agi (this page) future-agi	2.2k	Apache-2.0	Nov 1, 2026	Scanned, no flagged issues
Ragflow infiniflow	93k	Apache-2.0	Oct 31, 2026	Scanned, no flagged issues
Cherry Studio CherryHQ	53k	AGPL-3.0	Nov 1, 2026	Scanned, no flagged issues
PageIndex VectifyAI	40k	MIT	Oct 29, 2026	Scanned, no flagged issues
Graphiti getzep	32k	Apache-2.0	Nov 1, 2026	Scanned, no flagged issues
Cua trycua	31k	MIT	Nov 1, 2026	Scanned, no flagged issues