Browse agents

Control a Portveil WireGuard VPN account: list devices with their live speed, and move, rotate, reconnect or disconnect agent machines between exit countries. Moves only count once the exit server confirms the device.

Access Tilt resources, logs and management operations for Kubernetes development environments.

Manage Sevalla cloud infrastructure.

Deploy static HTML folders to permanent Vibie URLs, with folder markers for easy redeploys.

Deploy and manage static sites: upload files, get a URL and connect custom domains.

Cloud infrastructure analysis: detect IaC drift, missing indexes, security gaps and performance anti-patterns across AWS services and databases.

Manage any Kubernetes resource, including native resources and CRDs, through natural language.

Deploy live HTTPS websites on subdomains or custom .xyz domains, paid in USDC on Base, with templates for crypto tokens and AI agent profiles.

Manage domains, DNS records, contacts and marketplace listings via the Spaceship API.

SRE observability for Kubernetes and OpenShift: Tekton pipeline debugging, log analysis, root cause analysis and predictive monitoring.

Interact with Kubernetes clusters: list and apply Kubernetes resources.

Interact with OCI registries: retrieve container image information, list tags and more.

Publish a static site or edge function to the web in one call, then manage updates, custom domains, SSL, env vars, databases and email.

Publish agent-made HTML to private, unguessable URLs with passcode or email-domain gating, expiry, burn-after-read and in-place updates.

Kubernetes cluster operations.

Interface with Nutanix Prism Central resources.

Get up-to-date EC2 prices in one call from a pre-parsed AWS price catalogue.

Multi-client MCP proxy: read across every client's accounts, write only to the named one, via providers' own MCP tools (Cloudflare, Vercel, Notion and more).

Query book information.

Multi-cluster Kubernetes management and operations with a management UI and logging, covering common DevOps tasks for standard and CRD resources.

Multi-cluster Kubernetes management and operations, embeddable as an SDK, covering common DevOps tasks for standard and CRD resources.

Kubernetes management plus cluster and application health analysis.

Kubernetes cluster operations: inspect pods, deployments, services and logs.

Build and host full-stack web apps and sites on Hatchable, with per-project database, auth, storage, domains and cron.

Live AWS, GCP and Azure prices for FinOps: public list prices and enterprise negotiated rates (Reserved Instances, Savings Plans, CUDs, EDPs).

Cloud architecture design for AWS, GCP, Azure and Databricks: cost estimates, compliance checks, Terraform/CloudFormation export and blast-radius analysis.

Install and manage a self-hosted XNS Relayer, S3-compatible object storage on a decentralized provider network: setup, health, configuration and backups.

VMware vSphere/vCenter management: VM lifecycle, deployment, guest operations, snapshots and clusters, with confirmation gates, dry-run mode and audit logging.

VMware Avi Load Balancer (NSX ALB) management with AKO Kubernetes integration: virtual services, pools, analytics metrics and AKO lifecycle.

Read-only VMware vSphere/vCenter monitoring: inventory, alarms, events, host health, VM info and snapshot listing.

VMware NSX network management: segments, Tier-0/Tier-1 gateways, NAT rules, static/BGP routing and IPAM pools, with dry-run previews and delete confirmation.

VMware NSX security: Distributed Firewall policies and rules, security groups, Traceflow troubleshooting and IDS/IPS profiles, with checks before deletion.

VMware vSphere storage management: NFS/VMFS datastores, iSCSI software adapters and dynamic targets, and vSAN cluster operations, with dry-run previews.

VMware Tanzu / vSphere Kubernetes Service: Supervisor cluster, namespace and Tanzu Kubernetes Cluster lifecycle, with dry-run mode and kubeconfig export.

Publish Markdown or HTML to a public shareable link, served script-free from a separate cookieless origin.

Run JavaScript snippets in isolated Docker sandboxes with on-the-fly npm dependency installation and clean teardown.

Execute code through the Piston remote code execution engine.

E2B cloud sandboxes: create isolated Linux VMs, clone repos, run commands, manage files and perform git operations without touching the local machine.

Access any API through its existing OpenAPI documentation.

Containerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.

Dedicated Linux VM sandboxes for untrusted, model-generated code: run commands, move files, expose a preview URL and destroy the VM.

Delegate tasks to other AI providers' models, e.g. ask OpenAI to generate an image.

Python runtime interpreter that executes submitted code in an isolated environment.

Submit SLURM jobs, run YAML workflows, monitor GPU resources, manage SSH profiles and sync files with local or SSH-remote HPC clusters.

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

Self-hostable GPU-aware job broker: dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier and monitor them across sessions.

MATLAB integration: execute code, run async jobs with progress reporting, get interactive Plotly plots and expose custom .m functions as tools.

Access any API via its OpenAPI specification, with full JSON Schema support for parameters and request bodies.

JavaScript sandbox that uses V8 isolation to run AI-generated code locally, with heap snapshotting for persistent sessions.

Persistent cloud dev environments for coding agents: create, run commands, checkpoint and fork, with files, services and terminal state kept between calls.

SWI-Prolog execution for LLMs with CLP(FD), negation as failure and recursion.

Control Google Colab notebooks and assign GPUs (T4/L4/A100). Fork of Google's colab-mcp with all tools visible at startup and Windows support.

Agent-oriented programming language: agents emit a JSON AST that the compiler validates, type- and effect-checks, verifies with Z3/SMT and compiles to WASM.

Code-mode MCP server: collapses user-defined tools into code execution plus docs search, sandboxed in node:vm, WASM or remote microVMs.

Code and logic calculator with an offline core: run code, exact symbolic math, SMT/logic and complexity analysis, with optional gVisor/AppContainer sandboxing.

Run LLM-generated code in a YepCode sandbox and create custom MCP tools in JavaScript or Python with npm and PyPI packages.

Localhost review board where different coding agents (Claude Code, Codex, OpenCode, Trae, ZCode) review each other's work: objections must state flip conditions, revisions clear all verdicts, resolution requires the whole active quorum, and every vote is append-only audited. Ships its own audited self-review history as evidence. Install: `pipx install mcp-review-board`.

Shared session bus for coding agents such as Claude Code, Codex and Grok: list, read, hand off, message and spawn live agent sessions via MCP or CLI.

Manage a 5dive agent fleet: file tasks, message and inspect agents, and read the fleet digest.

Explore and download AI agent blueprints: list them, get summaries and download full Agent Skills directories for coding agents to implement.

Self-hosted relay where coding-agent sessions on different machines share a team board, message each other and check for git conflicts, with isolated teams, private sessions and an OAuth MCP endpoint for Claude in the cloud.

Document exchange for coding agents across services: versioned Markdown store, pub-sub notifications with structured diffs and lifecycle stage tracking.

AI council: query CLI agents (Claude Code, Codex, Gemini and OpenCode) in parallel with deliberation rounds.

Delegate tasks to the Antigravity CLI (Gemini): file analysis, repo archaeology, web lookups and second-opinion code reviews, with quota-aware model failover.

DevOps and networking tools: network monitoring, system diagnostics, automation workflows and infrastructure management.

Control plane for long-running Codex Desktop tasks: submit asynchronously, poll state, approve Plan Mode, recover retries and search SQLite-backed history.

Structured, model-driven interaction with network devices via Cisco pyATS.

Adversarial test generation in Cline: detects the stack, writes and runs tests, and classifies failures as real bugs, environment problems or test bugs.

Local MCP that lets a Chief of Staff client find, create and register Codex projects; submit exact prompts; track durable receipts; continue existing tasks; and organize scoped work inside allowlisted directories.

Interact with TUI/CLI applications through a structured terminal state tree with element detection, like Playwright for terminals.

IDE assistance for the Intlayer i18n/CMS tool: CLI access and documentation.

Self-hosted Slack bot: mention it and Claude Code or Codex investigates CloudWatch logs, runs tests and opens PRs, with credentials held by an MCP server.

Shared, signed index of failures other coding agents already solved: check it before retrying and ingest fixes so the next agent does not repeat the work.

Multi-agent consultation for Claude Code: MCP servers wrapping Codex, Gemini and Qwen CLIs for parallel code review and problem-solving with fallback chains.

SSH control for Linux and Windows servers, with long-running commands and execution on multiple hosts at once.

Local router for Agent Skills across coding agents and MCP clients, with hybrid matching on the local CPU that spends no tokens.

Deterministic orchestrator for CLI coding agents such as Claude Code, Codex and Aider, with per-agent git worktrees, an audit trail and cost-aware routing.

Delegate multi-file implementation to Cursor's CLI agent over ACP and get typed results: final message, changed files, session ID and plan.

Coordination bus for multiple coding agents: atomic claims, advisory file leases, a shared event ledger, presence, handoffs and a task graph. Self-hostable.

Coordinate parallel coding agents: TTL file claims across git worktrees, hooks blocking colliding edits, presence, handoff notes and searchable lessons.

Search, retrieve and solve LeetCode problems, with metadata filtering and access to user profiles, submissions and contest data.

Turn any CLI tool with --help output into an MCP server, with caching.

Reasoning, code, anti-deception and memory tools for AI agents.

Coding agent with basic read, write and command line tools.

Multi-LLM deliberation with anonymized peer review: parallel responses, anonymous ranking and synthesis, based on Andrej Karpathy's LLM Council concept.

Delegate tasks to OpenClaw AI assistant agents with sync and async tools.

Communication and shared work state across coding agent harnesses: live messages, scope claims before editing, preserved decisions and evidence handoffs.

Access iTerm: run commands and ask questions about what is shown in the terminal.

Local daemon that pre-indexes a codebase into a SQLite catalog and serves AST-compressed snapshots on every query to reduce token usage.

Structured planning and validation for Claude Code: turns an objective into a validated DAG of modules built by worker agents in parallel git worktrees.

Run arbitrary commands and scripts.

Rust reimplementation of WCGW for coding agents: shell execution and file management.

Wraps the Claude Code CLI as MCP tools for queries, search, structured output and sessions, with budget caps and granular tool sandboxing.

Requires every AI agent code change to leave a problem, reason and approach audit record before commit, with a pre-commit hook and audit trail dashboard.

Delegate real-world actions to Hermes Agent: research, browser workflows, messaging, scheduling and skills, with risky actions requiring approval.

See and control long-running processes such as web servers: start, stop, restart and read logs.

Specialist agent council for AI coding CLIs with a self-learning router, cross-CLI memory and guards against dependency hallucinations and decision drift.

Access LeetCode problems, solutions, submissions and public data, with optional login for user features such as notes; supports the global and China sites.

Work in a VS Code workspace: read the directory structure, see linter and language server problems, read code files and make edits.

Governed runtime for AI coding agents with budget caps, verifier gates, runaway-loop prevention, rollback evidence and inspectable run receipts.