vibekit by superagent - open-source sandbox and safety layer for coding agents
About VibeKit (Superagent)
Looking for the mobile AI app builder at vibekit.bot? That is a different product: see VibeKit at /tools/vibekit-bot. This page covers superagent-ai/vibekit, the open-source sandbox.
MIT-licensed CLI wrapper and SDK from Superagent (YC) that runs Claude Code, Gemini CLI, Codex, Grok CLI, and OpenCode inside an isolated sandbox, redacting secrets from completions and logging every file change, shell command, and outbound call. Install with npm and prefix your usual command: `vibekit claude`. The local path uses Docker and needs no cloud account; the `@vibe-kit/sdk` package embeds the same sandboxing in your own app across E2B, Dagger, Daytona, Northflank, Cloudflare, Modal, and Fly.io. Development has been quiet since November 2025: no commits to the default branch since 2025-11-10, no npm publish since 2025-10-14, and Superagent's recent work has shifted to its grok-cli and gateway projects. The code is MIT and still installs, so treat it as forkable rather than actively supported.
Naming history, and there are three collisions worth knowing. First: in July 2025 the team shipped an open-source v0 clone called vibe0, built on VibeKit. That name has been retired and the project is now just VibeKit, with the template surviving in the repo as templates/v0-clone. Second: VibeKit at vibekit.bot is an unrelated mobile-first AI app builder by Brian Boisjoli, still actively shipping, and its own about page states it is not affiliated with this project. Third: Vibe Scan at vibe0.com.au is a security scanner from a Perth consultancy that happens to share the vibe0 name.
Key Capabilities
Wraps any coding agent CLI in an isolated sandbox
Strips secrets and API keys out of completions
Logs file changes, shell commands, and outbound calls
Local Docker path runs with no cloud account
SDK embeds the same sandbox across seven providers
Dormant since November 2025: fork rather than depend on it
Standout Features
Sandboxed Execution
Agents run in a Docker or cloud sandbox instead of your host machine.
Secret Redaction
Strips API keys and sensitive values out of agent completions.
Full Observability
Records file changes, shell commands, and outbound network calls.
Agent Agnostic
Prefixes Claude Code, Gemini, Codex, Grok, and OpenCode alike.
Perfect for
Pricing
How much does VibeKit (Superagent) cost?
Free, MIT licensed. No paid tier for the project itself; cloud sandbox providers bill separately
Compare VibeKit (Superagent)
Similar Tools to VibeKit (Superagent)
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
free-claude-code
MIT-licensed local Python gateway that sits in front of coding agents and routes Anthropic-format traffic to free, paid, subscription and local backends. The README claims 50 ToS-friendly providers, 1.3B+ free tokens a month and 10 coding agents (Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider) behind one searchable model catalog, with automatic fallback to the next configured model when a provider fails. It is an independent project, not affiliated with Anthropic: you keep the agent harness, not Claude's weights, and free-tier limits belong to each upstream provider and may change. A GitHub issue titled "Malicious claims about this repo" is a community dispute, not a verified finding, and no privacy or security policy page exists beyond the README.
Apache Maka
Apache-incubating agent workspace where the Desktop app, the TUI and the CLI are thin clients of one Runtime Host, and every model message, tool call, permission decision and termination is written as an append-only RuntimeEvent: the project's own line is "the log is the runtime". You bring the model (a cloud API, a local model or a compatible gateway) and sessions, settings and run records stay on your machine. Its site publishes a nine-harness Terminal-Bench 2.1 table with per-task CSVs rather than a headline claim. Read the status before installing: as of 8 September 2026 Maka has not made an Apache release, the desktop nightlies are unsigned previews not intended for production, and the CLI ships as maka-agent@next on npm (the unrelated maka package is not this project). Its SECURITY.md is unusually direct: the only enforcement boundary against an adversarial LLM is the operating system, and API keys sit in a local plaintext credential file readable only by your OS account.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
Moadim
A loop engine that runs coding agents on a schedule against your codebase. A loop pairs a prompt, a schedule and an agent (Claude, Codex, Hermes, NanoClaw or Pi), and each run executes in a throwaway workbench so a hung run gets killed rather than left behind. Everything is exposed twice, as a REST endpoint and as an MCP tool, so another agent can schedule work as easily as you can. Routines live in ~/.config/moadim/ and are git-trackable. It runs entirely on your own machine: no cloud, no account, no data leaving the host.
OKF Agent Memory
Persistent memory for coding agents kept as plain files in your repository rather than in a vector database. It implements Google's OKF v0.2 specification with progressive disclosure, so the agent pulls in only the slice of memory a task needs instead of paying for the whole store on every request, and retrieval uses BM25 rather than embeddings. Because the memory is git-native it diffs, reviews and reverts like the rest of your code, and it publishes its own security documentation, which is unusual for a tool whose entire job is persisting context to disk.
Related Articles
Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.
ready to try vibekit (superagent)?
go to the official site and judge VibeKit (Superagent) yourself.
try vibekit (superagent) now