Give your coding agent the whole stack.

Package MCP servers, APIs, and commands as focused Caplets. Your agent opens only what each task needs.

You choose every capability and credential boundary.

Any backend. One capability layer.

Turn the systems you already use into focused capabilities that travel across supported agents.

Backends flow through a reusable Caplet to supported coding agents.

CONNECT

  • MCP
  • OpenAPI
  • Google APIs
  • GraphQL
  • HTTP
  • CLI
  • Caplet files
Caplet

REUSE

  • CodexMCP
  • ClaudeMCP
  • OpenCodeNative · MCP
  • PiNative · MCP
  • Remote clientsRemote Attach
The definition travels. Credentials stay with each host.
Create a Caplet

One agent. The whole job.

Move one change from issue to production without carrying every handoff yourself.

  1. LinearRead issuerequirements
  2. GitHubChange codepull request
  3. CICheck buildverified
  4. DeployReleaseproduction
  5. StatusReportclosed loop

Each step runs only after you expose and authorize that capability.

Smaller surface. Same completed work.

Code Mode cut the tool wall and token load without losing the result.

10/10
tasks completed
72.0% fewer
request + output tokens
7 vs 215
initial choices
Run June 2026 with the real-world large MCP suite, openai-codex/gpt-5.5, 10 tasks, 2 runs per task, and a large no-fixture MCP stack.Review the benchmark

Get one real result.

Set up Caplets and run OSV. No authentication required.

OSV

Add OSV

Public vulnerability lookups. No token or OAuth.

OSV quickstart
  1. caplets setup
  2. caplets install spiritledsoftware/caplets osv
  3. codex "try using the osv caplet"