Quickstart
Get Moltis running in under 5 minutes.
1. Install
curl -fsSL https://www.moltis.org/install.sh | sh
Or via Homebrew:
brew install moltis-org/tap/moltis
2. Start
moltis
Youβll see output like:
π Moltis gateway starting...
π Open http://localhost:13131 in your browser
3. Configure a Provider
You need an LLM provider configured to chat. The fastest options:
Option A: API Key (Anthropic, OpenAI, Gemini, etc.)
- Set an API key as an environment variable and restart Moltis:
export ANTHROPIC_API_KEY="sk-ant-..." # Anthropic export OPENAI_API_KEY="sk-..." # OpenAI export GEMINI_API_KEY="..." # Google Gemini - Models appear automatically in the model picker.
Or configure via the web UI: Settings β Providers β enter your API key.
Option B: OAuth (Codex / Copilot)
- In Moltis, go to Settings β Providers
- Click OpenAI Codex or GitHub Copilot β Connect
- Complete the OAuth flow
Option C: Local LLM (Offline)
- In Moltis, go to Settings β Providers
- Click Local LLM
- Choose a model and save
See Providers for the full list of supported providers.
4. Chat!
Go to the Chat tab and start a conversation:
You: Write a Python function to check if a number is prime
Agent: Here's a Python function to check if a number is prime:
def is_prime(n):
if n < 2:
return False
for i in range(2, int(n ** 0.5) + 1):
if n % i == 0:
return False
return True
Use Copy as Markdown on an assistant response to preserve its formatting, or Save as Markdown in the session toolbar to download the full conversation.
Whatβs Next?
Enable Tool Use
Moltis can execute code, browse the web, and more. Tools are enabled by default with sandbox protection.
Try:
You: Create a hello.py file that prints "Hello, World!" and run it
Connect Telegram
Chat with your agent from anywhere:
- Create a bot via @BotFather
- Copy the bot token
- In Moltis: Settings β Telegram β Enter token β Save
- Message your bot!
Connect Discord
- Create a bot in the Discord Developer Portal
- Enable Message Content Intent and copy the bot token
- In Moltis: Settings β Channels β Connect Discord β Enter token β Connect
- Invite the bot to your server and @mention it!
Add MCP Servers
Extend capabilities with MCP servers:
# In moltis.toml
[mcp]
[mcp.servers.github]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-github"]
env = { GITHUB_TOKEN = "ghp_..." }
Set Up Memory
Enable long-term memory for context across sessions:
# In moltis.toml
[memory]
provider = "openai"
model = "text-embedding-3-small"
Add knowledge by placing Markdown files in ~/.moltis/memory/.
Useful Commands
| Command | Description |
|---|---|
/new | Start a new session |
/model <name> | Switch models |
/agent | List or switch chat agents |
/mode | List or switch temporary session modes |
/clear | Clear chat history |
/help | Show available commands |
File Locations
| Path | Contents |
|---|---|
~/.config/moltis/moltis.toml | Configuration |
~/.config/moltis/provider_keys.json | API keys |
~/.moltis/ | Data (sessions, memory, logs) |
Getting Help
- Documentation: docs.moltis.org
- GitHub Issues: github.com/moltis-org/moltis/issues
- Discussions: github.com/moltis-org/moltis/discussions