Skip to main content
@context is a self-hosted context manager that gives your AI tools one private CRM and knowledge base for your work. Individuals and small teams use @context to capture relationships, decisions, reminders, and knowledge once, then retrieve them from Claude, ChatGPT, Claude Code, Codex, Cursor, Slack, and the AgentOS UI. Teammates and their agents can submit updates while your private context and action tools remain owner-only. @context is an App: a complete agent product you fork, run on your own infrastructure, and adapt. See the repo for the source.

​
How it works

@context is one Agno agent that captures, files, and retrieves your working context across many sources. In production, AgentOS verifies HTTP identities from JWTs. Slack verifies signed events and maps their authors to user IDs. Local HTTP requests trust the caller-supplied user_id, so run them only on a trusted machine. @context assigns tools from that identity:
  1. Owner mode. You get every tool. Capture context (“met Kyle from Agno, follow up next week”), retrieve context (“give me a rundown of my day”), and prepare context (“process today”).
  2. Guest mode. Teammates and their agents can leave updates in your queue and check their own submissions. When Calendar is configured, they can also ask owner_availability for your open windows. It returns free/busy intervals without event details. You get briefed when you ask for a rundown.

​
Five jobs

  1. Maintain a CRM. Share “met Kyle from Agno, wants a partnership, follow up next week”, and @context stores a contact, a note, and a dated reminder without you picking forms or fields.
  2. Maintain a knowledge base. @context writes product specs, parses customer interview notes, manages project briefs, and runs deep research, then keeps it all organized in one place.
  3. Run your day, plan your week, prep ahead. @context runs repeatable playbooks to make things easier. A few come built in, and you should customize them and add your own.
  4. Represent you. A teammate types “@your-context my claude fixed the auth bug”, and it lands in your queue and surfaces in your next rundown. It works outbound too. @context can message people and channels on Slack on your behalf, and @-mention a teammate’s @context to drop an update in their queue. That’s how a team’s contexts talk to each other (the context network).
  5. Draft and schedule. Connect Gmail and Calendar, and @context reads your real inbox and calendar, drafts your follow-ups straight into Gmail for you to send, and sends calendar changes to your approvals queue.
The built-in playbooks: @context runs these on demand. When Slack is configured, the scheduled daily rundown and weekly plan DM the brief straight to you. Playbooks live in skills/, one SKILL.md per folder, alongside process-today, research, and knowledge-review.

​
Context sources

Most sources are sub-agents behind at most two tools: query_<id> to read and update_<id> to write. The workspace source is the exception; it exposes its read tools (list_files, search_content, read_file) directly to the agent. The crm source is the structured store: contacts, projects, meetings, reminders, notes, and queued updates in the crm Postgres schema. Writes are confined to that schema and every row is scoped to your user_id, so a guest can’t see this data. The knowledge source is the prose store for specs and research notes. It lives on the filesystem by default and can use a private Git repository in production.

​
Security

@context is an alter ego with access to a lot of sensitive information, so the security boundaries need to be airtight. The toolset is chosen in code from the request identity before the model runs. Production HTTP requests use verified JWT identities, and Slack events use signed author identities. Local HTTP development trusts the caller-supplied identity. The owner gets the full surface. A guest gets submit_update to append to your queue, my_updates to see only their own submissions, and owner_availability when Calendar is configured. The availability tool returns free/busy intervals without event details. Guests cannot access your CRM, knowledge base, inbox, or calendar events. Each caller gets separate user memory. The Slack, Calendar, and Gmail write tools are owner-only. update_slack sends messages immediately. update_calendar pauses for your explicit approval before it changes the calendar. update_gmail creates a draft for you to review and send. It never sends email. @context runs locally or in your own cloud. Its CRM and inbound queue live in Postgres. Its knowledge base lives on the filesystem by default and can use a private Git repository in production. Slack, Gmail, Calendar, and web are external sources accessed through provider APIs. See docs/SECURITY.md.

​
Run locally

Prerequisites: Docker installed and running. An OpenAI API key.
Confirm it is live at localhost:8000/docs. OWNER_ID decides who counts as the owner. Set it to your email; anyone else gets the capture-only guest tools. OWNER_NAME is an optional display name.

​
Connect the AgentOS UI

AgentOS comes with a web UI for managing and monitoring @context. Use it to chat with @context, view sessions, and approve actions.
  1. Open os.agno.com and sign in with the email you set as OWNER_ID.
  2. Click Connect AgentOS → Local, enter http://localhost:8000, and name it Local Context.
  3. Open the chat under Context and try one of the quick prompts.

​
Connect MCP clients

The main way to use @context is from an MCP client like Claude Code, Codex, Claude, Cursor, or ChatGPT. The local server runs at http://localhost:8000/mcp with keyless-as-owner access. With OWNER_ID configured, every client that can reach the endpoint is treated as that owner and receives the full read, write, and action surface. Keep the development endpoint on a trusted machine. One command adds @context to every MCP client on your machine:
The script finds Claude Code, Codex, Claude Desktop, and Cursor, and registers @context with each. Use --dry-run to preview and --remove to undo. To register the CLI clients by hand:
Claude Desktop and Cursor take config-file entries. See docs/MCP.md for both.

​
Deploy to Railway

@context runs anywhere that runs a Docker container. For a quick deployment, scripts/railway/up.sh runs @context and Postgres on the same private network. It reads credentials from .env.production and creates the public domain you connect to in the AgentOS UI. Prerequisites: Railway CLI installed and railway login completed.
1

Create a production env

The deploy scripts read .env.production first and fall back to .env.
2

Deploy

The script creates your public domain, then pauses and waits while you mint the JWT verification key.
3

Mint your JWT key

Token-Based Authorization is on by default. Without a JWT_VERIFICATION_KEY in .env.production, the AgentOS will not serve traffic. That is the safe default for an agent that holds your work context. You can also issue and verify your own JWT.
  1. Open os.agno.com, click Connect AgentOS → Live, and paste the domain the script printed.
  2. Turn on Token-Based Authorization and click Connect.
  3. Copy the public key into .env.production as JWT_VERIFICATION_KEY.
  4. Back in the terminal, press Enter. The script reads the key and deploys the service.
4

Verify

Open https://<your-domain>/docs to confirm the API is serving.
If you add or update values in .env.production, sync them with ./scripts/railway/env-sync.sh. After code changes, redeploy with ./scripts/railway/redeploy.sh, or connect the repo in the Railway dashboard to auto-deploy on push.

​
Point MCP clients at production

Production connections ride MCP OAuth. Setting MCP_CONNECT_SECRET turns the deployment into its own OAuth 2.1 authorization server on /mcp: a client connects by URL, and you approve it once on a consent page by typing the secret. up.sh already generated the secret on deploy. If you deployed before it existed, one command arms everything:
setup_context.sh makes sure MCP_CONNECT_SECRET and AGENTOS_MCP_SIGNING_KEY exist in .env.production (generating them when missing), syncs the env to Railway, runs an explicit code and image redeploy, and prints the connector recipe with your real domain and secret. Add --no-redeploy to skip the explicit railway up redeploy. Environment sync can still trigger a Railway redeploy when it pushes changed variables. Then connect your clients. In claude.ai or ChatGPT, add https://<your-domain>/mcp as a custom connector, leave the OAuth client ID and secret fields empty, and approve the consent page with the secret. For the CLI clients, uvx agno connect --url https://<your-domain> wires Claude Code, Codex, Cursor, and Claude Desktop and prints each client’s sign-in step. The AgentOS UI keeps working alongside; it authenticates with the os.agno.com JWT, a separate door from MCP OAuth. Rotating AGENTOS_MCP_SIGNING_KEY revokes every issued token, and rotating MCP_CONNECT_SECRET only gates future consents. See docs/MCP.md for the consent flow, per-client specifics, and ChatGPT and Claude on the web.

​
Back the knowledge base with Git

Local runs store the knowledge base in a gitignored knowledge/ folder. In production, back it with a private Git repo: create one, mint a fine-grained token with read and write access to its contents, and add both to .env.production:
Then sync with ./scripts/railway/env-sync.sh. Every update commits and pushes, so the git history is your audit trail. See docs/KNOWLEDGE.md.

​
Connect to Slack

With Slack configured, teammates can @-mention @context to leave you updates, you can DM it for private conversations, and the scheduled daily rundown and weekly plan land in your DMs.
  1. Create a Slack app from the manifest in docs/SLACK.md.
  2. Copy the Bot User OAuth Token and Signing Secret.
  3. Set SLACK_BOT_TOKEN and SLACK_SIGNING_SECRET in .env or .env.production.
  4. Restart the application.
Local runs need a public URL for Slack’s callbacks, so use an ngrok tunnel. Once you deploy, repoint the app’s /slack/events and /slack/interactions request URLs at your Railway domain.

​
Connect Gmail and Calendar

Connect Gmail and Calendar to ground the rundown and meeting prep in your real inbox and calendar. Set GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and GOOGLE_PROJECT_ID, then mint the consent tokens once with python scripts/google_mint_tokens.py. See docs/GOOGLE.md.

​
Example prompts

Try these from the AgentOS UI, Slack, or an MCP client:
  • Add Dana Reyes, Head of Platform at Acme, dana@acme.com. Remind me to send her the integration spec next Tuesday.
  • Who do I know at Acme?
  • What’s on today?
  • Prep for my 2pm with Kyle
  • Write up a decision: we’re standardizing on Agno
  • What in my knowledge base needs attention?

​
Run evals

@context comes with an eval suite (evals/) for regression testing the security model. It tests the claim that anyone can write and only you can read: deterministic gates check that a guest’s toolset stays capture-only and the MCP server stays owner-only, and an adversarial guest arc tries to break the boundary.

​
Source

The GitHub repo has the full detail: