FastAPI for Agents

AgentOS, built on Agno, launches an open-source platform that turns AI agents into production-ready APIs with 80+ endpoints for runs, sessions, memory, knowledge, and evals. The platform connects agents to apps like Claude, ChatGPT, Slack, WhatsApp, Telegram, and Discord, and includes coding-agent skills for self-improvement. It aims to provide a unified AI backend for multiple frontends, running entirely in the user's cloud.

AgentOS turns your agents into a production API: 80+ endpoints for runs, sessions, memory, knowledge, and evals. Build your product on top of it, connect your agents to AI apps like Claude and ChatGPT, and chat interfaces like Slack, WhatsApp, Telegram, and Discord. AgentOS gives you one AI backend for every frontend: Your product. Call the REST API from your app: run agents, stream responses, and manage sessions, memory, and knowledge. AgentOS UI. Chat with agents, build new ones with AgentOS Studio, and inspect sessions, traces, memory, and evals from the AgentOS UI at os.agno.com https://os.agno.com?utm source=github&utm medium=example-repo&utm campaign=agentos-railway&utm content=agentos-railway&utm term=railway . Coding agents. Manage the full agent development lifecycle create, extend, improve, eval and review using the skills in. .agents/skills/ AI apps. MCP clients like Claude and ChatGPT can use your agents through the MCP server at /mcp . Chat interfaces. Chat with your agents from Slack, WhatsApp, Telegram, and Discord. Built on Agno https://docs.agno.com . Everything runs in your cloud, your data lives in your database. This codebase comes with: Two platform agents that help you build and run the platform from your favorite AI apps like Claude and ChatGPT. Agent Builder creates agents, teams, and workflows using the AgentOS Studio. Platform Manager understands, monitors, and explains the platform: codebase questions, eval history, deployment checks, schedules. Coding-agent skills let Claude Code, Codex, Cursor, and other coding agents build, test, and improve the platform automatically — see Using the platform using-the-platform . Trace data, agent code, evals, and system logs are all available to coding agents, so the platform can inspect and improve itself end to end. The fastest way to get started is using a coding agent. Copy the prompt below into Claude Code, Cursor or Codex and it'll take you from zero to a running platform. Help me set up AgentOS on this machine. Be self-driving: anything you can do — open a file, open a URL, launch an app — do it. Stop when you need a human: typing a secret, installing software, signing in to a website. When you do stop, tell me exactly what to do. Never read or print secrets. 1. Clone https://github.com/agno-agi/agentos-railway.git into a folder called agent-platform and cd in. Then read AGENTS.md end to end — it is the source of truth for how this platform works and answers most questions you'll hit along the way. 2. Confirm Docker is installed and running docker info succeeds . If it's installed but not running, start it open -a Docker on macOS and poll until it's up. Stop for me only if Docker isn't installed — then give me steps to install Docker Desktop and wait. 3. Set up my environment. Run cp example.env .env , then help me set my OPENAI API KEY. If it's already set in my shell, tell me you found one and offer to copy it in — move the value across without reading or printing it. Otherwise open .env in my editor cursor, code etc. and ask me to paste the key. Never open a terminal editor like vim or nano from your own shell — it will hang this session. 4. Start the platform with docker compose up -d --build , then poll http://localhost:8000/docs until it returns 200 first build takes a few minutes . If it never comes up, read docker compose logs agentos-api and fix what you find. 5. Prove it end to end with ./scripts/mcp check.sh — it should print "MCP OK" and a real agent answer. Show me that answer: it's my platform talking. 6. Next, help me set up the AgentOS UI. Ask if you can open https://os.agno.com and walk me through the connection process: Connect OS → enter http://localhost:8000 → name it "Local AgentOS". That's where I chat with my agents and inspect sessions, memory, and evals. 7. Finish with a short summary and what I should do next: run /create-new-agent right here and you'll build a new agent with me, then /improve-agent to sharpen it — that loop is yours to keep. Mention in one line that I can also connect my platform to coding agents like yourself using uvx agno connect , and to claude.ai / ChatGPT over OAuth once it's deployed to production. Prerequisite: Docker installed and running. git clone https://github.com/agno-agi/agentos-railway.git agentos cd agentos Configure credentials cp example.env .env Open .env and set OPENAI API KEY Run the platform on docker docker compose up -d --build Confirm your AgentOS is running at http://localhost:8000/docs http://localhost:8000/docs . - Open os.agno.com https://os.agno.com?utm source=github&utm medium=example-repo&utm campaign=agentos-railway&utm content=agentos-railway&utm term=railway and sign in. - Click Connect OS , enter http://localhost:8000 as the URL, name it Local AgentOS , and connect. - Click Chat under the Agent Builder agent and try the first prompt: "Build an agent that tracks AI news and writes a daily brief". Go through the agent development process. - Once created, click the Refresh button on the top right. You should now see the "Daily AI News Brief" agent in the Agents dropdown. Click the newly created agent. - Ask: "What's new with Anthropic?" Click Chat under Platform Manager and ask: "How healthy is the platform?" It answers from the codebase and runtime data — eval history, deployment checks, schedules, and the component you just built. You can run the platform anywhere that supports containerized images. This codebase comes with scripts to deploy the platform to Railway https://railway.com . Prerequisite: Railway CLI installed and railway login completed. Create a new .env.production file for production credentials. cp .env .env.production or cp example.env .env.production Edit .env.production with production values Keeping a separate .env.production lets us use different values for local and production: different OpenAI keys, production-only credentials, a different Slack workspace. ./scripts/railway/up.sh This provisions the AgentOS service and Postgres on the same private network. The script pauses and asks for a JWT verification key for authentication see next section . Token-Based Authorization is on by default. Without a JWT VERIFICATION KEY or JWT JWKS FILE , the app refuses to serve traffic in production. The platform's job is to keep your data private, so the safe default is "refuse to start" without an authentication token. Token-Based Auth gives you three things: No public access. The server rejects requests without a valid token. Per-request identity. Middleware parses the token and extracts the user id , session id , and custom claims. Each request is tied to a user and session, giving you auditability and traceability. Granular permissions. User tokens can run an agent and view their own sessions. Admin tokens read everyone's sessions and test any agent. During ./scripts/railway/up.sh , the script creates your Railway domain and pauses so you can mint the key before the app starts. - Open os.agno.com https://os.agno.com?utm source=github&utm medium=example-repo&utm campaign=agentos-railway&utm content=agentos-railway&utm term=railway , click Connect OS → Live , enter your Railway domain, and connect. - Name it Live AgentOS . - Go to Settings → OS & Security . - Turn Token-Based Authorization JWT on. - Copy the public key. - Paste the full public key into the up.sh prompt. The script saves it into your env file for future syncs: JWT VERIFICATION KEY="-----BEGIN PUBLIC KEY----- MIIBIjANBgkq... -----END PUBLIC KEY-----" Heads up.Live AgentOS Connections are a paid feature. Use PLATFORM30 to get 1 month off. We are working on a free trial so you don't have to pay to try. If you get something wrong, you can re-sync environment variables with ./scripts/railway/env-sync.sh . Re-run uvx agno connect , this time pointed at your deployed domain, to connect Claude Code, Claude Desktop, Codex, and Cursor to your production platform: uvx agno connect --url https://<railway-domain For claude.ai and ChatGPT web : add https://<railway-domain /mcp as a custom connector in the chat app's connector settings. Leave the form's optional OAuth fields client ID / client secret empty. Click Connect and, on the consent page, enter the MCP CONNECT SECRET that up.sh generated during deploy saved in .env.production . You can check the logs on the Railway dashboard, or by running the following command: railway logs --service agent-os To redeploy your AgentOS, run the following command: ./scripts/railway/redeploy.sh Recommended: Auto-deploy on merge to main using: - Open the Railway dashboard, your project, the agent-os service, Settings . - Under Source , click Connect Repo and pick your repo. - Set the deploy branch to main and save. Push to main triggers a build and rolling deploy. ./scripts/railway/env-sync.sh is still how you sync env changes. To re-sync environment variables, run the following command: ./scripts/railway/env-sync.sh ./scripts/railway/down.sh Deletes the Railway project: the agent-os service, the pgvector database, and its volume, including all data . It also removes the AGENTOS URL from your env file so a future up.sh starts clean. Set authorization=False in app/main.py /agno-agi/agentos-railway/blob/main/app/main.py and redeploy. Use this only inside a private VPC behind another auth layer. Without it, anyone who guesses your Railway domain can access your platform. This platform is designed so that coding agents can drive the entire create → improve → evaluate → maintain lifecycle for you. Open your coding agent of choice Claude Code, Codex, Cursor and run: /create-new-agent It asks a few questions, generates the agent file in agents/ , registers it in app/main.py , adds its description and quick prompts to app/config.yaml , restarts the container, and smoke-tests it live. Improve your agents by running the following skills: — Add a tool, add a capability, refine the instructions, fix a known bug. /extend-agent — Claude simulates scenarios from the agent's /improve-agent INSTRUCTIONS , runs them against the live container, judges the responses, and edits until they pass. Run the eval suite to check for regressions. The evals live in evals/cases.py /agno-agi/agentos-railway/blob/main/evals/cases.py , and run history shows up at os.agno.com next to your sessions and traces. The evals run on the host machine, so set up the venv with ./scripts/venv setup.sh && source .venv/bin/activate , then: python -m evals --tag smoke fast checks of the self-driving surfaces python -m evals --tag release broader pre-release confidence python -m evals --name <case one case while iterating python -m evals -v stream the full run with rich panels If a case fails, run /eval-and-improve — it diagnoses each failure, fixes what's in scope, and loops until green. Because the repo is managed by coding agents, it moves fast. Run /review-and-improve before a release or after a refactor: it sweeps for drift between docs, code, and config, auto-fixes mechanical drift like stale paths and missing env vars, and flags anything bigger. AgentOS comes with an MCP server at /mcp enabled by setting mcp server=True in app/main.py /agno-agi/agentos-railway/blob/main/app/main.py , so any MCP client can call your agents, teams, and workflows through tools like run agent , run team , and run workflow .Register your AgentOS with the MCP clients on your machine: uvx agno connect It auto-detects Claude Code, Claude Desktop, Codex, and Cursor and registers http://localhost:8000/mcp . After a successful connection, open one of these apps and ask: can you access my agentos mcp? claude.ai and ChatGPT web . Hosted AI apps reach your platform over the internet and need an OAuth login. Deploy to production above , add https://<domain /mcp as a remote connector, and approve the consent page with your connect secret. | Variable | Required | Default | Description | |---|---|---|---| OPENAI API KEY | yes | none | OpenAI key for models and embeddings. | RUNTIME ENV | no | prd | dev disables JWT. Compose sets this to dev for local — never put it in an env file that syncs to Railway, or production deploys unauthenticated. | JWT VERIFICATION KEY | prd | none | Public key from os.agno.com. Required when RUNTIME ENV=prd , unless JWT JWKS FILE is set. | JWT JWKS FILE | prd | none | Path to a JWKS file; alternative to JWT VERIFICATION KEY for production JWT verification. | AGENTOS URL | no | http://127.0.0.1:8000 | Scheduler base URL. scripts/railway/up.sh auto-sets it to your Railway domain; set by hand only for a custom domain or tunnel. Also the public origin OAuth metadata derives from when MCP CONNECT SECRET is set. | MCP CONNECT SECRET | no | none | If set ≥16 chars, e.g. openssl rand -base64 32 , /mcp becomes its own OAuth 2.1 authorization server so claude.ai and ChatGPT web can connect; connecting asks for this secret on a consent page. Requires AGENTOS URL . scripts/railway/up.sh auto-generates it on deploy. PAT and JWT bearers keep working alongside. | AGENTOS MCP SIGNING KEY | no | none | Optional high-entropy signing-key material ≥32 chars for OAuth tokens. Unset, a strong key is generated and persisted in the database. Rotating it invalidates outstanding tokens. | ENABLE DEPLOY CHECK | no | True | The reference deployment-check cron runs daily by default. Set False to disable; the workflow is runnable on demand regardless. | ENABLE SCHEDULED EVALS | no | False | If True , schedules the run-evals workflow daily. Off by default because it uses model calls. | EVALS TAG | no | smoke | Eval tag run by the run-evals workflow. | EVALS CASE TIMEOUT SECONDS | no | 90 | Default per-case timeout for run-evals runs; applies only to cases that don't set their own timeout seconds . | EVALS SUITE TIMEOUT SECONDS | no | 900 | Whole-suite timeout for run-evals runs; per-case timeouts are the granular limit. The default bounds the smoke tag's worst case incl. builder-case teardown . | PARALLEL API KEY | no | none | Authenticates the WebSearch Agent's Parallel SDK / MCP connection. | SLACK BOT TOKEN / SLACK SIGNING SECRET | no | none | Both must be set to enable the Slack interface. | DB HOST / DB PORT / DB USER / DB PASS / DB DATABASE | no | matches compose | Postgres connection. | DB DRIVER | no | postgresql+psycopg | SQLAlchemy driver. | AGNO DEBUG | no | False | If True , Agno emits verbose debug logs. Compose sets this for dev. | WAIT FOR DB | no | False | If True , the entrypoint blocks on the DB before starting. Compose sets this. | Agno documentation https://docs.agno.com?utm source=github&utm medium=example-repo&utm campaign=agentos-railway&utm content=agentos-railway&utm term=railway AgentOS introduction https://docs.agno.com/agent-os/introduction?utm source=github&utm medium=example-repo&utm campaign=agentos-railway&utm content=agentos-railway&utm term=railway Agno on GitHub https://github.com/agno-agi/agno . Drop a star if this is useful.