Catnip

Open source toolPersistent environment

Run Claude Code Everywhere — a containerized web service that automates git-worktree creation and runs many AI coding agents in parallel, operable from the web, a native iOS app, or SSH.

Homepage Docs Repository

Scanned 7 Jun 2026 · Schema v5 · features v10

Licence: Apache-2.0
Self-hosted; you pay for the infrastructure.
Free tier: Free to run
Isolation: Container
shares the host kernel
Regions: —
Not disclosed on the public surface.
Capabilities: 7 / 50
4 partial · 21 fail · 11 not assessed
Agent readiness: 4/10 · 5/8
read · drive, pre-login surface

Advertised for

Parallel AI coding agents · Claude code sessions · Containerized dev environments · LLM app development · Remote mobile coding

Built for

Developers, then technical

· CLI-first (`curl -sSfL install.catnip.sh | sh`; `catnip run`) + SSH + Remote-SSH (Cursor/VS Code)
· Container/devcontainer/Codespaces vocabulary; Docker-in-Docker; Go backend + React/TS frontend
· Built around Claude Code; 'run many agents in parallel'; LLM-app dev (FastAPI/Jupyter/vector DBs)

01 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

Container working filesystem + your mounted host git repo; agent edits auto-committed to git refs (refs/catnip/$NAME) and synced to named branches. Persistence is tied to the host / Codespace lifecycle — there is no managed persistent-volume primitive.

Snapshots / forks

Resources & limits

Storage

Per-workspace git worktrees inside the container; mounts the host git repo (changes round-trip via refs/catnip/$NAME → named branches, fetchable with `git fetch catnip`); a built-in git server (http clone, e.g. `git clone -o catnip http://localhost:6369/repo.git`).

Limits & quotas

Bounded by the host machine / Codespace resources; language versions set at boot via CATNIP_*_VERSION; single-operator (your own instance), no multi-tenant quotas.

GPU

Access

Deploy interface

cliweb-uimobile-appsshdevcontainer

SDK languages

None

Network & secrets

Egress controls

Secrets

Bring your own cloud

Placement & use

Jurisdiction

Advertised workloads

Parallel AI coding agentsClaude code sessionsContainerized dev environmentsLLM app developmentRemote mobile coding

02 Capabilities 7 pass · 4 partial · 21 fail · 50 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 0/7

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Partially supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not assessed

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not assessed

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Not supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not applicable

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Partially supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not supported

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not assessed

Networking & delivery 1/3

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not applicable

Built-in reverse proxyPlatform routes external traffic to workload services.

Supported

Custom domainsBring-your-own domain via CNAME/DNS.

Not applicable

Public preview URLsShareable per-deploy / per-branch URLs.

Partially supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not applicable

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Not supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not assessed

Email send / receiveSend and/or receive email from the workload.

Not applicable

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 4/8

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Not supported

SSH accessDirect SSH into workloads.

Supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Partially supported

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Not supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not assessed

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 1/8

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Not supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Not supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not applicable

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not assessed

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not assessed

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not assessed

Data 0/1

First-party databasePlatform-provided managed database.

Not supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not applicable

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 0/3

Scheduled tasksCron / scheduled job primitive.

Not supported

Durable workflowsDurable execution / long-running workflow primitive.

Not applicable

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not supported

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Not supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not assessed

Organisation & security 1/2

Built-in authPlatform-provided authentication / IAM for workloads.

Not applicable

SSO / SAMLEnterprise single sign-on.

Not applicable

Secrets managementFirst-class secrets storage / injection.

Not supported

TeamsMulti-user team accounts.

Not applicable

SharingShare a running workload/resource via link (optionally gated).

Not applicable

BYOCRuns inside the customer's own cloud account.

Not applicable

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not assessed

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not assessed

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Parallel agent workspaces via git worktrees (spawn many coding-agent sessions in parallel, each in its own worktree)parallel-agent-workspaces
“'Worktree's let you spawn multiple agents in parallel. Catnip keeps everything organized.' — automated git-worktree creation as the parallel-agent primitive.” github.com
Embedded git server in the workspace container (clone over http; fetch agent changes back to the host)embedded-git-server
“'We also run a git server in the container... git clone -o catnip http://localhost:6369/my-sick-repo.git ... run git fetch catnip back on your host to see your changes.'” github.com
Agent-change checkpointing to a dedicated git ref (auto-commit every agent edit for granular review/rollback)agent-change-checkpointing
“'When you start a Claude session in Catnip the system automatically commits changes as Claude makes them' to refs/catnip/$NAME, synced to a named branch. (Conductor has a comparable checkpoint model — a potential 2-product watch.)” github.com

03 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

4/10

1 full · 3 partial · 40% of applicable checks

llms.txt
Not supported
“catnip.run/llms.txt returns the SPA app shell (633 bytes, identical across all well-known paths) — no real llms.txt.”
llms-full.txt
Not supported
“No /llms-full.txt (same SPA shell).”
robots.txt AI policy
Partially supported
“catnip.run/robots.txt (Cloudflare-managed) is default-allow (Allow: / for *) and does NOT block major AI-assistant UAs (GPTBot/ClaudeBot/PerplexityBot), but it blocks some scraper bots (Amazonbot/Bytespider/Applebot-Extended) and sets Content-Signal ai-train=no — default-allow with a no-train signal, not an explicit AI allow.”
JSON-LD
Not supported
“No application/ld+json on the catnip.run SPA shell.”
Sitemap
Not supported
“catnip.run/sitemap.xml returns the SPA shell (not a real sitemap); robots.txt declares no Sitemap:.”
Meta tags
Partially supported
“The SPA shell has <title>Catnip</title> + PWA meta (theme-color, apple-itunes-app, manifest, favicon) but no meta description / OG — present but thin.”
Markdown negotiation
Not supported
“catnip.run serves the SPA; rich markdown (README, docs/*.md) lives on GitHub only, not via content negotiation on the web surface.”
Content efficiency
Not supported
“catnip.run is a 633-byte JS SPA shell (an empty #root + script tags) → ~0% readable text in the raw HTML (<1%).”
Docs discoverable
Partially supported
“Docs are first-class in the GitHub repo (README self-host guide + docs/ architecture + OpenAPI spec), but the catnip.run web landing is a login bridge with no docs link.”
Machine-readable pricing
Not applicable
“oss-tool — free under Apache-2.0, no hosted pricing surface.”
No anti-bot wall
Supported
“catnip.run GET 200 with a normal UA — no challenge on public content (Cloudflare-fronted but no bot challenge).”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

5/8

3 full · 2 partial · 63% of applicable checks

Public API
Supported
“Documented HTTP API on the Go container server (OpenAPI/Swagger spec in container/docs/), machine-usable once Catnip is running.”
OpenAPI spec
Supported
“container/docs/swagger.json + swagger.yaml — a real OpenAPI/Swagger spec, served by the container.”
MCP server
Not supported
“No MCP server (empty `mcp` grep over the repo tree).”
SDK packages
Not supported
“No official client SDK package.”
Auth documented
Not applicable
“Localhost API (no remote API to authenticate to); the catnip.run GitHub-OAuth flow is for the mobile bridge, not the run-destination API.”
Self-serve credentials
Not applicable
“No hosted signup for the run-destination — it's self-hosted; nothing to self-serve credentials for.”
Webhooks
Not supported
“No documented webhooks.”
CLI tool
Supported
“The `catnip` CLI is official and central (install.catnip.sh → `catnip run`).”
Error model
Partially supported
“The OpenAPI/Swagger spec defines API response schemas; no separately-documented JSON error model in prose.”
Rate limits documented
Not applicable
“Local/self-hosted API — no hosted rate limits.”
Agent config files
Partially supported
“AGENTS.md + CLAUDE.md present at the repo root (one surface) — but contributor-facing (for agents working ON Catnip), not a user-integration agent-config surface.”

04 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 1

Claude Code Anthropic
Supported
“'Run Claude Code Everywhere'; 'Currently optimized for Claude Code'. Catnip is purpose-built to host and orchestrate Claude Code sessions (terminal, web, mobile, SSH).”
Source github.com

Plausible compatibility 14

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

Aider
Amp
Antigravity
Codex CLI
Devin
Droid
Gemini CLI
Goose
Hermes Agent
Kilo Code
Kiro CLI
OpenCode
Pi
Qwen Code

05 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 0

No attestations found on the public surface. Empty means nothing is advertised, after checking, not that nothing was checked.

Regions —

No region list captured.

Legal

Privacy notice Terms of service

06 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: Go
Stars: 485
Forks: 39
Created: 9 Jul 2025
Archived: No

Activity

Last commit: 20 May 2026
Latest release: v0.12.1 · 8 Jan 2026
Issues open / closed: 5 / 5 · 50% closed

Frequent 0.x releases through late 2025 (v0.11.2 Oct → v0.11.3 Nov → v0.11.4 Dec 2025 → v0.12.0/.1 Jan 2026, plus dev pre-releases). GitHub RELEASES have PAUSED since v0.12.1 (2026-01-08), even though commits continue (pushedAt 2026-05-20) — development active, release tagging dormant. Observation, not a graded velocity.

Fetched via gh on 7 Jun 2026.

Self-hosting

Methods: binarydockerother
You operate: docker

Apache-2.0; self-host is the ONLY mode (no hosted tier). Three ways: (1) LOCAL — `curl -sSfL install.catnip.sh | sh` then `catnip run` (a Go binary with an embedded Vite SPA; on `catnip run` it boots a 'universal' container — inspired by openai/codex-universal — pre-installed with node/python/go/gcc/rust, language versions overridable via CATNIP_*_VERSION env); (2) GITHUB CODESPACES / devcontainers — add the `ghcr.io/wandb/catnip/feature:1` devcontainer feature to `.devcontainer/devcontainer.json` and forward port 6369 (the recommended/cloud path); (3) the wandb/catnip CONTAINER image (Docker Hub + ghcr). REQUIRES a container runtime on the host: Docker, or Apple's Container SDK on macOS. catnip.run is NOT a hosted run-destination — it is a mobile bridge (GitHub OAuth → starts/redirects to YOUR OWN codespace). Cost = free under Apache-2.0 + your own machine, or GitHub-billed Codespaces compute (not billed by catnip).

Documentation signals 7/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Not supportedllms.txt
SupportedExamples
SupportedArchitecture doc

07 Company & presence Facts only, not scored

Company

Headquarters: San Francisco, California, USA
Founded: 2017 (Weights & Biases); Catnip repo created 2025-07-09
Team size: W&B: large (hundreds, now part of CoreWeave); Catnip is a small W&B team project
Hiring: Weights & Biases / CoreWeave hire globally

Notable people

Weights & Biases engineering
CoreWeave (parent)

Activity

Last release: v0.12.1 (2026-01-08); GitHub releases paused since, while commits continue (pushedAt 2026-05-20) github.com
Last blog post: —

Presence 5

Links found on the public surface scanned; not an exhaustive search.

08 Sources & method How this entry was produced

Public surface only

Everything here was read from catnip.run's unauthenticated pages, docs, pricing and repository on 7 Jun 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v10). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v10
Keys tracked today: 61
Assessed on this entry: 50

Something wrong on this page?

Nearby in the atlas

All Persistent environment products →