Janito — AI Coding Agent
Janito is an AI Coding Agent with tools, MCP, and skills.
📖 Full documentation available at https://joaompinto.github.io/janito/
⚠️ Disclaimer: The code on this repo has been developed mostly using AI.
Features
- 🔧 Function Calling - Built-in tools for file operations, web search, and more
- 🔌 Plugins - Gmail, code search, OneDrive, and more via the plugin system
- 🔌 MCP Support - Connect to Model Context Protocol servers
- 🧩 Skills - Install and use task-specific skills from GitHub
- 🌐 Web UI (Alpha) - Chat through a browser instead of the terminal with
--web - 🔌 Agent Client Protocol (ACP) - Run as an ACP v1 subprocess agent for editors like Zed with
--acp - ↪️ Session Resume - Exit a terminal chat and reopen it with
janito -C(full conversation restored) - 📊 Real-time Progress - Watch tool execution progress as it happens
- 🚀 Easy Setup - Interactive configuration with
--configor quick setup with--setflags - 🔗 OpenAI-Compatible & Native APIs - Works with any OpenAI-compatible endpoint (OpenAI, LM Studio, Ollama, custom) and native SDKs (Anthropic, DashScope)
NOTE: Janito should be used on development systems on which data loss is tolerable and there are no critical secrets
Quick Start
# Install
pip install janito
# Or, with uv (recommended)
uv tool install janito
# Configure interactively
janito --config
# Or set options directly (two steps: config, then API key or ChatGPT login)
janito --set provider=openai --set model=gpt-6.1-sol
janito --set-api-key="sk-your-key" --provider openai
# ...or sign in with your ChatGPT plan instead of an API key:
# janito --provider openai --login
# Start chatting
janito "Hello!"
Installation
From PyPI
pip install janito
Or, with uv:
uv tool install janito
For development setup, see README_DEV.md.
Configuration
Interactive Setup
janito --config
You'll be prompted for:
- Provider -
openaiorcustom - API Key - Masked for security
- Model - e.g.,
gpt-6.1-sol - Max Output Tokens - Maximum output tokens (default: 65536)
- Max Input Tokens - Maximum input tokens / context window (default: 128000)
Quick Configuration with --set
Set options directly from the command line:
# Single key-value
janito --set model=gpt-6.1-sol
You can also use --get, --unset, and --set-secret with multiple values.
View Configuration
janito --show-config
Costs per provider
| Provider | Last Model | Price |
|---|---|---|
| Alibaba | qwen3.8-flash | Pay as you go |
| Moonshot | kimi-k3 | $15/month (Moderato) |
| z.ai | glm-5.3-flash | $12.6/month (Lite) |
| openai | gpt-6.1-sol | Pay as you go / ChatGPT plan (OAuth) |
For custom endpoints (base-url), see README_custom.md.
Usage
Single Prompt
janito "What is the capital of France?"
Pipe Input
echo "Tell me a joke" | janito
Interactive Chat
janito
Commands in chat mode:
/exit- End the sessionclear- Clear conversation and start a new oneCtrl+D/Ctrl+Zthen Enter - Exit (EOF)/help- List all commands (with descriptions) and shortcuts
Web UI (Alpha)
⚠️ Alpha — The
--webmode is currently in alpha. It works, but the interface, CLI flags, and API may change between releases.
Janito can serve a browser-based chat interface instead of the terminal. This requires optional dependencies that are not part of the core install:
# Install with the web extra
pip install janito[web]
# or
uv tool install janito[web]
Then start the server (opens your browser automatically):
janito --web
# All normal Janito flags still apply, plus web-specific ones:
janito --web -r -w --web-port 9090 # privileges + web, custom port
janito --web --no-web-open # don't auto-open the browser
The server binds to 127.0.0.1 by default (localhost only). For full details
(features, security, API endpoints, architecture), see the
Web UI documentation.
System Prompt Options
Control how the system prompt is handled:
# Use default system prompt (with tools enabled)
janito "What can you do?"
# Disable system prompt entirely (no tools at all)
janito -Z "Simple prompt without system context"
# Override with a custom system prompt (tools stay enabled)
janito -S "You are a concise coding assistant" "Explain recursion"
# Keep the system prompt but skip tool loading (skill tools stay enabled)
janito --no-tools "Explain recursion"
# Skip only the parallel-tasks toolset (StartTask/StopTask/WaitForTask/ListTasks)
janito --no-tasks "Refactor this file"
| Flag | Description |
|---|---|
-Z, --no-system-prompt |
Skip system prompt and disable tools |
-S, --system-prompt |
Custom system prompt |
--no-tools |
Do not load tools (skill tools stay enabled) |
--no-tasks |
Do not load the tasks toolset (StartTask, StopTask, WaitForTask, ListTasks); all other tools stay enabled |
Note: When using
-Z, built-in tools (file operations, MCP) are disabled. Use the default mode or-Sflag when you need tool access.Note:
--no-toolsdisables loading of all non-skill tools (file operations, MCP) while keeping the skill tools (load_skill,read_skill_resource) available, so the model can still load installed skills on demand.Note:
--no-tasksdisables only the tasks toolset (theStartTask/StopTask/WaitForTask/ListTaskstools that spawn parallel child processes). File, system, net and skill tools stay available.
Logging
janito --log=info "Your prompt" # Info level
janito --log=debug "Your prompt" # Debug level
janito --log=info,debug "Your prompt" # Multiple levels
Examples
OpenAI
# Step 1: Set provider and model
janito --set provider=openai --set model=gpt-6.1-sol
# Step 2a: Store API key (pay as you go)
janito --set-api-key="sk-your-key" --provider openai
# ...or step 2b: sign in with ChatGPT (OAuth, no API key)
# janito --provider openai --login
# Then run any prompt
janito "Explain quantum computing"
Alibaba (Qwen)
# Step 1: Set provider and model
janito --set provider=alibaba --set model=qwen3.8-flash
# Step 2: Store API key
janito --set-api-key="your-dashscope-api-key" --provider alibaba
# Then run any prompt
janito "Explain quantum computing"
Custom Endpoint
janito --set provider=custom --set base-url=http://localhost:8000/v1
Built-in Tools
janito includes tools for common tasks:
File Operations
# List files
python -m janito.tools.files.list_files . --recursive --pattern "*.py"
# Read file
python -m janito.tools.files.read_file README.md --max-lines 20
MCP Tools
Connect to MCP servers using the /mcp command inside the interactive shell:
# Add a stdio-based MCP server
/mcp add myserver stdio python -m mcp.server
# Add an HTTP-based MCP server
/mcp add remote http https://api.example.com/mcp
# List configured servers
/mcp list
For full MCP documentation, see README_MCP.md.
Tool Progress Reporting
Tools report progress in real-time:
🔄 Reading files...
📊 Processing: 50/100 files
✅ Completed: 100 files (2.3MB)
Progress messages go to stderr so they don't interfere with tool output.
Error Handling
| Exit Code | Meaning |
|---|---|
0 |
Success |
1 |
Configuration or runtime error |
130 |
User cancelled (Ctrl+C or Enter) |
Dependencies
- Python 3.10+
openai>=1.0.0rich>=10.0.0prompt-toolkit>=3.0.0requests>=2.28.0(for MCP support)pathspec>=0.11.0(for.gitignore-aware file listing)questionary>=2.1.1(for the interactive--configwizard)
Optional extras: janito[web] adds fastapi/uvicorn (for --web); the
native API types need anthropic (--api-type Anthropic), dashscope
(DashScope) or google-genai (Gemini).
License
MIT License
2 maintainers
Metadata
2 maintainers
Release files for janito 4.48.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| janito-4.48.0.tar.gz | 1.2 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| janito-4.48.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.9 MB
Release files / janito-4.48.0.tar.gz
| Download URL | janito-4.48.0.tar.gz |
|---|---|
| Size | 1.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
375f5fd77a73cbe96ba663efbe983a3977cd5f8264d2fac83547e2329d3e8807
|
|
BLAKE2b-256 checksum How to use checksums |
a3efd1822272faecb8c79378f0b1fd0cafbeb45467b87ad8206a227ca329c161
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 13, 2026.
Transparency logRelease files / janito-4.48.0-py3-none-any.whl
| Download URL | janito-4.48.0-py3-none-any.whl |
|---|---|
| Size | 700.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b30749f14655dfd58a2c0c87aa732bb03945412eb54ad89bf1dfbb4b5570e11b
|
|
BLAKE2b-256 checksum How to use checksums |
7c6fd62dd0b25e90ec4015bd87499d1313f5ff36d6e1965182352e6b9a4b19d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 13, 2026.
Transparency log
