Native mounts
Finder, editors, and apps see normal paths. No browser dashboard, no custom client.
Every API your agent needs. One folder.
Paste an OpenAPI, GraphQL, or MCP server URL and Parlo connects instantly. APIs and cloud storage mount as ~/parlo. Agents discover the right tool by intent, not by scanning schemas. No SDK, no glue code.
parlo; zsh
mounted
$ ls ~/parlo
drive/ github/ linear/ projects/ stripe/
$ ls ~/parlo/projects/video
q3-launch.mov timeline.prproj
$ head -3 ~/parlo/linear/ENG-123.md
--- id: ENG-123 state: In Progress
Parlo Drive
Works with your favorite tools & platforms
Paste a URL. Get a filesystem.
Watch a new service get mounted live. Once it's connected, you'll see how to use it.
Connect any APIparlo connect …
One filesystem. Three interfaces. Same Stripe API calls under the hood.
Humans and agents, editing together.
Your AI agent writes from the CLI while you edit in the browser. Every keystroke syncs instantly, and version history shows exactly who wrote what.
projects/roadmap.mdLive
EditPreviewSplit
R
C
1---
2title: Q3 Product Roadmap
3updated: 2026-06-07
4---
5
6# Q3 Product Roadmap
7
8## Launch milestones
9
10- [x] Cloud drives with on-demand caching
11- [x] API connections as markdown files
12- [x] Live collaborative editorRob
13- [ ] Public share links
14- [ ] Commenting and threads
Version history
Rob2 min ago
Claude5 min ago
Rob12 min ago
Claude1 hr ago
Markdown preview & JSON viewerVersion history; who wrote whatHuman + agent, same session
Sign upFree — no credit card required
APIs become folders. Files stay in the cloud.
Paste any API URL to connect instantly. Browse APIs as markdown files. Store projects in cloud-backed drives that mount locally, cache on demand, and are accessible via MCP from any agent.
Connect any API instantly
20+ pre-built services ready to go. Paste any OpenAPI, GraphQL, or MCP server URL and Parlo connects in seconds, no code required. Agents find the right tool by intent via semantic search.
ShopifyAny API
Cloud storage you can mount anywhere
Store your files once. Access them from any machine; your laptop, a CI runner, an agent sandbox. Parlo caches what you touch and streams the rest on demand.
No bulk syncMount first. Fetch bytes only when your app reads them.
Local hot cacheWarm files and scrubbed ranges stay on disk for instant replay.
MCP endpoint includedOne hosted MCP server covers all your connections and drives. No extra setup.
Share with a linkparlo share; get a URL anyone can open, no account needed.
The filesystem is the interface.
Paste a URL to connect
Paste any OpenAPI, GraphQL, or MCP server URL. Parlo builds the adapter and connects in seconds. Full CRUD with destructive ops gated by policy.
Agents just work
Claude Code, Codex, Cursor read and write files. Agents discover tools by intent via semantic search, not by scanning every schema. No per-service SDK required.
Teams share context
Connect once, every member's agents see the same live data. No per-agent setup.
Edit in the browser
Click any file to open a live editor. Markdown preview, JSON viewer, multiplayer cursors. Agent writes appear instantly.
Auto-versioned
Every write creates a snapshot with diffs. See who changed what; human or agent; without git.
How Parlo compares
Every approach gives agents API access. Only one does it without custom code.
Parlo
MCP servers
Custom SDK
Setup time per service
~30 seconds
Hours
Days
Lines of glue code
0
100–500
200–1,000+
Agent compatibility
Works with any agent
Prompt tokens per service
~200
2,000–8,000
1,000–5,000
Add a new API
Paste a URL
Build a server
Write an integration
Tool discovery
Semantic / by intent
Manual
Manual
Destructive ops
Gated by policy
Uncontrolled
Uncontrolled
Cloud file storage
Team sharing
Built for agents that already know files
Let agents explore the workspace instead of loading every tool.
Parlo mounts APIs and cloud storage as native folders and files. Agents discover with ls, inspect with cat, and search with grep ; so they act on only the exact resource needed.
Without Parlo100 MCP tools loaded
6,638 prompt tokens · 6 tool calls
With Parlo~/parlo mounted
1,407 prompt tokens · 1 file read
78.8% less prompt context · same result
Simple, transparent pricing
Start free. Scale with your team.
Free
For individuals getting started.
$0
- 10 GB cloud storage
- 3 drives
- 5 API connections
- 10 adapter generations / hour
- Community support
Starter
For developers using Parlo daily.
$19/mo
- 50 GB cloud storage
- 10 drives
- 25 API connections
- 50 adapter generations / hour
- Priority support
Most popular
Pro
For power users and heavy agent workflows.
$49/mo
- 200 GB cloud storage
- Unlimited drives
- Unlimited API connections
- 200 adapter generations / hour
- Bulk exports (all.jsonl)
- Priority support
Teams
Business
For teams sharing context across agents.
$29/seat/mo
- 1 TB shared storage
- Team drives & connections
- Invite & manage members
- Org-scoped API connections
- All agents see the same data
- SSO (coming soon)
Enterprise
For organizations at scale.
Custom
- Unlimited storage
- Unlimited everything
- Custom adapter SLAs
- SSO & SCIM provisioning
- Dedicated support
- On-prem / VPC deployment
All plans include encrypted token storage, real-time sync, and FUSE mounts.
Prices in USD. Annual billing available on Pro and above.