Free Claude Code：让 Claude Code、Codex 和 Pi 接入多模型网关

通过 Free Claude Code 代理运行的 Claude Code。

使用本地 FCC Responses 提供商的 Codex CLI。

Claude Code 原生 /model 选择器中的 FCC 网关模型。

Codex 原生 /model 选择器中的生成式 FCC 模型目录。

• 使用 fcc-claude 启动 Claude Code，使用 fcc-codex 启动 Codex，或使用 fcc-pi 启动 Pi。
• 可在 Windows 或 macOS 上通过桌面启动器在后台运行 FCC。
• 可在 Admin UI 中切换 31 个云端和本地提供商。
• 使用各编码 Agent 原生的模型选择器。
• 将 Fable、Opus、Sonnet、Haiku 及回退流量路由至不同模型。
• 在兼容模型之间保留流式输出、工具使用、推理和图像输入能力。
• 在 VS Code 中连接 Claude Code 和 Codex，或通过 JetBrains ACP 使用 Claude Code。
• 可选地通过 Discord 或 Telegram 运行 Claude Code 会话，并支持语音消息转写。
• 通过可选令牌认证保护本地代理。

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")))

如需更新，可随时重新运行相同命令。运行前可查看安装脚本：install.sh 和 install.ps1。

安装程序会询问要安装或验证哪些编码 Agent。至少选择一个；跳过的 Agent 将保持不变。

从桌面或开始菜单打开 Free Claude Code。

从桌面或“应用程序”文件夹打开 Free Claude Code。

运行：

在 Windows 和 macOS 上，FCC 会在系统托盘或菜单栏中运行，无需打开终端。可通过其菜单打开 Admin、检查服务器状态、重启或退出。在 Windows 上，左键单击托盘图标会直接打开 Admin。

若要在不启动服务器的情况下打印已安装的 Free Claude Code 版本，请运行 fcc-server --version。

使用 fcc-server 时，请保持终端窗口打开。默认情况下，服务器健康后会在浏览器中打开 Admin UI。其地址会显示在启动日志中：

INFO:     Admin UI: http://127.0.0.1:8082/admin (local-only)

如果终端显示的端口不是 8082，请使用该端口。

1. 在 build.nvidia.com/settings/api-keys 创建 API 密钥。
2. 从服务器日志中打开 Admin UI URL。
3. 将密钥粘贴到 NVIDIA_NIM_API_KEY。
4. 将 MODEL 保持为默认的 nvidia_nim/nvidia/nemotron-3-super-120b-a12b，或搜索模型下拉列表并选择其他模型。
5. 点击 Validate，然后点击 Apply。

Claude Code：

Codex：

Pi：

三个启动器均使用当前 Admin UI 设置。使用 Agent 的模型选择器，从 FCC 暴露的模型中选择。常规 CLI 参数仍然有效，例如：

fcc-pi 仅为该 Pi 进程注册 FCC；你现有的 Pi 设置、会话、凭据和扩展均保持不变。

1. 在下方打开某个提供商链接，获取其密钥、模型或配置说明。
2. 在 Admin UI 中配置列出的设置。对于 OpenAI，请改用 Providers → Connected accounts。
3. 搜索 MODEL 下拉列表并选择模型。如果提供商无法列出模型，请手动输入 <provider-id>/<exact-provider-model-id>。
4. 点击 Validate，然后点击 Apply。

提供商	Admin UI 设置	MODEL 示例
NVIDIA NIM	NVIDIA_NIM_API_KEY	nvidia_nim/nvidia/nemotron-3-super-120b-a12b
OpenAI / ChatGPT	在 Admin UI 中连接 ChatGPT	openai/<model-id>
Azure OpenAI	AZURE_OPENAI_API_KEY 和 AZURE_OPENAI_BASE_URL	azure_openai/<deployment-name>
OpenRouter	OPENROUTER_API_KEY	open_router/openrouter/free
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/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
GitHub Models	GITHUB_MODELS_TOKEN	github_models/openai/gpt-4.1
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
Groq	GROQ_API_KEY	groq/llama-3.3-70b-versatile
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
Cloudflare Workers AI	CLOUDFLARE_API_TOKEN 和 CLOUDFLARE_ACCOUNT_ID	cloudflare/@cf/moonshotai/kimi-k2.6
Z.ai	ZAI_API_KEY	zai/glm-5.2
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>

重要的提供商说明：

• OpenAI 使用你的 ChatGPT 订阅，而非 API 密钥。请通过 Providers → Connected accounts 进行连接；默认使用浏览器 PKCE，无头环境可使用设备代码。FCC 会将自身的可续期凭据保存到 ~/.fcc/auth/ 下，且不会影响 Codex 登录。连接后请重启已运行的 Agent，以刷新其模型选择器。
• Azure OpenAI 使用资源中的部署名称。将 AZURE_OPENAI_BASE_URL 设置为完整 v1 端点，例如 https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/，并选择支持 Chat Completions 的部署。Azure 不会通过其数据平面模型列表公开自定义部署名称，因此请将部署名称作为自定义模型 slug 输入。
• Mistral Codestral 使用与 Mistral La Plateforme 不同的独立密钥。
• Kimi Code 订阅密钥使用 kimi_code/；Kimi API 额度密钥使用 kimi/。Kimi Code 计划适用于个人交互式编码 Agent 使用，须遵守 Kimi 社区指南。
• OpenCode Zen 和 OpenCode Go 共用 OPENCODE_API_KEY，但使用不同的模型前缀。
• Amazon Bedrock 使用其 Mantle OpenAI 兼容端点。将 BEDROCK_BASE_URL 设为与 API 密钥同一区域的端点，并从 FCC 的模型选择器返回结果中选择一个模型。
• Vertex AI 使用 Google Application Default Credentials，而非 API 密钥。在本地运行一次 gcloud auth application-default login；也支持服务账号文件和已附加的服务账号。设置 VERTEX_PROJECT_ID，并可将默认值为 global 的 VERTEX_LOCATION 更改为其他值。FCC 会自动刷新即将过期的访问令牌。
• Cloudflare 同时需要 API 令牌和账户 ID。
• Ollama Cloud 直接连接至 ollama.com；请使用 FCC 模型选择器显示的精确模型 ID。本地 Ollama 仍可通过独立的 ollama/ 前缀使用。
• 编码 Agent 应优先使用具备工具调用能力的模型。本地模型还需要拥有足以容纳 Agent 系统提示词和工具定义的上下文窗口。

本地提供商设置

启动 LM Studio 的本地服务器，加载支持工具调用的模型，并使用 LM Studio 显示的模型标识符及 lmstudio/ 前缀。默认 URL 为 http://localhost:1234/v1。

使用 OpenAI 兼容的 Chat Completions API 启动 llama-server，并为模型提供足够上下文。使用本地模型 ID 及 llamacpp/ 前缀。LLAMACPP_BASE_URL 默认值为 http://localhost:8080/v1；FCC 接受服务器根地址或显式的 /v1 后缀。

ollama pull llama3.1
ollama serve

使用 ollama list 显示的标签及 ollama/ 前缀。OLLAMA_BASE_URL 默认值为 http://localhost:11434；FCC 接受根 URL 或显式的 /v1 后缀。

可选的模型层级路由

MODEL 是每个请求的回退模型。为 MODEL_FABLE、MODEL_OPUS、MODEL_SONNET 或 MODEL_HAIKU 选择模型，即可覆盖单个 Claude Code 层级；选择 None 则使用 MODEL。

例如，将 Opus 路由至 nvidia_nim/nvidia/nemotron-3-super-120b-a12b，Sonnet 路由至 open_router/openrouter/free，Haiku 路由至 lmstudio/qwen3.5-coder，同时将 MODEL 保持为 zai/glm-5.2。

打开 Admin UI → Model Config → Reasoning，并选择所需行为。

选择	行为
From client（默认）	使用 Claude Code、Codex 或 Pi 发送的 effort。若未发送，则保留提供商默认设置。
Off	请求禁用推理。
Low、Medium、High、X-High 或 Max	使用选定的推理等级覆盖客户端设置。
Inherit（仅 Fable、Opus、Sonnet 和 Haiku）	使用根级 Reasoning 选择。

不支持所选控制项的提供商将保留其自身行为。

在终端中使用时，先启动 fcc-server，再运行 fcc-claude、fcc-codex 或 fcc-pi。编辑器集成请使用下方指南。

VS Code 中的 Claude Code

安装 Claude Code 扩展。以 JSON 形式打开 VS Code 用户设置，并添加：

"claudeCode.disableLoginPrompt": true,
"claudeCode.environmentVariables": [
  { "name": "ANTHROPIC_BASE_URL", "value": "http://localhost:8082" },
  { "name": "ANTHROPIC_AUTH_TOKEN", "value": "freecc" },
  { "name": "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY", "value": "1" },
  { "name": "CLAUDE_CODE_AUTO_COMPACT_WINDOW", "value": "190000" },
  { "name": "DISABLE_AUTOUPDATER", "value": "1" },
  { "name": "DISABLE_FEEDBACK_COMMAND", "value": "1" },
  { "name": "DISABLE_ERROR_REPORTING", "value": "1" }
]

使端口和认证令牌与 Admin UI 保持一致，然后重新加载扩展。

Codex App

启动 FCC，然后将其提供商和生成的模型目录添加至用户级 Codex 配置。

Windows — 编辑 %USERPROFILE%\.codex\config.toml，并替换 YOUR_USERNAME：

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
model_catalog_json = "C:/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http://127.0.0.1:8082/v1"
http_headers = { Authorization = "Bearer freecc" }
wire_api = "responses"

macOS — 编辑 ~/.codex/config.toml，并替换 YOUR_USERNAME：

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
model_catalog_json = "/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http://127.0.0.1:8082/v1"
http_headers = { Authorization = "Bearer freecc" }
wire_api = "responses"

使模型、端口和 bearer token 与 Admin UI 保持一致。完成设置或更改模型后重启 Codex App，再使用其模型选择器选择任意 FCC 提供商/模型 slug。

VS Code 中的 Codex

安装 Codex 扩展。创建或编辑 ~/.codex/config.toml（Windows 上为 %USERPROFILE%\.codex\config.toml）：

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http:/

Claude Code running through the Free Claude Code proxy.

Codex CLI using the local FCC Responses provider.

Claude Code native/model picker with FCC gateway models.

Codex native/model picker with the generated FCC catalog.

• Launch Claude Code with fcc-claude, Codex with fcc-codex, or Pi with fcc-pi.
• Run FCC in the background from a desktop launcher on Windows or macOS.
• Switch among 31 cloud and local providers from the Admin UI.
• Use each coding agent's native model picker.
• Route Fable, Opus, Sonnet, Haiku, and fallback traffic to different models.
• Keep streaming, tool use, reasoning, and image input across compatible models.
• Connect Claude Code and Codex in VS Code or Claude Code through JetBrains ACP.
• Optionally run Claude Code sessions through Discord or Telegram with voice-note transcription.
• Protect the local proxy with optional token authentication.

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")))

Re-run the same command whenever you want to update. You can review the installers before running them: install.sh and install.ps1.

The installer asks which coding agents to install or verify. Choose at least one; skipped agents are left unchanged.

Open Free Claude Code from your desktop or Start menu.

Open Free Claude Code from your desktop or Applications folder.

Run:

On Windows and macOS, FCC runs in the system tray or menu bar without opening a terminal. Use its menu to open Admin, check server status, restart, or quit. On Windows, left-clicking the tray icon opens Admin directly.

To print the installed Free Claude Code version without starting the server, run fcc-server --version.

When using fcc-server, keep the terminal open. The Admin UI opens in your browser once the server is healthy by default. Its address is shown in the startup log:

INFO:     Admin UI: http://127.0.0.1:8082/admin (local-only)

Use the port shown in your terminal if it differs from 8082.

1. Create an API key at build.nvidia.com/settings/api-keys.
2. Open the Admin UI URL from the server log.
3. Paste the key into NVIDIA_NIM_API_KEY.
4. Leave MODEL on the default nvidia_nim/nvidia/nemotron-3-super-120b-a12b, or search the model dropdown and select another model.
5. Click Validate , then Apply.

Claude Code:

Codex:

Pi:

All three launchers use the current Admin UI settings. Use the agent's model picker to choose from the models FCC exposes. Normal CLI arguments still work, for example:

fcc-pi registers FCC only for that Pi process; your existing Pi settings, sessions, credentials, and extensions remain unchanged.

1. Open a provider link below for its key, models, or setup instructions.
2. In the Admin UI, configure the listed setting. For OpenAI, use Providers → Connected accounts instead.
3. Search the MODEL dropdown and select a model. If the provider cannot list models, enter <provider-id>/<exact-provider-model-id> manually.
4. Click Validate , then Apply.

Provider	Admin UI setting	Example MODEL
NVIDIA NIM	NVIDIA_NIM_API_KEY	nvidia_nim/nvidia/nemotron-3-super-120b-a12b
OpenAI / ChatGPT	Connect ChatGPT in the Admin UI	openai/<model-id>
Azure OpenAI	AZURE_OPENAI_API_KEY and AZURE_OPENAI_BASE_URL	azure_openai/<deployment-name>
OpenRouter	OPENROUTER_API_KEY	open_router/openrouter/free
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/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
GitHub Models	GITHUB_MODELS_TOKEN	github_models/openai/gpt-4.1
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
Groq	GROQ_API_KEY	groq/llama-3.3-70b-versatile
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
Cloudflare Workers AI	CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID	cloudflare/@cf/moonshotai/kimi-k2.6
Z.ai	ZAI_API_KEY	zai/glm-5.2
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>

Important provider notes:

• OpenAI uses your ChatGPT subscription rather than an API key. Connect from Providers → Connected accounts ; browser PKCE is the default and device code is available for headless setups. FCC stores its own renewable credentials under ~/.fcc/auth/ and leaves Codex login untouched. Restart an already-running agent after connecting to refresh its model picker.
• Azure OpenAI uses the deployment names from your resource. Set AZURE_OPENAI_BASE_URL to its complete v1 endpoint, such as https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/, and select a deployment that supports Chat Completions. Azure does not expose custom deployment names through its data-plane model list, so enter the deployment name as a custom model slug.
• Mistral Codestral uses a separate key from Mistral La Plateforme.
• Kimi Code subscription keys use kimi_code/; Kimi API credit keys use kimi/. Kimi Code plans are for personal interactive coding-agent use under Kimi's community guidelines.
• OpenCode Zen and OpenCode Go share OPENCODE_API_KEY but use different model prefixes.
• Amazon Bedrock uses its Mantle OpenAI-compatible endpoint. Set BEDROCK_BASE_URL to the endpoint for the same region as the API key and select one of the models returned by FCC's model picker.
• Vertex AI uses Google Application Default Credentials instead of an API key. Locally, run gcloud auth application-default login once; service-account files and attached service accounts also work. Set VERTEX_PROJECT_ID, and optionally change VERTEX_LOCATION from its global default. FCC refreshes expiring access tokens automatically.
• Cloudflare requires both its API token and account ID.
• Ollama Cloud connects directly to ollama.com; use the exact model IDs shown by FCC's model picker. Local Ollama remains available through 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

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.

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 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.

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, or Pi. 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.

For terminal use, start fcc-server, then run fcc-claude, fcc-codex, or fcc-pi. Use the guides below for editor integrations.

Claude Code in VS Code

Install the Claude Code extension. Open VS Code's user settings as JSON and add:

"claudeCode.disableLoginPrompt": true,
"claudeCode.environmentVariables": [
  { "name": "ANTHROPIC_BASE_URL", "value": "http://localhost:8082" },
  { "name": "ANTHROPIC_AUTH_TOKEN", "value": "freecc" },
  { "name": "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY", "value": "1" },
  { "name": "CLAUDE_CODE_AUTO_COMPACT_WINDOW", "value": "190000" },
  { "name": "DISABLE_AUTOUPDATER", "value": "1" },
  { "name": "DISABLE_FEEDBACK_COMMAND", "value": "1" },
  { "name": "DISABLE_ERROR_REPORTING", "value": "1" }
]

Match the port and authentication token to the Admin UI, then reload the extension.

Codex App

Start FCC, then add its provider and generated model catalog to your user-level Codex configuration.

Windows — edit %USERPROFILE%\.codex\config.toml and replace YOUR_USERNAME:

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
model_catalog_json = "C:/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http://127.0.0.1:8082/v1"
http_headers = { Authorization = "Bearer freecc" }
wire_api = "responses"

macOS — edit ~/.codex/config.toml and replace YOUR_USERNAME:

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
model_catalog_json = "/Users/YOUR_USERNAME/.fcc/codex-model-catalog.json"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http://127.0.0.1:8082/v1"
http_headers = { Authorization = "Bearer freecc" }
wire_api = "responses"

Match the model, port, and bearer token to the Admin UI. Restart the Codex App after setup or model changes, then use its model picker to select any FCC provider/model slug.

Codex in VS Code

Install the Codex extension. Create or edit ~/.codex/config.toml (%USERPROFILE%\.codex\config.toml on Windows):

model_provider = "fcc"
model = "nvidia_nim/nvidia/nemotron-3-super-120b-a12b"

[model_providers.fcc]
name = "Free Claude Code"
base_url = "http://127.0.0.1:8082/v1"
http_headers = { Authorization = "Bearer freecc" }
wire_api = "responses"

Match model, the port, and bearer token to the Admin UI, then restart VS Code. For WSL-backed Codex, edit the file inside WSL.

Claude Code in JetBrains ACP

Edit the installed Claude ACP configuration:

• Windows: C:\Users\%USERNAME%\AppData\Roaming\JetBrains\acp-agents\installed.json
• Linux/macOS: ~/.jetbrains/acp.json

Set the environment for acp.registry.claude-acp:

"env": {
  "ANTHROPIC_BASE_URL": "http://localhost:8082",
  "ANTHROPIC_AUTH_TOKEN": "freecc",
  "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY": "1",
  "CLAUDE_CODE_AUTO_COMPACT_WINDOW": "190000",
  "DISABLE_AUTOUPDATER": "1",
  "DISABLE_FEEDBACK_COMMAND": "1",
  "DISABLE_ERROR_REPORTING": "1"
}

Match the port and token to the Admin UI, then restart the IDE.

Claude Code still asks you to log in

If Claude Code asks you to log in after you configure the FCC URL and token, open its state file:

• Windows: %USERPROFILE%\.claude.json
• macOS/Linux/WSL: ~/.claude.json

Merge this property into the existing JSON without removing its other fields:

"hasCompletedOnboarding": true

If the file does not exist, create it with a complete JSON object:

{
  "hasCompletedOnboarding": true
}

Restart Claude Code or the IDE after saving the file.

Configure integrations from Admin UI → Messaging , then click Validate and Apply.

Discord bot

1. Create a bot in the Discord Developer Portal.
2. Enable Message Content Intent and invite it with read, send, message-history, and Manage Messages permissions so /clear can remove user prompts.
3. Set Messaging Platform to discord.
4. Enter Discord Bot Token , Allowed Discord Channels , and an absolute Allowed Directory.
5. Apply the settings and restart the server if requested.

Telegram bot

1. Create a bot with @BotFather.
2. Get your numeric user ID from @userinfobot. In groups, grant the bot permission to delete messages.
3. Set Messaging Platform to telegram.
4. Enter Telegram Bot Token , Allowed Telegram User ID , and an absolute Allowed Directory.
5. Apply the settings and restart the server if requested.

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 voice backend you need.

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 the CUDA 13.0 PyTorch backend
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 the CUDA 13.0 PyTorch backend
& ([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.

Re-run the matching command from Install Or Update.

Stop every running FCC command first. The uninstaller verifies every FCC command is gone before deleting its managed data.

Removes

• Free Claude Code, including its desktop launcher and commands
• ~/.fcc/

Keeps

• uv and Python
• Claude Code, Codex, and Pi
• 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")))

MIT License. See LICENSE for details.