README.md
September 24, 2026 · View on GitHub
Independent open-source project. Not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.
What You Get
- 54 ToS-friendly providers. 1.3B+ free tokens every month. Use free, paid, subscription, and local models from one searchable UI without putting your account at risk. FCC follows provider terms and removes integrations if they stop being allowed.
- 10 coding agents. One model catalog. Run Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, or Aider with your FCC models.
- Keep coding through provider outages. After retries are exhausted, FCC automatically tries your next configured model without making you restart the turn—across every client.
- Up to 90% fewer terminal-output tokens. Optional RTK filters common command output, while five FCC optimizations handle quota probes, command-prefix detection, titles, suggestions, and filepaths without calling a provider.
- Native Code sessions in your browser. Choose a folder and run Codex in the browser with real-time and background support. Freely switch providers/models in the same session. Support for switching harnesses in the same session coming soon!
- Terminal, desktop, IDE, or phone. Work through native launchers, VS Code, Codex App, JetBrains, Discord, or Telegram.
- Voice notes in. Code out. Talk to your agent using local Whisper or NVIDIA NIM transcription.
- Agent capabilities stay intact. Stream responses, use tools, preserve native interleaved thinking for maximum performance, send images, and route Fable, Opus, Sonnet, and Haiku independently with compatible models.
Free-tier availability and limits are controlled by each provider and may change.
Claude Code running with FCC.
A native Codex session in FCC's browser UI.
Quick Start
1. Install
macOS/Linux:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh
Windows PowerShell:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1")))
When prompted, choose at least one coding agent and optionally RTK. You can review the installers before running them: install.sh and install.ps1.
2. Start FCC
Windows
Open Free Claude Code from your desktop or Start menu.
macOS
Open Free Claude Code from your desktop or Applications folder.
Linux
Run:
fcc-server
FCC opens the Admin UI after starting. On Windows and macOS, use the tray or
menu-bar icon to open Admin, restart, or quit. When using fcc-server, keep its
terminal open.
3. Configure NVIDIA NIM
- Create an API key at build.nvidia.com/settings/api-keys.
- Open the Admin UI URL from the server log.
- Paste the key into
NVIDIA_NIM_API_KEY. - Leave
MODELon the defaultnvidia_nim/nvidia/nemotron-3-super-120b-a12b, or search the model dropdown and select another model. - Click Apply.
To protect the local proxy with a bearer token, enable Proxy Authentication in Admin.
4. Run Your Coding Agent
Claude Code:
fcc-claude
Codex:
fcc-codex
Pi:
fcc-pi
OpenCode 2:
fcc-opencode
To upgrade from OpenCode 1, rerun the FCC installer with OpenCode selected. It
upgrades the native installation in ~/.opencode/bin; for npm or other package
managers, follow OpenCode's migration instructions
first. For npm v1, run npm uninstall -g opencode-ai, then rerun the FCC installer.
Close OpenCode before upgrading. OpenCode manages its own data upgrades.
RTK integration is temporarily unavailable for OpenCode 2. The installer saves the recognized old RTK plugin outside the plugin directory; customized plugins need manual migration. RTK continues to work with the other supported agents.
Use fcc-opencode for coding and sessions. Use plain opencode for commands
such as upgrades, service management, ACP, and MCP setup.
Cline:
fcc-cline
Hermes:
fcc-hermes
DeepSeek Harness Web:
fcc-dsh
Grok Build:
fcc-grok
Muse Code:
fcc-muse
Aider:
fcc-aider
Select an FCC model from Claude Code's native /model picker.
Choose A Provider
- Open a provider link below for its key, models, or setup instructions.
- In the Admin UI, configure the listed setting. For OpenAI / ChatGPT subscription access, use Providers → OAuth providers instead.
- Search the
MODELdropdown and select a model. If the provider cannot list models, enter<provider-id>/<exact-provider-model-id>manually. - Click Apply.
Optional: add an ordered Fallback Models list under Model Config. It applies to every connected client. A failed request may reach and consume usage from more than one provider before succeeding.
Provider catalog
| Provider | Admin UI setting | Example MODEL |
|---|---|---|
| NVIDIA NIM | NVIDIA_NIM_API_KEY | nvidia_nim/nvidia/nemotron-3-super-120b-a12b |
| OpenRouter | OPENROUTER_API_KEY | open_router/openrouter/free |
| Groq | GROQ_API_KEY | groq/llama-3.3-70b-versatile |
| ClinePass | CLINE_API_KEY | cline_pass/cline-pass/kimi-k3 |
| OpenAI / ChatGPT | Connect ChatGPT in the Admin UI | openai/<model-id> |
| OpenAI API | OPENAI_API_KEY | openai_api/gpt-5.6-sol |
| GitHub Copilot | Connect GitHub Copilot in the Admin UI | github_copilot/<model-id> |
| xAI (Grok) | XAI_API_KEY | xai/grok-4.5 |
| QwenCloud Token Plan | QWENCLOUD_API_KEY | qwencloud/qwen3.7-plus |
| QwenCloud Coding Plan | QWENCLOUD_CODING_API_KEY | qwencloud_coding/qwen3.7-plus |
| Together AI | TOGETHER_API_KEY | together/zai-org/GLM-5.2 |
| DeepInfra | DEEPINFRA_API_KEY | deepinfra/deepseek-ai/DeepSeek-V4-Flash |
| SiliconFlow | SILICONFLOW_API_KEY | siliconflow/Qwen/Qwen3-32B |
| Nebius Token Factory | NEBIUS_API_KEY | nebius/Qwen/Qwen3-30B-A3B |
| Chutes | CHUTES_API_KEY | chutes/Qwen/Qwen3-32B-TEE |
| Featherless AI | FEATHERLESS_API_KEY | featherless/Qwen/Qwen3-32B |
| Agnes AI | AGNES_API_KEY | agnes/agnes-2.0-flash |
| ZenMux | ZENMUX_API_KEY | zenmux/deepseek/deepseek-v4-flash-free |
| W&B Inference | WANDB_API_KEY | wandb/openai/gpt-oss-20b |
| Azure OpenAI | AZURE_OPENAI_API_KEY and AZURE_OPENAI_BASE_URL | azure_openai/<deployment-name> |
| Google AI Studio (Gemini) | GEMINI_API_KEY | gemini/models/gemini-3.1-flash-lite |
| Google Vertex AI | VERTEX_PROJECT_ID + ADC | vertex/google/gemini-3.5-flash |
| DeepSeek | DEEPSEEK_API_KEY | deepseek/deepseek-chat |
| Mistral La Plateforme | MISTRAL_API_KEY | mistral/devstral-small-latest |
| Mistral Codestral | CODESTRAL_API_KEY | mistral_codestral/codestral-latest |
| OpenCode Zen | OPENCODE_API_KEY | opencode_zen/gpt-5.3-codex |
| OpenCode Go | OPENCODE_API_KEY | opencode_go/minimax-m2.7 |
| Vercel AI Gateway | AI_GATEWAY_API_KEY | vercel/openai/gpt-5.5 |
| Amazon Bedrock | AWS_BEARER_TOKEN_BEDROCK | bedrock/openai.gpt-oss-120b |
| Hugging Face Inference Providers | HUGGINGFACE_API_KEY | huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct:fastest |
| Cohere | COHERE_API_KEY | cohere/command-a-plus-05-2026 |
| Wafer | WAFER_API_KEY | wafer/DeepSeek-V4-Pro |
| Kimi API | KIMI_API_KEY | kimi/kimi-k2.5 |
| Kimi Code | KIMI_CODE_API_KEY | kimi_code/k3 |
| MiniMax | MINIMAX_API_KEY | minimax/MiniMax-M3 |
| Cerebras Inference | CEREBRAS_API_KEY | cerebras/gpt-oss-120b |
| SambaNova | SAMBANOVA_API_KEY | sambanova/Meta-Llama-3.3-70B-Instruct |
| Kilo.ai | KILO_API_KEY | kilo/kilo-auto/free |
| Fireworks AI | FIREWORKS_API_KEY | fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct |
| Novita AI | NOVITA_API_KEY | novita/deepseek/deepseek-v4-flash-0731 |
| Cloudflare Workers AI | CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID | cloudflare/@cf/moonshotai/kimi-k2.6 |
| Z.ai Coding Plan | ZAI_API_KEY | zai/glm-5.2 |
| Z.ai API (pay as you go) | ZAI_API_KEY | zai_api/glm-4.7-flash |
| TokenRouter | TOKENROUTER_API_KEY | tokenrouter/moonshotai/kimi-k3-free |
| NaraRoute | NARAROUTE_API_KEY | nararoute/kimi-k3-free |
| Poolside AI | POOLSIDE_API_KEY | poolside/poolside/laguna-s-2.1 |
| LLM7.io | LLM7_API_KEY | llm7/default |
| Scaleway | SCW_SECRET_KEY | scaleway/deepseek/deepseek-v4-flash |
| Lightning AI | LIGHTNING_API_KEY | lightning/lightning-ai/Qwen3.8-27B |
| Experiential Labs | EXPLABS_API_KEY | experiential/union-alpha |
| Ollama Cloud | OLLAMA_API_KEY | ollama_cloud/qwen3-coder:480b |
| LM Studio | LM_STUDIO_BASE_URL | lmstudio/<model-id> |
| llama.cpp | LLAMACPP_BASE_URL | llamacpp/<model-id> |
| Ollama | OLLAMA_BASE_URL | ollama/<model-tag> |
Provider-specific setup
- OpenAI / ChatGPT uses your ChatGPT subscription rather than an API key. Connect from Providers → OAuth providers → OpenAI / ChatGPT → Connect in the Admin UI and finish signing in through your browser. Restart an already-running agent after connecting.
- OpenAI API uses a separate Platform API key. Enter it under Providers → Cloud providers → OpenAI API → Configure. The model list may include IDs that cannot handle coding requests; choose a text-generation model.
- GitHub Copilot uses your signed-in GitHub account and subscription. Install
Copilot CLI 1.0.83
on PATH, then choose Providers → OAuth providers → GitHub Copilot → Connect.
FCC reuses the native profile or shows a GitHub device code when sign-in is needed.
You can also sign in first with
copilot login --device-code. Select a concretegithub_copilot/<model-id>from the discovered list; available models and quotas depend on your subscription and organization policies. Restart an already-running agent after connecting. Disconnect stops FCC use and leaves the native login intact. FCC pins its SDK and CLI compatibility because direct endpoint access is experimental. - Azure OpenAI uses the deployment names from your resource. Set
AZURE_OPENAI_BASE_URLto its complete v1 endpoint, such ashttps://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/, and select a deployment that supports Chat Completions. Enter the deployment name as a custom model slug if it does not appear in the model dropdown. - Mistral Codestral uses a separate key from Mistral La Plateforme.
- Kimi Code subscription keys use
kimi_code/; Kimi API credit keys usekimi/. Kimi Code plans are for personal interactive coding-agent use under Kimi's community guidelines. - QwenCloud Coding Plan keys use
qwencloud_coding/; QwenCloud Token Plan keys useqwencloud/. The keys and endpoints are not interchangeable. Coding Plan is for local, personal, interactive coding-agent use under the Coding Plan terms. - OpenCode Zen and OpenCode Go share
OPENCODE_API_KEYbut use the explicitopencode_zen/andopencode_go/model prefixes. - For Amazon Bedrock, set
BEDROCK_BASE_URLto the URL for the same region as the API key and select one of the listed models. - Vertex AI uses Google Application Default Credentials instead of an API key.
Locally, run
gcloud auth application-default loginonce; service-account files and attached service accounts also work. SetVERTEX_PROJECT_ID, and optionally changeVERTEX_LOCATIONfrom itsglobaldefault. - Cloudflare requires both its API token and account ID.
- For Ollama Cloud, use the exact model IDs shown in the model picker. Local
Ollama uses the separate
ollama/prefix. - Prefer tool-capable models for coding agents. Local models also need enough context for the agent's system prompt and tool definitions.
Local provider setup
LM Studio
Start LM Studio's local server, load a tool-capable model, and use the model identifier shown by LM Studio with the lmstudio/ prefix. The default URL is http://localhost:1234/v1.
llama.cpp
Start llama-server with its OpenAI-compatible Chat Completions API and enough context for the model. Use the local model ID with the llamacpp/ prefix. LLAMACPP_BASE_URL defaults to http://localhost:8080/v1; FCC accepts either the server root or an explicit /v1 suffix.
Ollama
ollama pull llama3.1
ollama serve
Use the tag shown by ollama list with the ollama/ prefix. OLLAMA_BASE_URL defaults to http://localhost:11434; FCC accepts either the root URL or an explicit /v1 suffix.
Optional model-tier routing
MODEL is the fallback for every request. Select a model for MODEL_FABLE, MODEL_OPUS, MODEL_SONNET, or MODEL_HAIKU to override an individual Claude Code tier; select None to use MODEL.
For example, route Opus to nvidia_nim/nvidia/nemotron-3-super-120b-a12b, Sonnet to open_router/openrouter/free, Haiku to lmstudio/qwen3.5-coder, and keep MODEL on zai/glm-5.2.
Reasoning control
Open Admin UI → Model Config → Reasoning and select the behavior you want.
| Selection | Behavior |
|---|---|
| From client (default) | Use the effort sent by Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, or Aider. If none is sent, keep the provider default. |
| Off | Request reasoning to be disabled. |
| Low, Medium, High, X-High, or Max | Override the client with the selected reasoning level. |
| Inherit (Fable, Opus, Sonnet, and Haiku only) | Use the root Reasoning selection. |
Providers that do not support a selected control retain their own behavior.
Connect Your Client
For terminal use, start fcc-server, then run fcc-claude, fcc-codex,
fcc-pi, fcc-opencode, fcc-cline, fcc-hermes, fcc-dsh, fcc-grok,
fcc-muse, or fcc-aider.
For editor and app integrations, install the client, start FCC, then open Admin UI → Integrations and click Connect on its card.
- Claude Code in VS Code — install the Claude Code extension.
- Claude Desktop — install Claude Desktop. Fully quit it before connecting or disconnecting, then reopen it. Disconnect returns to normal Claude sign-in.
- Codex in VS Code and App — install the Codex extension or Codex App.
- Claude Code in JetBrains ACP — install Claude Agent in JetBrains AI Assistant and start it once, then click Connect in FCC. Reopen the IDE, select Claude Code (FCC), and start a new chat. After JetBrains updates the agent, restart FCC before starting a new chat. Requires a local IDE in its standard installation locations.
Reload VS Code or restart the app/IDE after connecting. In Codex and Claude Desktop, select an FCC model from the model picker. FCC keeps connected integrations up to date when it starts; reload or restart the client when FCC reports updated settings. Use Disconnect on the same card to remove the integration.
Run FCC on the same computer and in the same user environment as the client you are configuring.
Optional Integrations
Configure integrations from Admin UI → Messaging, then click Apply.
Discord bot
- Create a bot in the Discord Developer Portal.
- Enable Message Content Intent and invite it with read, send,
message-history, and Manage Messages permissions so
/clearcan remove user prompts. - Set Messaging Platform to discord.
- Enter Discord Bot Token, Allowed Discord Channels, and an absolute Allowed Directory.
- Apply the settings and restart the server if requested.
Telegram bot
- Create a bot with @BotFather.
- Get your numeric user ID from @userinfobot. In groups, grant the bot permission to delete messages.
- Set Messaging Platform to telegram.
- Enter Telegram Bot Token, Allowed Telegram User ID, and an absolute Allowed Directory.
- Apply the settings and restart the server if requested.
Messaging commands
| Usage | Behavior |
|---|---|
/stats | Show session state. |
Standalone /stop | Cancel all work. |
Reply with /stop | Cancel only the selected request while other queued requests continue. |
Standalone /clear | Reset all FCC state and remove every tracked message in that chat, including user prompts, voice notes, FCC replies, Telegram's online notice, and the clear command itself. |
Reply with /clear | Delete the selected message and its literal platform reply subtree while preserving its ancestors and siblings. |
Voice notes
Re-run the installer with the command for your voice backend.
macOS/Linux:
NVIDIA NIM transcription:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-nim
Local Whisper on CPU or CUDA:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-local
Both backends:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-all
Local Whisper with CUDA 13.0:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-local --torch-backend cu130
Windows PowerShell:
NVIDIA NIM transcription:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceNim
Local Whisper on CPU or CUDA:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocal
Both backends:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceAll
Local Whisper with CUDA 13.0:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocal -TorchBackend cu130
Restart fcc-server. In Admin UI → Messaging → Voice, enable voice notes, select cpu, cuda, or nvidia_nim, and choose the Whisper model. Local gated models need HUGGINGFACE_API_KEY; NVIDIA NIM transcription needs NVIDIA_NIM_API_KEY.
Manage Your Installation
Run fcc-server --version to check the installed version without starting FCC.
Update
Stop all running FCC commands, then run:
fcc-update
This runs the same installer as above, including its coding-agent prompts and checks. If you use voice support, pass the same voice options used during installation.
If your installation does not have fcc-update yet, run the installer once to add it.
Muse Code on native Windows
Rerunning FCC's Windows installer with Muse Code selected installs or updates FCC's managed Muse executable. To install or update only Muse Code:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install-muse.ps1")))
To remove only that managed Muse executable while preserving Muse data and other installations:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall-muse.ps1")))
FCC's ordinary uninstaller below continues to leave Muse Code installed.
Uninstall
Stop every running FCC command before uninstalling.
Removes
- Free Claude Code, including its desktop launcher and commands
~/.fcc/
Keeps
- uv and Python
- Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider, and RTK
- Shared PATH entries
macOS/Linux:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall.sh" | sh
Windows PowerShell:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall.ps1")))
Project Links
License
MIT License. See LICENSE for details.