Orchestra logo orchestra
[Hint: Shift+Tab] capabilities workflow compare demo commands download GitHub
local · v1.0.0 · powered by ollama

An AI agent that never
leaves your terminal
or your machine.

Orchestra is a privacy-first, terminal-native coding agent. It plans, calls tools, reads your codebase, and writes code with the same fluency as cloud tools like Claude Code — running entirely on ollama, on hardware you own.

click me!
orchestra — zsh — 120×32
Welcome to Orchestra v1.0.0. Type a command to see it in action.
Try: | |
you › _

Everything a cloud agent does. Nothing leaves the machine.

Nine tools, one loop, zero network dependency on your code or your prompts.

100% local & private

No API keys, no subscriptions. Your code and prompts never leave your machine.

Agentic tool swarm

Reads files, lists directories, runs bash, and edits your codebase autonomously.

Artifact system

Ask for an architectural plan or doc — it's generated as a markdown artifact you can view and re-inject later.

Multi-session support

Isolated chat sessions. Jump between debugging and brainstorming without cross-contaminating context.

Context injection

/add file.py feeds files into context. Prefix any host command with ! to inject its output.

Dynamic theming

Switch between Dracula, Nord, Monokai, and Synthwave on the fly, mid-session.

Prompt library

Save frequently used prompts to ~/.orchestra/prompts/ and load them instantly.

Ambient focus

Toggle background ambient music with Shift+Tab to stay in flow.

Permission gate

Dangerous actions like write_file or run_bash require explicit y/n approval before they execute.


The Autonomous Loop.

Orchestra isn't just an autocomplete. It runs in a continuous feedback loop until the goal is achieved.

1. Set Goal
Set a prompt from library or define a custom goal
2. Understand Context
Read workspace state and gather context
3. Plan & Artifacts
Create a step-by-step implementation plan
4. Human Approval
User reviews and approves the plan
8. Summary
Mark goal done and provide final summary
Execution Loop
7. Verify Task
Check if task succeeded.
6. Execute Task
Run tools, edit files.
(Ask human permission if required)
5. Task Breakdown
Break approved plan into sub-tasks

Why Orchestra?

How Orchestra stacks up against other AI coding assistants in the landscape.

Feature Orchestra Claude Code Antigravity Codex
Privacy / Execution 100% Local (Ollama) Cloud (Anthropic) Hybrid (Depends) Cloud (OpenAI)
Agentic Loop Yes (Autonomous) Yes Yes No (Autocomplete)
Interface Rich TUI CLI IDE Extension / CLI IDE Extension
Cost Free (Open Source) Pay-per-token API Subscription / API Subscription

One prompt. A full plan, executed and verified.

A real Orchestra session: the agent breaks the task down, searches, writes the artifact, and marks it done — no manual steps in between.

session — orchestra
you › Write a detailed 5-day workout plan and save it as an artifact named 'workout_plan'.
tasks_add Added task #1: Research workout routines and create a 5-day plan.
search_web 1. The 5-Day Workout Routine And Split
create_artifact Artifact created successfully: ~/.orchestra/artifacts/workout_plan.md
tasks_done Marked #1 as done: Research workout routines and create a 5-day plan.

Slash commands

Type / inside the TUI for a self-documenting command menu with contextual hints.

CommandDescription
/helpShow the help menu
/sessionManage isolated chat sessions — new, list, delete, switch
/artifactView and inject AI-generated architectural plans and documents
/add <file>Inject a specific file into the agent's context for the next prompt
/prompt <name>Load a saved prompt from your personal library
/model <name>Switch the active Ollama model
/theme <name>Switch the visual theme — dracula, nord, monokai, synthwave
/tasks · /goalView and manage your persistent autonomous task list
/contextView context window usage and a visual map of the conversation

Running in under five minutes.

Install Python 3.10+ and Ollama, then clone Orchestra and you're ready to go.

1
Install Ollama and download a model
$ brew install ollama $ ollama pull qwen3:4b-instruct
2
Install Orchestra
$ git clone https://github.com/TheAhsanFarabi/orchestra.git $ cd orchestra $ python3 -m venv .venv $ source .venv/bin/activate $ pip install -e .
3
Start Orchestra
$ orchestra
1
Install Ollama and download a model
$ curl -fsSL https://ollama.com/install.sh | sh $ ollama pull qwen3:4b-instruct
2
Install Orchestra
$ git clone https://github.com/TheAhsanFarabi/orchestra.git $ cd orchestra $ python3 -m venv .venv $ source .venv/bin/activate $ pip install -e .
3
Start Orchestra
$ orchestra
1
Install Ollama and download a model
> winget install Ollama.Ollama > ollama pull qwen3:4b-instruct
2
Install Orchestra (PowerShell)
> git clone https://github.com/TheAhsanFarabi/orchestra.git > cd orchestra > python -m venv .venv > .venv\Scripts\Activate.ps1 > pip install -e .
3
Start Orchestra
> orchestra
If PowerShell blocks activation, run: Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass and activate the virtual environment again.
Local-first Ollama Compatible Privacy-first MIT Licensed

"

Orchestra was born from true human-AI collaboration. By blending the raw power of agentic coding with deliberate engineering intuition, we forged a completely unique value proposition. Version 1 is the culmination of 48 hours of relentless building, testing, and manual curation. But this is just the beginning. The upcoming updates will redefine the landscape. Ultimately, my north star remains unchanged: advancing environmental sustainability, championing human-centered AI, and ensuring uncompromising AI safety.

Ahsan Farabi Creator of Orchestra