OpenClaude is an open-source coding-agent CLI for cloud and local model providers.
Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat, and other supported backends while keeping one terminal-first workflow: prompts, tools, agents, MCP, slash commands, and streaming output.
One CLI across cloud APIs and local model backends — no per-provider tooling
Guided provider setup and saved profiles with /provider
Coding-agent workflows in one place: bash, file tools, grep, glob, agents, tasks, MCP, and web tools
A bundled VS Code extension for launch integration and theme support
A pixel-art hero companion who fires an arrow every time you press Enter (really — see Meet your buddy)
Quick Start
Install
OpenClaude requires Node.js >=22.0.0 for npm installs and runtime. Bun is
only needed for source builds and local development.
npm install -g @twigpine/openclaude@latest
Upgrading from @gitlawb/openclaude? The package moved to the @twigpine
scope and the old one is no longer updated. Both packages provide the
openclaude command, so npm refuses to install one over the other — remove
the old one first:
Your settings and sessions (~/.openclaude and ~/.openclaude.json) are not
touched. Don't use --force to install over the old package instead: a later
uninstall of the old one would then remove the openclaude command. If that
happens, uninstall @twigpine/openclaude and install it again.
If you're on Arch Linux, you can install OpenClaude from the community-maintained AUR package:
paru -S openclaude
If the install later reports ripgrep not found, install ripgrep system-wide and confirm rg --version works in the same terminal before starting OpenClaude.
run /provider for guided provider setup and saved profiles
run /onboard-github for GitHub Models onboarding
run /search to choose the web search backend (Exa by default) or add a search API key
Note: OpenClaude does not automatically load project .env files. We recommend using the /provider command for setup, which saves provider profiles and credentials in .openclaude-profile.json. If you prefer environment variables, export them explicitly or run openclaude --provider-env-file .env for provider/setup variables. Export runtime/debug knobs from your shell or launcher.
Resume or fork a conversation
Resume an existing conversation by session ID, or continue the most recent
conversation in the current directory:
Forking is conversation branching only. It does not create filesystem isolation,
copy your working tree, or create a git worktree branch.
Manage saved conversations
Run /sessions inside OpenClaude to list this project's saved conversations.
Press Enter on one to Resume, Delete (asks for confirmation, defaulting
to Cancel), or go Back to the list. As a shortcut, press d on a row and
then d again to delete it; any other key in between cancels. Deleting removes
the transcript and its sidecar files from disk and cannot be undone. The
session you are currently in is not listed and cannot be deleted.
Background sessions
Run long non-interactive prompts detached from the current terminal:
Background sessions are local child processes. OpenClaude does not start a daemon
or network service, and permission/provider/model/settings flags are passed to
the child process the same way they are for a foreground --print run. Session
metadata and logs are stored under the resolved OpenClaude config directory,
usually ~/.openclaude/bg-sessions/; OPENCLAUDE_CONFIG_DIR can point
OpenClaude somewhere else. CLAUDE_CONFIG_DIR is ignored for OpenClaude
background-session storage. Session names can be reused after older sessions
reach a terminal state; use the session ID to inspect older logs with the same
name. A naturally finished session is recorded as exited when its process
returns zero and failed when it returns nonzero or handles a termination
signal. stale remains the conservative result when the process disappears
without an observed outcome; an explicit successful openclaude kill is
recorded as killed, and killed takes precedence over a natural exited or
failed outcome for the same process. Terminal outcomes are stored separately
under bg-sessions/terminal/; deleting that directory makes finished sessions
fall back to liveness-derived status. OpenClaude does not infer POSIX signal
names on Windows.
Unobservable force termination, host crashes, and power loss remain stale on
every platform.
openclaude attach currently reports the matching session and
points to openclaude logs -f; full terminal reattach is not implemented
for local background sessions yet.
OpenClaude config cutover
OpenClaude stores its own config under ~/.openclaude and ~/.openclaude.json
by default. It does not read ~/.claude, project .claude/ directories, or
CLAUDE_CONFIG_DIR; new users can start with an empty OpenClaude config and do
not need Claude Code installed.
If you previously used OpenClaude with .claude paths, migrate intentionally:
copy only the settings, commands, agents, skills, scheduled tasks, or other files
you personally created for OpenClaude into the matching .openclaude location.
Do not blanket-copy .claude, and do not copy Claude Code credentials or auth
files. For provider authentication, prefer running OpenClaude's provider setup
again or exporting provider-specific environment variables.
For Ollama, OpenClaude uses Ollama's native chat API and requests a 32768-token
context window on each chat request so same-session history is not silently
truncated by Ollama's OpenAI-compatible shim. Set OPENCLAUDE_OLLAMA_NUM_CTX
or OLLAMA_CONTEXT_LENGTH if you need a different request-level context size.
See Advanced Setup for
verification with ollama ps.
Uses https://api.aimlapi.com/v1, auto-detects the OpenAI-compatible route from AIMLAPI_API_KEY, sends OpenClaude attribution headers, and discovers chat-capable models from the public /models catalog
Concentrate
/provider or CONCENTRATE_API_KEY
Unified OpenAI-compatible gateway at https://api.concentrate.ai/v1; defaults to deepseek-v4-flash and auto-discovers the chat model catalog
LLMTR
/provider or OpenAI-compatible env vars
Multi-model gateway at https://llmtr.com/v1; /provider and --provider llmtr default to deepseek/deepseek-v4-flash, while raw env setup must set OPENAI_BASE_URL=https://llmtr.com/v1 and OPENAI_MODEL; accepts LLMTR_API_KEY or OPENAI_API_KEY after the route is selected and discovers tool-capable Chat Completions models from the public catalog
Command Code
/provider or OpenAI-compatible env vars
Hybrid OpenAI-compatible gateway at https://api.commandcode.ai/provider/v1; /provider and --provider commandcode default to deepseek/deepseek-v4-flash, while raw env setup must set OPENAI_BASE_URL=https://api.commandcode.ai/provider/v1 and OPENAI_MODEL; requires CMD_API_KEY, COMMANDCODE_API_KEY, or the official COMMAND_CODE_API_KEY after the route is selected and discovers Chat Completions models from the public catalog. Claude models are unsupported by this Chat Completions integration
ApiSmart
/provider or APISMART_API_KEY
Uses https://gw.apismart.ai/v1, defaults to DEEPSEEK_V4_FLASH, and supports optional APISMART_MODEL plus authenticated model discovery
API Route
/provider or API_ROUTE_API_KEY
Uses https://global.api-route.com/v1, defaults to claude-sonnet-4-6, and supports optional API_ROUTE_MODEL plus authenticated model discovery
GMI Cloud
/provider, --provider gmi-cloud, or env vars
Uses GMI_API_KEY at https://api.gmi-serving.com/v1 and defaults to Qwen/Qwen3.8-Max; --provider gmi-cloud also reads an optional GMI_MODEL, and the model list comes from authenticated discovery
Hicap
/provider or OpenAI-compatible env vars
Uses api-key auth, discovers models from unauthenticated /models, and supports Responses mode for gpt- models
Fireworks AI
/provider or env vars
First-class provider with 276 curated models (DeepSeek, Qwen, Llama, Gemma, and more); uses FIREWORKS_API_KEY
LongCat
/provider or env vars
Meituan LongCat OpenAI-compatible API at https://api.longcat.chat/openai/v1; uses LONGCAT_API_KEY and defaults to LongCat-2.0
ClinePass
/provider or env vars
AI model gateway with usage limits (5hr, weekly, monthly); uses CLINE_API_KEY at https://api.cline.bot/api/v1
Gemini
/provider or env vars
Supports API key only
GitHub Models
/onboard-github
Interactive onboarding with saved credentials
Codex OAuth
/provider
Opens ChatGPT sign-in in your browser and stores Codex credentials securely
Smart gateway at https://opengateway.gitlawb.com/v1; requires an API key from https://gitlawb.com/opengateway/keys and routes Xiaomi MiMo and other partner models by OPENAI_MODEL
OpenCode Zen
/provider or env vars
Pay-as-you-go AI gateway (48 models); uses OPENCODE_API_KEY via https://opencode.ai/zen/v1; shared key with OpenCode Go
OpenCode Go
/provider or env vars
$10/mo subscription for open models (13 models); uses OPENCODE_API_KEY via https://opencode.ai/zen/go/v1; shared key with OpenCode Zen
Xiaomi MiMo
/provider or env vars
OpenAI-compatible API at https://mimo.mi.com; uses MIMO_API_KEY and defaults to mimo-v2.5-pro
NEAR AI
/provider or env vars
Unified gateway (Claude, GPT, Gemini + TEE open models); uses NEARAI_API_KEY at https://cloud-api.near.ai/v1
Cloudflare Workers AI
/provider or env vars
OpenAI-compatible API at https://api.cloudflare.com/client/v4/accounts//ai/v1; uses CLOUDFLARE_API_TOKEN. Replace `` with your Cloudflare account id.
Ollama
/provider or env vars
Local inference with no API key
Atomic Chat
/provider, env vars, or bun run dev:atomic-chat
Local Model Provider; auto-detects loaded models
Bedrock / Vertex / Foundry
env vars
Anthropic-family cloud routes; Vertex is for Claude on Vertex AI, not arbitrary Model Garden models
Streaming responses: Real-time token output and tool progress
Tool calling: Multi-step tool loops with model calls, tool execution, and follow-up responses
Images: URL and base64 image inputs for providers that support vision. Paste from the clipboard with Ctrl+V (Alt+V on Windows). 1080p/4K screenshots still attach. If processing fails and the image is over the 5MB payload limit or the 8000px API edge, the prompt shows that error instead of "No image found". For Anthropic requests containing more than 20 images (including retained conversation history and tool results), local images must fit within 2000×2000 pixels. On Amazon Bedrock and Google Cloud Vertex AI, document blocks also count toward that 20-block threshold. OpenClaude attempts to resize them before sending; if processing cannot produce a compliant image, it reports an actionable error rather than silently dropping attachments. Resize the affected images or start a new conversation with fewer images (or documents on those partners).
Provider profiles: Guided setup plus saved user-level provider profile support
Local and remote model backends: Cloud APIs, local servers, and Apple Silicon local inference
Codebase intelligence (repo map): Structural map of the repository ranked by PageRank importance, auto-injected into context when the REPO_MAP flag is enabled or the REPO_MAP environment variable is set. Inspect with /repomap (2048-token default). See docs/repo-map.md for details.
A companion with signature moves: A truecolor pixel-art hero who lives beside your prompt and reacts when you work. See below.
Meet Your Buddy
Run /buddy to hatch a companion — a truecolor pixel-art hero who stands
beside your prompt, idles, blinks, and fires their signature move every time
you submit a message:
/buddy hatch (first run) or pet your companion
/buddy set robinhood the green archer — arrow shot on every Enter
/buddy set kaio gold-haired warrior — charges a full-width energy wave
/buddy set strawhat stretchy punch that snaps back
/buddy set merlin twinkling sparkle stream
/buddy set kage spinning shuriken
/buddy set ember dragon fire with a real heat gradient
/buddy set corsair cannonball with smoke trail
/buddy name Robin rename your companion
/buddy set random back to your rolled hero
Companions respect prefersReducedMotion, degrade gracefully to line art in
low-color terminals, and can be silenced with /buddy mute. Requires a
terminal at least 100 columns wide for the full sprite.
Provider Notes
OpenClaude supports multiple providers, but behavior is not identical across all of them.
Anthropic-specific features may not exist on other providers
Tool quality depends heavily on the selected model
Smaller local models can struggle with long multi-step tool flows
Some providers impose lower output caps than the CLI defaults, and OpenClaude adapts where possible
AI/ML API uses the OpenAI-compatible route, defaults to gpt-4o, and only surfaces chat-capable models from its public catalog
Twigpine Opengateway is the fresh-install startup default and requires an API key from https://gitlawb.com/opengateway/keys. It uses one OpenAI-compatible base URL; switch between mimo-* and google/gemini-3.1-flash-lite-preview with /model, and do not pin the base URL to /v1/xiaomi-mimo.
Z.AI GLM Coding Plan uses https://api.z.ai/api/coding/paas/v4 with glm-5.2 by default. On that direct route, GLM-5.3-Flash is selectable as glm-5.3-flash and accepts image input. Its OpenClaude effort choices are low, high, and xhigh, with xhigh requesting Z.AI max; GLM-5.3 and the existing GLM-5.2 query controls remain supported. These capabilities are not claimed for gateways that happen to carry the same model name.
Xiaomi MiMo uses api-key header auth on the direct OpenAI-compatible route and currently does not support /usage reporting in OpenClaude
GitHub Copilot serializes sub-agent execution by default to reduce Premium Request consumption — see Agent Routing and Step Limits for tuning
For best results, use models with strong tool/function calling support.
Agents
Route different agents to different models (cost optimization, splitting work
by model strength), cap sub-agent tool steps with maxSteps, and tune GitHub
Copilot sub-agent behavior. Configured via settings, agent frontmatter, and
environment variables:
per-agent provider/model overrides via agentModels + agentRouting in ~/.openclaude/settings.json
model-only routes that reuse your current provider's credentials
built-in agents (Explore and Plan [feature-gated], verification [feature-gated: requires VERIFICATION_AGENT + tengu_hive_evidence], code-reviewer [requires diff inline]) routable by type name
Exa is the default web search backend. With no setup, WebSearch on non-Anthropic models uses Exa's keyless free tier, which has per-second and daily limits. Run /search to pick a backend, add an API key, or test search:
/search # pick a backend
/search key exa # add an Exa API key (hidden input) for higher limits
/search remove-key # remove a saved Exa key
/search status # show which backend handles searches
/search test # run a test search
/search anysearch # select AnySearch (works without a key)
/search key anysearch # optionally add an AnySearch API key in the hidden input
Other backends in the auto chain that you configure with a key (Tavily, Brave, Firecrawl, …) run before the Exa free tier, and DuckDuckGo is the last-resort fallback. When the active provider is Ollama, OpenClaude uses the signed-in local Ollama Web Search endpoint ahead of the free tier. Set OLLAMA_API_KEY to enable the hosted Ollama endpoint as a fallback. Set EXA_FREE_TIER=0 if searches should never go to Exa without a key. See Web Search Providers for every backend and option.
AnySearch is available as an explicit backend with /search anysearch or WEB_SEARCH_PROVIDER=anysearch. ANYSEARCH_API_KEY is optional; anonymous access has lower service limits. Set ANYSEARCH_MAX_RESULTS to an integer from 1 to 10 (default 10) to control the requested result count. AnySearch does not change the auto search order.
Note: DuckDuckGo fallback works by scraping search results and may be rate-limited, blocked, or subject to DuckDuckGo's Terms of Service.
For Anthropic-native backends and Codex responses, OpenClaude keeps the native provider web search behavior unless you pick a specific backend with /search (for example /search exa).
To select Ollama search explicitly, use WEB_SEARCH_PROVIDER=ollama. A local Ollama route uses its configured OPENAI_BASE_URL or OLLAMA_BASE_URL; hosted search sends OLLAMA_API_KEY only to https://ollama.com/api/web_search.
WebFetch works, but its basic HTTP plus HTML-to-markdown path can still fail on JavaScript-rendered sites or sites that block plain HTTP requests.
Set a Firecrawl API key if you want Firecrawl-powered search/fetch behavior:
export FIRECRAWL_API_KEY=your-key-here
With Firecrawl enabled:
WebSearch can use Firecrawl's search API while the Exa free tier remains the default free path for non-Claude models
WebFetch uses Firecrawl's scrape endpoint instead of raw HTTP, handling JS-rendered pages correctly
Free tier at firecrawl.dev includes 500 credits. The key is optional.
Headless gRPC Server
OpenClaude can run as a headless gRPC service with bidirectional streaming —
integrate its agentic capabilities into other applications, CI/CD pipelines,
or custom UIs. Start it with npm run dev:grpc; a test CLI client ships with
the repo. See Headless gRPC Server for configuration
and client generation from src/proto/openclaude.proto.
Development
Use Node.js >=22.0.0 and Bun 1.3.13 or newer for source builds.
bun install
bun run build
node dist/cli.mjs
Day-to-day commands:
bun run dev — build and launch from source
bun test — full unit suite (Bun's built-in runner)
bun test path/to/file.test.ts — focused runs for the areas you touch
bun run test:coverage — coverage to coverage/lcov.info plus a visual report at coverage/index.html (bun run test:coverage:ui rebuilds just the UI)
bun run smoke — smoke checks
bun run doctor:runtime, bun run verify:privacy; for PR intent scanning, use the fresh-upstream, explicit-ref workflow in the local pre-push validation contract
Focused suites: bun run test:provider, bun run test:provider-recommendation.
To benchmark the launcher module compile cache, build the CLI and run:
bun run build
bun run benchmark:startup
The benchmark requires Node >=22.8.0, where the compile-cache API was added;
the built OpenClaude launcher continues to support the declared Node >=22.0.0
runtime range.
The benchmark defaults to 30 separate-process warm runs and 10 isolated
empty-cache runs. It reports the median, IQR, MAD, first cache-populating run,
first warm-up, Node/OS/CPU details, bundle size, and commit. Direct bundle
timings are included only as a secondary diagnostic; the full launcher result
is the decision signal. Use
bun run benchmark:startup -- --warm-runs 40 --cold-runs 10 to request a
larger sample set. The benchmark records results without enforcing a timing
threshold in CI.
OpenClaude leaves Node's standard compile-cache controls authoritative. Set
NODE_DISABLE_COMPILE_CACHE=1 to disable the optimization, including for V8
coverage runs that require uncached compilation.
Before opening or updating a PR, run the authoritative local pre-push validation contract. The commands below are useful for narrow iteration, but they do not replace that required preflight:
bun run build
bun run smoke
bun run test:coverage when your change affects shared runtime or provider logic
focused bun test ... runs for the files and flows you changed
Repository Structure
src/ - core CLI/runtime
scripts/ - build, verification, and maintenance scripts
docs/ - setup, contributor, and project documentation
vscode-extension/openclaude-vscode/ - VS Code extension
.github/ - repo automation, templates, and CI configuration
bin/ - CLI launcher entrypoints
VS Code Extension
The repo includes a VS Code extension in vscode-extension/openclaude-vscode for OpenClaude launch integration, provider-aware Control Center, in-editor chat, theme support, and optional Microsoft Foundry / Azure OpenAI configuration (endpoint, API version, deployment, API key via Secret Storage) injected into launched terminals. See that folder's README.
Security
If you believe you found a security issue, see SECURITY.md.
Contributions are welcome. For larger changes, open an issue first so the
scope is clear before implementation. See Development for the
build, test, and pre-PR validation commands.
Disclaimer
OpenClaude is an independent community project and is not affiliated with, endorsed by, or sponsored by Anthropic.
OpenClaude originated from the Claude Code codebase and has since been substantially modified to support multiple providers and open use. "Claude" and "Claude Code" are trademarks of Anthropic PBC. See LICENSE for details.
License
MIT for OpenClaude contributors' modifications; the derived Claude Code remains Anthropic's. See more.
