# Free Claude Code
### Use Claude Code CLI & VSCode — for free. No Anthropic API key required.
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
[](https://github.com/astral-sh/uv)
[](https://github.com/Alishahryar1/free-claude-code/actions/workflows/tests.yml)
[](https://pypi.org/project/ty/)
[](https://github.com/astral-sh/ruff)
[](https://github.com/Delgan/loguru)
A lightweight proxy server that translates Claude Code's Anthropic API calls into **NVIDIA NIM**, **OpenRouter**, or **LM Studio** format.
Get **40 free requests/min** on NVIDIA NIM, access **hundreds of models** on OpenRouter, or run **fully local** with LM Studio.
[Features](#features) · [Quick Start](#quick-start) · [How It Works](#how-it-works) · [Discord Bot](#discord-bot) · [Configuration](#configuration)
---
Claude Code running via NVIDIA NIM — completely free
## Features
| Feature | Description |
|---------|-------------|
| **Zero Cost** | 40 req/min free on NVIDIA NIM. Free models on OpenRouter. Fully local with LM Studio |
| **Drop-in Replacement** | Set 2 env vars — no modifications to Claude Code CLI or VSCode extension needed |
| **3 Providers** | NVIDIA NIM, OpenRouter (hundreds of models), LM Studio (local & offline) |
| **Thinking Token Support** | Parses `` tags and `reasoning_content` into native Claude thinking blocks |
| **Heuristic Tool Parser** | Models outputting tool calls as text are auto-parsed into structured tool use |
| **Request Optimization** | 5 categories of trivial API calls intercepted locally — saves quota and latency |
| **Discord Bot** | Remote autonomous coding with tree-based threading, session persistence, and live progress (Telegram also supported) |
| **Smart Rate Limiting** | Proactive rolling-window throttle + reactive 429 exponential backoff + optional concurrency cap across all providers |
| **Subagent Control** | Task tool interception forces `run_in_background=False` — no runaway subagents |
| **Extensible** | Clean `BaseProvider` and `MessagingPlatform` ABCs — add new providers or platforms easily |
## Quick Start
### Prerequisites
1. Get an API key (or use LM Studio locally):
- **NVIDIA NIM**: [build.nvidia.com/settings/api-keys](https://build.nvidia.com/settings/api-keys)
- **OpenRouter**: [openrouter.ai/keys](https://openrouter.ai/keys)
- **LM Studio**: No API key needed — run locally with [LM Studio](https://lmstudio.ai)
2. Install [Claude Code](https://github.com/anthropics/claude-code)
3. Install [uv](https://github.com/astral-sh/uv)
### Clone & Configure
```bash
git clone https://github.com/Alishahryar1/free-claude-code.git
cd free-claude-code
cp .env.example .env
```
Choose your provider and edit `.env`:
NVIDIA NIM (recommended — 40 req/min free)
```dotenv
NVIDIA_NIM_API_KEY=nvapi-your-key-here
MODEL=nvidia_nim/stepfun-ai/step-3.5-flash
```
OpenRouter (hundreds of models)
```dotenv
OPENROUTER_API_KEY=sk-or-your-key-here
MODEL=open_router/stepfun/step-3.5-flash:free
```
LM Studio (fully local, no API key)
```dotenv
MODEL=lmstudio/lmstudio-community/qwen2.5-7b-instruct
```
### Run It
**Terminal 1** — Start the proxy server:
```bash
uv run uvicorn server:app --host 0.0.0.0 --port 8082
```
**Terminal 2** — Run Claude Code:
```bash
ANTHROPIC_AUTH_TOKEN=freecc ANTHROPIC_BASE_URL=http://localhost:8082 claude
```
That's it! Claude Code now uses your configured provider for free.
Multi-Model Support (Model Picker)
`claude-pick` is an interactive model selector that lets you choose any model from your active provider each time you launch Claude — no need to edit `MODEL` in `.env` every time you want to switch.
https://github.com/user-attachments/assets/9a33c316-90f8-4418-9650-97e7d33ad645
**1. Install [fzf](https://github.com/junegunn/fzf)** (highly recommended for the interactive picker):
```bash
brew install fzf # macOS/Linux
```
**2. Add the alias to `~/.zshrc` or `~/.bashrc`:**
```bash
# Use the absolute path to your cloned repo
alias claude-pick="/absolute/path/to/free-claude-code/claude-pick"
```
Then reload your shell (`source ~/.zshrc` or `source ~/.bashrc`) and run `claude-pick` to pick a model and launch Claude.
**Skip the picker with a fixed model** (no picker needed):
```bash
alias claude-kimi='ANTHROPIC_BASE_URL="http://localhost:8082" ANTHROPIC_AUTH_TOKEN="freecc:moonshotai/kimi-k2.5" claude'
```
VSCode Extension Setup
1. Start the proxy server (same as above).
2. Open Settings (`Ctrl + ,`) and search for `claude-code.environmentVariables`.
3. Click **Edit in settings.json** and add:
```json
"claude-code.environmentVariables": [
{ "name": "ANTHROPIC_BASE_URL", "value": "http://localhost:8082" },
{ "name": "ANTHROPIC_AUTH_TOKEN", "value": "freecc" }
]
```
4. Reload extensions.
5. **If you see the login screen** ("How do you want to log in?"): Click **Anthropic Console**, then authorize. The extension will start working. You may be redirected to buy credits in the browser — ignore that; the extension already works.
To switch back to Anthropic models, comment out the added block and reload extensions.
---
## How It Works
```
┌─────────────────┐ ┌──────────────────────┐ ┌──────────────────┐
│ Claude Code │───────>│ Free Claude Code │───────>│ LLM Provider │
│ CLI / VSCode │<───────│ Proxy (:8082) │<───────│ NIM / OR / LMS │
└─────────────────┘ └──────────────────────┘ └──────────────────┘
Anthropic API │ OpenAI-compatible
format (SSE) ┌───────┴────────┐ format (SSE)
│ Optimizations │
├────────────────┤
│ Quota probes │
│ Title gen skip │
│ Prefix detect │
│ Suggestion skip│
│ Filepath mock │
└────────────────┘
```
- **Transparent proxy** — Claude Code sends standard Anthropic API requests to the proxy server
- **Request optimization** — 5 categories of trivial requests (quota probes, title generation, prefix detection, suggestions, filepath extraction) are intercepted and responded to instantly without using API quota
- **Format translation** — Real requests are translated from Anthropic format to the provider's OpenAI-compatible format and streamed back
- **Thinking tokens** — `` tags and `reasoning_content` fields are converted into native Claude thinking blocks so Claude Code renders them correctly
---
## Providers
| Provider | Cost | Rate Limit | Models | Best For |
|----------|------|------------|--------|----------|
| **NVIDIA NIM** | Free | 40 req/min | Kimi K2, GLM5, Devstral, MiniMax | Daily driver — generous free tier |
| **OpenRouter** | Free / Paid | Varies | 200+ (GPT-4o, Claude, Step, etc.) | Model variety, fallback options |
| **LM Studio** | Free (local) | Unlimited | Any GGUF model | Privacy, offline use, no rate limits |
Switch providers by changing `MODEL` in `.env` — use the prefix format `provider/model/name`. Invalid prefix causes an error.
| Provider | MODEL prefix | API Key Variable | Base URL |
|----------|--------------|------------------|----------|
| NVIDIA NIM | `nvidia_nim/...` | `NVIDIA_NIM_API_KEY` | `integrate.api.nvidia.com/v1` |
| OpenRouter | `open_router/...` | `OPENROUTER_API_KEY` | `openrouter.ai/api/v1` |
| LM Studio | `lmstudio/...` | (none) | `localhost:1234/v1` |
OpenRouter gives access to hundreds of models (StepFun, OpenAI, Anthropic, etc.) through a single API. Set `MODEL` to any OpenRouter model ID.
LM Studio runs locally — start the server in LM Studio's Developer tab or via `lms server start`, load a model, and set `MODEL` to the model identifier.
---
## Discord Bot
Control Claude Code remotely from Discord. Send tasks, watch live progress, and manage multiple concurrent sessions. Discord is the default messaging platform; Telegram is also supported.
**Capabilities:**
- Tree-based message threading — reply to messages to fork conversations
- Session persistence across server restarts
- Live streaming of thinking tokens, tool calls, and results
- Unlimited concurrent Claude CLI sessions (provider concurrency controlled by `PROVIDER_MAX_CONCURRENCY`)
- **Voice notes** — send voice messages; they are transcribed to text and processed like regular prompts (see [Voice Notes](#voice-notes))
- Commands: `/stop` (cancel tasks; reply to a message to stop only that task), `/clear` (standalone: reset all sessions; reply to a message to clear that branch downwards), `/stats`
### Setup
1. **Create a Discord Bot** — Go to [Discord Developer Portal](https://discord.com/developers/applications), create an application, add a bot, and copy the token. Enable **Message Content Intent** under Bot settings.
2. **Edit `.env`:**
```dotenv
MESSAGING_PLATFORM=discord
DISCORD_BOT_TOKEN=your_discord_bot_token
ALLOWED_DISCORD_CHANNELS=123456789,987654321
```
> Enable Developer Mode in Discord (Settings → Advanced), then right-click a channel and "Copy ID" to get channel IDs. Comma-separate multiple channels. If empty, no channels are allowed.
3. **Configure the workspace** (where Claude will operate):
```dotenv
CLAUDE_WORKSPACE=./agent_workspace
ALLOWED_DIR=C:/Users/yourname/projects
```
4. **Start the server:**
```bash
uv run uvicorn server:app --host 0.0.0.0 --port 8082
```
5. **Invite the bot** to your server (OAuth2 → URL Generator, scopes: `bot`, permissions: Read Messages, Send Messages, Manage Messages, Read Message History). Send a message in an allowed channel with a task. Claude responds with thinking tokens, tool calls as they execute, and the final result. Reply to messages to cancel tasks or clear branches (see Commands above).
### Telegram (Alternative)
To use Telegram instead, set `MESSAGING_PLATFORM=telegram` and configure:
```dotenv
TELEGRAM_BOT_TOKEN=123456789:ABCdefGHIjklMNOpqrSTUvwxYZ
ALLOWED_TELEGRAM_USER_ID=your_telegram_user_id
```
Get a token from [@BotFather](https://t.me/BotFather); find your user ID via [@userinfobot](https://t.me/userinfobot).
### Voice Notes
Send voice messages on Telegram or Discord; they are transcribed to text and processed as regular prompts. Uses [Hugging Face transformers Whisper](https://huggingface.co/openai/whisper-large-v3-turbo) — free, no API key, works offline, CUDA 13 compatible. No ffmpeg required (audio loaded via librosa).
Install the optional voice extra:
```bash
uv sync --extra voice
```
**Configuration:**
| Variable | Description | Default |
|----------|-------------|---------|
| `VOICE_NOTE_ENABLED` | Enable voice note handling | `true` |
| `WHISPER_MODEL` | Hugging Face model ID or short name (`tiny`, `base`, `small`, `medium`, `large-v2`, `large-v3`, `large-v3-turbo`) | `base` |
| `WHISPER_DEVICE` | `cpu` \| `cuda` | `cpu` |
| `HF_TOKEN` | Hugging Face token for faster model downloads (optional; [create one](https://huggingface.co/settings/tokens)) | — |
---
## Models
NVIDIA NIM
Full list in [`nvidia_nim_models.json`](nvidia_nim_models.json).
Popular models:
- `nvidia_nim/minimaxai/minimax-m2.5`
- `nvidia_nim/qwen/qwen3.5-397b-a17b`
- `nvidia_nim/z-ai/glm5`
- `nvidia_nim/stepfun-ai/step-3.5-flash`
- `nvidia_nim/moonshotai/kimi-k2.5`
Browse: [build.nvidia.com](https://build.nvidia.com/explore/discover)
Update model list:
```bash
curl "https://integrate.api.nvidia.com/v1/models" > nvidia_nim_models.json
```
OpenRouter
Hundreds of models from StepFun, OpenAI, Anthropic, Google, and more.
Popular models:
- `open_router/stepfun/step-3.5-flash:free`
- `open_router/deepseek/deepseek-r1-0528:free`
- `open_router/openai/gpt-oss-120b:free`
Browse: [openrouter.ai/models](https://openrouter.ai/models)
Browse free models: [https://openrouter.ai/collections/free-models](https://openrouter.ai/collections/free-models)
LM Studio
Run models locally with [LM Studio](https://lmstudio.ai). Load a model in the Chat or Developer tab, then set `MODEL` to its identifier.
Examples (native tool-use support):
- `lmstudio-community/qwen2.5-7b-instruct`
- `lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF`
- `bartowski/Ministral-8B-Instruct-2410-GGUF`
Browse: [model.lmstudio.ai](https://model.lmstudio.ai)
---
## Configuration
| Variable | Description | Default |
|----------|-------------|---------|
| `MODEL` | Model to use (prefix format: `provider/model/name`; invalid prefix causes error) | `nvidia_nim/stepfun-ai/step-3.5-flash` |
| `NVIDIA_NIM_API_KEY` | NVIDIA API key (NIM provider) | required |
| `OPENROUTER_API_KEY` | OpenRouter API key (OpenRouter provider) | required |
| `LM_STUDIO_BASE_URL` | LM Studio server URL | `http://localhost:1234/v1` |
| `PROVIDER_RATE_LIMIT` | LLM API requests per window | `40` |
| `PROVIDER_RATE_WINDOW` | Rate limit window (seconds) | `60` |
| `PROVIDER_MAX_CONCURRENCY` | Max simultaneous open provider streams | `5` |
| `HTTP_READ_TIMEOUT` | Read timeout for provider API requests (seconds) | `300` |
| `HTTP_WRITE_TIMEOUT` | Write timeout for provider API requests (seconds) | `10` |
| `HTTP_CONNECT_TIMEOUT` | Connect timeout for provider API requests (seconds) | `2` |
| `FAST_PREFIX_DETECTION` | Enable fast prefix detection | `true` |
| `ENABLE_NETWORK_PROBE_MOCK` | Enable network probe mock | `true` |
| `ENABLE_TITLE_GENERATION_SKIP` | Skip title generation | `true` |
| `ENABLE_SUGGESTION_MODE_SKIP` | Skip suggestion mode | `true` |
| `ENABLE_FILEPATH_EXTRACTION_MOCK` | Enable filepath extraction mock | `true` |
| `MESSAGING_PLATFORM` | Messaging platform: `discord` or `telegram` | `discord` |
| `DISCORD_BOT_TOKEN` | Discord Bot Token | `""` |
| `ALLOWED_DISCORD_CHANNELS` | Comma-separated channel IDs (empty = none allowed) | `""` |
| `TELEGRAM_BOT_TOKEN` | Telegram Bot Token | `""` |
| `ALLOWED_TELEGRAM_USER_ID` | Allowed Telegram User ID | `""` |
| `VOICE_NOTE_ENABLED` | Enable voice note handling | `true` |
| `WHISPER_MODEL` | Local Whisper model size | `base` |
| `WHISPER_DEVICE` | `cpu` \| `cuda` | `cpu` |
| `MESSAGING_RATE_LIMIT` | Messaging messages per window | `1` |
| `MESSAGING_RATE_WINDOW` | Messaging window (seconds) | `1` |
| `CLAUDE_WORKSPACE` | Directory for agent workspace | `./agent_workspace` |
| `ALLOWED_DIR` | Allowed directories for agent | `""` |
See [`.env.example`](.env.example) for all supported parameters.
---
## Development
### Project Structure
```
free-claude-code/
├── server.py # Entry point
├── api/ # FastAPI routes, request detection, optimization handlers
├── providers/ # BaseProvider, OpenAICompatibleProvider, NIM, OpenRouter, LM Studio
│ └── common/ # Shared utils (SSE builder, message converter, parsers, error mapping)
├── messaging/ # MessagingPlatform ABC + Discord/Telegram bots, session management
├── config/ # Settings, NIM config, logging
├── cli/ # CLI session and process management
└── tests/ # Pytest test suite
```
### Commands
```bash
uv run ruff format # Format code
uv run ruff check # Code style checking
uv run ty check # Type checking
uv run pytest # Run tests
```
---
## Extending
### Adding a Provider
For **OpenAI-compatible APIs** (Groq, Together AI, etc.), extend `OpenAICompatibleProvider`:
```python
from providers.openai_compat import OpenAICompatibleProvider
from providers.base import ProviderConfig
class MyProvider(OpenAICompatibleProvider):
def __init__(self, config: ProviderConfig):
super().__init__(config, provider_name="MYPROVIDER",
base_url="https://api.example.com/v1", api_key=config.api_key)
def _build_request_body(self, request):
return build_request_body(request) # Your request builder
```
For **fully custom APIs**, extend `BaseProvider` directly:
```python
from providers.base import BaseProvider, ProviderConfig
class MyProvider(BaseProvider):
async def stream_response(self, request, input_tokens=0, *, request_id=None):
# Yield Anthropic SSE format events
...
```
### Adding a Messaging Platform
Extend `MessagingPlatform` in `messaging/` to add Slack or other platforms:
```python
from messaging.base import MessagingPlatform
class MyPlatform(MessagingPlatform):
async def start(self):
# Initialize connection
...
async def stop(self):
# Cleanup
...
async def send_message(self, chat_id, text, reply_to=None, parse_mode=None, message_thread_id=None):
# Send a message
...
async def edit_message(self, chat_id, message_id, text, parse_mode=None):
# Edit an existing message
...
def on_message(self, handler):
# Register callback for incoming messages
...
```
---
## Contributing
Contributions are welcome! Here are some ways to help:
- Report bugs or suggest features via [Issues](https://github.com/Alishahryar1/free-claude-code/issues)
- Add new LLM providers (Groq, Together AI, etc.)
- Add new messaging platforms (Slack, etc.)
- Improve test coverage
```bash
# Fork the repo, then:
git checkout -b my-feature
# Make your changes
uv run ruff format && uv run ruff check && uv run ty check && uv run pytest
# Open a pull request
```
---
## License
This project is licensed under the **MIT License** — see the [LICENSE](LICENSE) file for details.
Built with [FastAPI](https://fastapi.tiangolo.com/), [OpenAI Python SDK](https://github.com/openai/openai-python), [discord.py](https://github.com/Rapptz/discord.py), and [python-telegram-bot](https://python-telegram-bot.org/).