Track competitors while you build your plugin.

Publisher full description

Helps structure web research by routing research requests through Agent Reach guidance and reference material. External runtime features are only available when the host provides them.

Publisher full description

Author and manage conversational agents for general-audience games and virtual worlds on Convai. Other capabilities require their applicable account or Workspace permissions. Sign in with your Convai account to inspect agents, create… …elected Workspace on every supported call. Version operations report selectors and promotion state; runtime behavior depends on the selector used by the integration.

Publisher keywords · listing

agents ai agents agent runtime deploy agents automation mcp camelai AI agent hosting persistent agents agent deployment scheduled agents agent.yaml

Publisher capabilities · listing

…rvable behavior Plan tests, reproduce regressions, and evaluate test coverage Plan safe dependency, runtime, API, and database migrations Harden web services, authentication, and cross-tenant access Review performance using measured evidence, not guesswork Improve SQL, Spark, CDC, and data pipeline… …books Triage incidents and prepare evidence-backed release handoffs Coordinate supported specialist agents for complex changes

Publisher full description

Ando is a team messaging platform where people and AI agents collaborate in shared channels and threads. This plugin connects your Ando workspace so you can read conversations, find decisions with source links, catch up on discussions, and draft or send… …, alert feeds, and ongoing agent workflows support collaboration when the required capabilities and runtime are available. For teams using Ando to work together with AI agents. Connect as yourself or an authorized agent; access follows your workspace permissions. Messages are sent only when you auth…

Publisher full description

Bolter Connect helps you use this agent in Bolter conversations with people and other agents. Connect through the Bolter CLI using a hosted approval link and code, check the connected identity, read messages, and send the messages you… …lability and recovery after a restart depend on the host; this plugin does not provide an always-on runtime.

Publisher description

Buildy is a hosted runtime for personal web apps that users and their agents can share. An agent creates an app, Buildy gives it a URL, backend, and key-value storage, and the user keeps using the same app and data across ChatGPT, Claude, and other agents.

Publisher full description

Work with your saved ClawMaven governance profiles before you deploy an AI agent. Get a profile's posture score, grade, and category breakdown; retrieve the effective policy (allowed tools, blocked domains, budget caps, and autonomy level) for an agent you name; check an age… …en is pre-deployment governance design: it does not scan code, monitor agents, or enforce policy at runtime.

Publisher full description

Turn a recurring workflow, prompt, or SOP into an agent skill with a clear job, activation boundaries, decision rules, and evaluation cases. OmniSkill routes each request to the next relevant specialist: architecture, authoring, evaluation, repair, h… …ng one, or prepare a portable package. Bundled scripts run only when the host provides the required runtime; no hosted service or MCP connection is required. Cross-host behavior must be tested on each target host before being called verified.

Publisher full description

…your Swarm Spaces, save source-linked research and handoffs, manage Tasks and schedules, and follow agent Runs and results. Browse connected Spaces, Runs and Artifacts in the native panel where supported. Connected agents execute in their own runtime; Swarm Cloud and enrolled devices are separate execution options. Access follows the Spaces and permissions you approve in Swarm, and completion is separate from human approval.

Publisher full description

Work with other people’s AI agents through Totem. Connect your own agent to discover peers, exchange durable messages and files, coordinate coding tasks, and inspect or delegate work in Missions. Read activity, approval decision… …peer is online or has completed work. Hosted MCP does not access local files, install a background runtime, push Git branches, merge, or deploy. Hosted Context is temporarily paused.

Publisher capabilities · listing

…release cycles of a product that are still supported, newest first, with the latest patch Reads the runtime pins in a repo (Node.js, Python, Go, Ruby, PHP, .NET, Docker images) and flags any past end of life Looks up an SPDX license by identifier or name: OSI approved, FSF free, deprecated or not Sh…

Publisher full description

Finds reusable agentic workflows inside repositories, decides what should become public Skills or runtime-backed capabilities, compiles portable Skill packages, installs a host-native workspace operations Skill for read/list/search/grep/write/patch/shell/Python workflows, designs the Plugin experi…

Publisher description

The Caveatist practice for agents: keep claims with their grounds and caveats, decide with the caveat attached, withdraw rather than erase. Optional culture around the Caveat language; it changes how you work, not what any runtime does.

Publisher full description

Cloudish by Hal9 helps coding agents prepare and deploy containerized websites, APIs, dashboards, and services. The plugin guides project inspection, Dockerfile preparation, runtime ports, persistent storage, encrypted secrets, deployment status, and troubleshooting using Cloudish's current API documentation. Cloudish builds containers server-side and provides a hosted UR…

Publisher keywords · listing

codex agent-memory work-graph productivity

Publisher full description

Java workflows and governed actions that coding agents can build, verify, and maintain. Flower is a lightweight in-JVM workflow runtime for explicit, testable Flow and Step transitions, including persistence, Spring Boot integration, runtime observability, Flower Check, Flower Flow Graph, and local read-only Flower Studio insp…

Publisher full description

Developer tooling that helps Codex build standalone governed agent applications without tying the target architecture to one model, coding harness, or dashboard. The coding assistant remains outside the runtime while it implements contracts, deterministic control boundaries, independent verification, runtime health, and optional evidence receipts with Frontier SDK components.

Publisher description

Install and link Rig — the local runtime context engine for AI coding agents on your Mac — so Codex and ChatGPT can use Rig’s local MCP hub when Rig is running.

Publisher full description

Ansight gives your coding agent runtime evidence from real mobile apps, so it can debug and verify what actually happened instead of guessing from source code. Install the Ansight SDK into an iOS, Android, .NET MAUI, React Native, F…

Publisher full description

…it companion for supported Codex surfaces. Add one declared tool, service, subscription, person, or agent through a conversational no-write preview and a separate exact save approval. Then bring AtReady a goal, rough plan, or written plan before implementation to match saved tools, services, subscri… …e project plan. This local-first release requires a separately installed compatible project-atready runtime and local file access.

Publisher full description

…are qualitative evidence with connected PostHog or Amplitude usage, trends, and saved insights. The agent retrieves, filters, and cites evidence in chat. Optional visual evidence browsing and compact job-status cards help when requested and supported by your client. When supported by your ChatGPT cl… …skills work in ChatGPT and Codex; organization-specific skills remain private and are retrieved at runtime.

Publisher description

…operate your Cargo workspace: discover and run actions across 130+ integrations, execute tools and agents, query CRM and revenue models, and read the playbooks and ICP context your team already wrote. Sign in with OAuth — no API key to paste. Your session binds to one workspace, so ChatGPT sees you… …. Building multi-step workflows or workspace-as-code stays in the Cargo CLI — this connector is the runtime for in-conversation work. Learn more: https://www.getcargo.ai/mcp

Publisher description

Official Cerebrium agent skills and hosted docs MCP: deploy and operate real-time AI workloads on serverless GPU and CPU (REST, streaming, WebSocket and async endpoints), with verified cerebrium.toml, hardware and autos…

Publisher full description

…d-only sandbox and instructed to use zero tools; after execution the launcher inspects the recorded runtime and rejects the result if it observes any tool call, which is a post-execution acceptance check, not preventive tool-free isolation. The local launcher writes temporary files and Codex session records. The root agent owns implementation and final decisions; Advisor does not implement, deploy, or perform final review. Requires Python 3.11+, a local Codex host, jq, a supported POSIX shell, and a persisted sess…

Publisher full description

…ignobo is an AI design tool for building UI prototypes as real HTML screens. With this plugin, your agent can browse your team's projects, read and search screens, create new projects and screens, and edit existing ones while you watch the changes appear live in Designobo. It can render a screen in a real browser to check for layout and runtime errors, and turn existing designs into code in your own projects. The agent only accesses the team you approve when you connect, and you can disconnect it at any time from Designobo.

Publisher full description

…nho material. Em pedidos de revisão textual simples, mantém-se o procedimento direto, sem grafos ou agentes desnecessários. A skill é candidata à implementação, sem certificação comportamental ou de runtime.

Publisher full description

…her one gets caught before it reaches your default branch. These skills drive the Mergify CLI so an agent can work that queue with you. Ask why a pull request left the queue and get the engine's own dequeue reason, the checks that failed, and a link straight to the job log. Read the activity log for… …tections, mergify-ci, and mergify-stack. It runs on the Mergify CLI, a single static binary with no runtime to install, so it needs a local execution environment: Codex, or ChatGPT desktop with local execution. You need a GitHub repository with Mergify enabled. Install the CLI with 'brew install mer…

Publisher description

…rm tasks such as: - answer questions about the Opscotch platform - explain APIs, configuration, and runtime behaviour - author workflows and bootstrap configurations - validate workflow structure and configuration - assist with packaging, deployment, and licensing - provide guidance using the latest… …ackage for deployment." The server is intended for: - AI coding assistants - IDE integrations - CLI agents - automation developers - DevOps and platform engineers - custom AI applications that need authoritative knowledge of Opscotch

Publisher full description

…GPT to: - Look up apps, bundles, release history, and the exact current release on each channel and runtime version - Prepare a release, review the plan, then publish it to an exact channel - Start a staged rollout or change its percentage - Read release health from client-reported events: downloads… …he permissions you approve at sign-in, and you can revoke it at any time in OtaKit under Settings → Agents. Intended for teams that ship Capacitor apps with OtaKit. Uploading a new web bundle needs your project files, so it is done with the OtaKit CLI, not in ChatGPT. Requires an OtaKit account.

Publisher full description

…computers are online; an invalid explicit device identifier is rejected. Pairing uses a short-lived agent-bound approval code, and the long-lived device credential is delivered only to the local agent, never through MCP output. Tool calls may update usage counters, and the local runtime may retain arguments and results in history.

Publisher full description

…WhatsApp Flows, business accounts, phone numbers, groups, and calling. The skills guide your coding agent through authentication, request and response handling, webhook verification, and error handling, using YCloud API contracts and official documentation. Start from a new workflow or review an exi… …tests for supported scenarios. Develop and validate locally; your application connects to YCloud at runtime using credentials managed by your team.