Loading repository data…
psyb0t / repository
Claude Code in Docker. Drop-in OpenAI-compatible API, MCP server, Telegram bot, and CLI — five interfaces, one image. Persistent sessions, file ops, always-on skill injection, and a full dev toolchain (Go, Python, Node, K8s, Terraform, databases) or a minimal image with just the basics.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A runtime harness for Claude Code — the agentic coding CLI from Anthropic — running in a fully isolated Docker container with every dev tool pre-installed, passwordless sudo, docker-in-docker support, and --permission-mode bypassPermissions enabled by default.
v2.0.0 — rebased on
psyb0t/aicodebox. claudebox is now a thin child image of the shared aicodebox base (same pattern aspsyb0t/pibox). Every mode surface (API / Telegram / Cron / MCP) is inherited from the base and stays in lockstep with future base fixes. SeeCHANGELOG.mdfor the full migration guide (endpoint shape changes, env-var namespace, path renames — all mitigated by aliases + symlinks so existing configs keep working).
Runtime hardening (recommended docker run flags):
--cap-drop=ALL --cap-add=NET_BIND_SERVICE — drop every Linux capability, add back only bind-below-1024 if you actually need it.--security-opt no-new-privileges:true — block setuid privilege escalation inside the container.--memory=2g --cpus=2 --pids-limit=512 — cap runtime resource use so a runaway process can't starve the host.--read-only --tmpfs /tmp:rw,noexec,nosuid (only if you don't use /workspace for writes — otherwise skip).
The container drops from root to aicode (UID 1000) at boot via setpriv in the base entrypoint, so the process running your code is never root even without --user.claudebox wraps Claude Code with several distinct interfaces:
claude command, with persistent containers and automatic session resumption across runsSelected from shared topics, language and repository description—not editorial ratings.
yotsuda /
The universal MCP server for Claude Code and other MCP-compatible clients. One installation gives AI access to 10,000+ PowerShell modules and any CLI tool. You and AI collaborate in the same console with full transparency. Supports Windows, Linux, and macOS.
81/100 healthPythoughts-labs /
Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, root-cause debugger, and code generator, all in one shell-native loop.
69/100 healthchat/completions adapter that lets LiteLLM, OpenAI SDKs, and any OpenAI-compatible client talk to Claude Code, complete with streaming SSE, multi-turn conversations, and multimodal image handlingBeyond just running Claude Code in Docker, claudebox adds skill injection (auto-load SKILL.md files into every session), init hooks, custom script directories, structured JSON logging, and a workspace management layer that handles multi-tenant isolation with automatic busy/idle tracking.
Renamed from
docker-claude-code: This project was previously calleddocker-claude-codewith the Docker image atpsyb0t/claude-code. Starting with v1.0.0, it isclaudebox— the Docker image is nowpsyb0t/claudebox, the default binary name isclaudebox, the GitHub repository ispsyb0t/docker-claudebox, and the SSH key directory defaults to~/.ssh/claudebox. If you were using the old names, update your image references, wrapper scripts, and SSH paths accordingly.
Docker installed and running. That's it.
The install script pulls the Docker image, generates SSH keys for git operations inside the container, downloads the wrapper script, and installs it as a command on your system.
# minimal image — default; Claude installs what it needs on the fly
curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-claudebox/master/install.sh | bash
# full image — every dev tool pre-installed (Go, Python, kubectl, terraform, ...)
export CLAUDEBOX_FULL=1 && curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-claudebox/master/install.sh | bash
# custom binary name (e.g. if you want to call it 'claude' instead of 'claudebox')
curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-claudebox/master/install.sh | bash -s -- claude
# or: export CLAUDEBOX_BIN_NAME=claude && curl -fsSL .../install.sh | bash
v2 note: the variant naming flipped in v2.
latestis now the minimal image (was the full image pre-v2);latest-fullis the toolchain-loaded variant (waslatestpre-v2). TheCLAUDEBOX_MINIMAL=1opt-in from v1 is now a no-op — you already get minimal by default. SetCLAUDEBOX_FULL=1to opt into the toolchain image. Installing withCLAUDEBOX_FULL=1(as above) bakes the choice into the installed wrapper, so the full variant sticks for every run — you don't need to keep the env var set afterward.
Heads up on env vars:
VAR=x curl … | bashdoes not setVARfor the install script — bash semantics attach the var tocurlonly. Alwaysexportthe var first (or put it on thebashside of the pipe).
If you prefer not to pipe scripts to bash:
# 1. create the data directory
mkdir -p ~/.claude
# 2. create SSH keys for git operations inside the container
mkdir -p "$HOME/.ssh/claudebox"
ssh-keygen -t ed25519 -C "claude@claude.ai" -f "$HOME/.ssh/claudebox/id_ed25519" -N ""
# then add the public key to GitHub/GitLab/wherever you push code
# 3. pull the image
docker pull psyb0t/claudebox:latest # minimal (default)
# or: docker pull psyb0t/claudebox:latest-full # toolchain-loaded variant
# 4. grab the wrapper script and install it
# see install.sh for exactly how the wrapper is set up
psyb0t/claudebox:latest (minimal, default)The default v2 image. Just enough to run Claude Code on top of the aicodebox base: Ubuntu 24.04, git/curl/wget/jq, Node.js 22 LTS + npm, Python 3.12 + uv, Docker CE. Claude has passwordless sudo, so it will install whatever else it needs on the fly via apt-get, pip, npm, etc. Smaller image, faster pull, first run may take longer while Claude sorts out its own tooling.
curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-claudebox/master/install.sh | bash
Use /aicodebox-init.d/*.sh hooks (see Init Hooks) to pre-install your tools on first container create so Claude doesn't burn tokens figuring out package management.
psyb0t/claudebox:latest-full (toolchain-loaded)Everything pre-installed. Layered on top of the minimal image: Go 1.26, Python 3.12.11 via pyenv, Node.js dev tools, C/C++ toolchain, terraform, kubectl, helm, gh, database clients (sqlite/postgres/mysql/redis), editors (vim/nano/htop/tmux), linters + formatters (flake8/black/isort/pyright/mypy/ruff/eslint/prettier/gofumpt/…). Larger image but Claude wakes up ready.
export CLAUDEBOX_FULL=1 && curl -fsSL https://raw.githubusercontent.com/psyb0t/docker-claudebox/master/install.sh | bash
latest (minimal) | latest-full | |
|---|---|---|
| Ubuntu 24.04 | yes | yes |
| git, curl, wget, jq | yes | yes |
| Node.js LTS + npm | yes | yes |
| Docker CE + Compose | yes | yes |
| Claude Code CLI | yes | yes |
| Go 1.26.1 + tools | yes | - |
| Python 3.12.11 + tools | yes | - |
| Node.js dev tools | yes | - |
| C/C++ tools | yes | - |
| DevOps (terraform, kubectl, helm, gh) | yes | - |
| Database clients | yes | - |
| Shell utilities (ripgrep, bat, etc.) | yes | - |
Languages and runtimes:
DevOps and infrastructure:
gh)Database clients:
psql), mysql-client, redis-tools (redis-cli)Shell and system utilities:
Container automation:
CLAUDE.md in each workspace listing all available tools, so Claude knows what it has access to--update)~/.claude/bin (added to PATH automatically)~/.claude/init.d/*.sh (run once on first container create)~/.claude/.always-skills/ (injected into every invocation)--continue / --no-continue / --resume <session_id>DEBUG=trueYou need either an Anthropic API key or an OAuth token. Set up once, use everywhere:
# interactive OAuth token setup (one-time)
claudebox setup-token
# then use the token for programmatic and headless runs
CLAUDE_CODE_OAUTH_TOKEN=sk-ant-oat01-xxx claudebox "do stuff"
# or use an API key directly
ANTHROPIC_API_KEY=sk-ant-api03-xxx claudebox "do stuff"
claudebox can run in several modes — pick the one that matches how you want to use Claude Code. Each has its own page with full setup, env vars, and examples.
Drop-in replacement for claude. Persistent per-workspace container, automatic session resumption, plus utility commands like claudebox doctor, claudebox mcp list, claudebox stop, and claudebox clear-session.
claudebox
Non-interactive prompt → response for scripts, pipelines, and automation. Plain text, JSON, JSON-verbose (with full tool-call history), and stream-json output formats. Model selection, system prompt overrides, JSON-schema-constrained output, session continuation.
claudebox "explain this codebase" --output-format json --model haiku
Run as a long-lived HTTP server. Full REST API for prompts
amol21p /
MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection
71/100 healthjoinwell52-AI /
FCoP is a minimal protocol that lets multiple AI agents — running in Cursor, Claude Code, plain shells, CI runners — collaborate through ordinary markdown files in a folder. Agents write TASK-*.md when they're starting work, REPORT-*.md when they're done, ISSUE-*.md when they need clarification.
62/100 healthmrcodex-dev /
Most powerful filesystem MCP server for AI agents. Filesystem, shell, Windows internals, reverse engineering, LSP code intelligence, browser automation, and agent orchestration for Claude, Cline, Cursor. Outperforms Claude Code in raw system access.
63/100 healthCR7LXY /
AI Agent Skill security scanner. Detect prompt injection, reverse shells, data exfiltration, supply chain attacks in Claude Code / Codex / Cursor / Gemini CLI skills before you install them. 7-layer engine, 50+ patterns.
55/100 health