io.github.everyai-com/agentprofile

agentprofile

Your agent's identity, everywhere. One profile — skills, credentials, and memory — synced to every agent tool through a single MCP URL. Open source, zero-knowledge, and self-hostable on your own Cloudflare account.

Every AI tool you use — Claude Code, Cursor, Codex — starts from zero: its own skills, its own pasted API keys, its own amnesia. agentprofile gives them one shared brain.

Live now: hosted at **https://agentprofile.everyai-com.workers.dev** · dashboard at /app

Connect (any MCP client)

The server is a remote MCP server (Streamable HTTP) — no install needed, just one URL:

https://agentprofile.everyai-com.workers.dev/mcp

It supports two ways to authenticate:

• OAuth (recommended) — clients that support MCP OAuth discover it automatically from the URL and show a consent screen.
• Bearer token — run npx @magicteams_ai/agentprofile to get a token, or hit POST /profiles.

Claude Code

claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcp

Or with a bearer token:

claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcp \
  --header "Authorization: Bearer ap_…"

Cursor / other mcp.json clients

{
  "mcpServers": {
    "agentprofile": {
      "url": "https://agentprofile.everyai-com.workers.dev/mcp",
      "headers": { "Authorization": "Bearer ap_…" }
    }
  }
}

Codex CLI

export AGENTPROFILE_TOKEN="ap_…"
codex mcp add agentprofile --url https://agentprofile.everyai-com.workers.dev/mcp --bearer-token-env-var AGENTPROFILE_TOKEN

Or, for a client that does OAuth discovery:

codex mcp add agentprofile --url https://agentprofile.everyai-com.workers.dev/mcp

VS Code / Copilot

{
  "servers": {
    "agentprofile": {
      "type": "http",
      "url": "https://agentprofile.everyai-com.workers.dev/mcp"
    }
  }
}

Or just run npx @magicteams_ai/agentprofile and it configures every client it finds.

60-second demo

npx @magicteams_ai/agentprofile

That creates an anonymous profile (no signup) on the hosted instance, auto-detects your installed MCP clients, and writes their config. Restart your tools, then:

1. In Claude Code: "Remember that I prefer pnpm over npm."
2. In Cursor: "What package manager do I prefer?"

It recalls it. That's your profile, everywhere.

What's in this repo (Phase 1)

This is the Phase 1 implementation from the master plan: a working end-to-end skeleton that syncs skills and memory across tools over MCP. Credentials (zero-knowledge), OAuth, semantic recall, and the skill registry land in later phases — see Roadmap.

Web UI

• / — landing page with the one-command install and the pitch.
• /app — live dashboard. Paste your token (or hit "Create new") and watch skills and memory update in real time: when any agent calls remember, the fact appears instantly over a WebSocket. Add or delete memories and skills right from the page.
• /setup-prompt — the "set up with your agent" prompt: paste it into Claude Code or Cursor and your own agent installs and verifies agentprofile for you.

How it works

agent tool ──Streamable HTTP──▶ Worker ──idFromName(profileId)──▶ ProfileDO
  (Claude Code / Cursor)          /mcp                            per-user SQLite
                                                                  • facts (memory)
                                                                  • skills

• One Durable Object per user is the source of truth. It validates the profile's secret on every call and owns that profile's memory and skills.
• Bearer token = ap_<profileId>.<secret>. The profileId routes to the DO; the DO verifies a SHA-256 hash of the secret. No central token table.
• The MCP surface is 6 tools: get_context, list_skills, get_skill, remember, recall, forget. Deliberately small — every description byte is paid on every client turn (pinned in tests).

Run it locally

npm install
npm run dev            # starts the Worker on http://localhost:8787

In another terminal:

# point the CLI at your local server
AGENTPROFILE_SERVER=http://localhost:8787 npx @magicteams_ai/agentprofile

Run the tests and typecheck:

npm --workspace apps/worker run test
npm --workspace apps/worker run typecheck

Deploy your own (self-host)

agentprofile self-hosts on your own Cloudflare account — the free Workers tier covers personal use.

cd apps/worker
npx wrangler r2 bucket create agentprofile-bundles
npx wrangler deploy
# then set PUBLIC_BASE_URL to your deployed URL and connect with:
AGENTPROFILE_SERVER=https://agentprofile.<you>.workers.dev npx @magicteams_ai/agentprofile

Roadmap

• P1: MCP server + ProfileDO, 6 tools, memory + skills, instant-profile CLI, live dashboard. ✅
• P2: per-client grants + audit log with live enforcement + dashboard access panel ✅; MCP sessions (Mcp-Session-Id) ✅; semantic recall via Workers AI embeddings (keyword fallback) ✅; pluggable memory providers (builtin default + Mem0 + Supermemory adapters, /memory-config) ✅; OAuth 2.0 + PKCE consent flow with discovery, dynamic registration, and consent screen ✅.
• P3: zero-knowledge credentials (client-side E2E), JIT injection, approval flow.
• P4: one-click Deploy-to-Cloudflare, signed skill registry, format translators.
• P5: teams, SSO, hosted cloud.

See the full plan in docs/.

Contributing

Contributions are welcome under the DCO — sign off commits with git commit -s. See SECURITY.md for responsible disclosure.

License

Apache-2.0.

Part of the everyai-com agent stack

Open-source infrastructure for local-first, governed AI agents:

• distillory — local-first memory engine that reasons at ingestion
• agent-ready — turn any app into an MCP server + API + CLI, safe by default
• primer — live business context injected into any agent
• plainsync — local-first Markdown workspace for humans + agents
• argus — cloud-native software verification with parallel browser testing
• mintly-alternative — self-hostable documentation layer for humans + AI agents
• talltrack — sales calls in, publishable content out

Built by Phanindra Reddy · magicteams.ai