---

Andromity is a private, BYOK (Bring Your Own Key) autonomous AI coding agent. Use it inside VS Code with the extension, or run it as a standalone terminal workspace. It plans complex tasks, manages parallel subagents, shows live step-by-step blueprints, lets you review diffs before applying, and gives you instant one-click rollback.

Connect your preferred AI model (Claude 3.7 Sonnet, GPT-4o, Gemini 2.5 Pro, DeepSeek R1 & V3, Groq, OpenRouter) or run 100% locally and free with Ollama.

---

⚡ Quick Install & Get Started

🚀 Option A: VS Code Extension (Recommended)

👉 Recommended: Install directly from the marketplace:
🔗 Andromity AI Coding Agent for VS Code - Visual Studio Marketplace

Or install instantly via terminal:

code --install-extension agenticmarket.andromity-agent

💻 Option B: Terminal CLI

# Linux / macOS
curl -fsSL https://raw.githubusercontent.com/agenticmarket/andromity/main/install.sh | bash

# Windows (PowerShell)
irm https://raw.githubusercontent.com/agenticmarket/andromity/main/install.ps1 | iex

# Or with pipx
pipx install andromity

---

✨ Key Features

📝 Live Task Planner & Blueprints

Andromity analyzes your codebase, creates an interactive step-by-step implementation plan, and waits for your approval before writing a single line of code. Review, approve, or skip any step.

🌊 Live Execution Waterfall Profiler

Inspect agent reasoning turns, tool execution latencies (bash commands, file operations, web queries), and parallel subagents in real time on an interactive chronological timeline grid directly inside VS Code (/waterfall).

---

🤖 396+ Models — Including Free Local Ollama

Connect Claude 3.7, GPT-4o, Gemini 2.5 Pro, DeepSeek R1, Groq, or run 100% offline with Ollama. Swap models mid-session with Ctrl+L.

---

🔐 Trust Governance — You Are Always in Control

Mode	Plans	File Writes	Terminal Commands
SAFE (default)	Approve each	Approve each	Approve each
TRUST	Approve	Direct	Direct
FULL	Auto	Direct	Direct
YOLO	Auto	Silent	Silent

Nothing runs until you say a folder is trusted. Start in SAFE, move to YOLO when you know what the agent does.

---

How it compares

	Andromity	Aider	Cursor	Claude Code
Folder trust model	✅	❌	❌	❌
Permission levels (SAFE → YOLO)	✅	❌	Partial	❌
Live execution waterfall profiler	✅	❌	❌	❌
Built-in cron scheduler	✅	❌	❌	❌
Parallel sessions & subagents	✅	❌	❌	Partial
Inline diff viewer	✅	✅	✅	✅
Session management + /undo	✅	❌	Partial	❌
Agent profiles	✅	❌	❌	Partial
Local-first / Ollama / BYOK	✅	✅	❌	❌
MCP support	✅	❌	Partial	✅
VS Code Extension	✅	❌	✅	✅

---

⏰ Cron Scheduler — AI That Works While You Sleep

No other AI coding agent has this. Open /cron inside Andromity, write your task, set a schedule — and the agent executes it autonomously on a timer while you're away.

# Example: auto-run test suite and fix failures every night at 2 AM
/cron  →  "run pytest, fix any failing tests, commit the fix"  →  0 2 * * *

Jobs persist in .andromity/crons.json per project. Use FULL or YOLO mode for fully unattended overnight runs. Wake up to commits already made.

---

🤖 Parallel Sessions & Subagents

Spawn background subagents for parallel workstreams without interrupting your main session. Example: while one subagent researches an unfamiliar library, another implements a feature, and you review the plan in the main session — all simultaneously.

Main session      → Plan & implement Feature A
Subagent 1        → Research the best auth library
Subagent 2        → Write unit tests for Feature B

Switch between all sessions with Ctrl+O. Every session has its own context, history, and file change log. /undo reverts only the current session's changes.

---

What's inside the terminal workspace

The VS Code extension and the terminal share the same agent core. The terminal workspace gives you the raw power.

Profiles. Switch what the agent is trying to do mid-session.

• builder — plans first, then implements
• coder — implements directly, no planning phase
• reviewer — read-only, produces findings
• planner — plans only, touches nothing

MCP support. Drop a mcp.json in your project. Tool schemas load on demand — keeps token use sane with 50+ tools connected.

Sessions. Everything is saved. /sessions or Ctrl+O to switch. /compact when context gets heavy. /undo to revert the last turn and all its file changes.

Headless / scripted runs.

andromity run "add error handling to auth.py"
andromity run "refactor this to async" --yes      # auto-approve everything
andromity run "review session.py" --dry-run       # see what it would do

Model-agnostic. LiteLLM under the hood. Anthropic, OpenAI, Gemini, Groq, OpenRouter, Ollama, NVIDIA NIM. Swap mid-session with Ctrl+L.

---

Privacy

Your code goes to one place: the LLM provider you configure. Not us.

• API keys live in ~/.andromity/config.toml — encrypted locally
• Sessions stored locally in ~/.andromity/sessions/
• Opt out of telemetry: export DO_NOT_TRACK=1

---

🏆 Verified Air-Gapped Benchmarking (SWE-bench Lite)

Andromity is evaluated under 100% strict socket-level airgap isolation (ANDROMITY_AIRGAP=1) with zero internet access, non-loopback TCP connection blocking, and sanitized git history to guarantee completely unimpeachable, contamination-free results.

Evaluating the full 300 instances on the official SWE-bench Docker testbed places Andromity in the Top 10 Globally on the SWE-bench Lite Leaderboard:

Benchmark Suite	Evaluated Tasks	Autonomous Patches	Tests Resolved	Resolve Rate (% of 300)	Airgap Guarantee	Global Standing
SWE-bench Lite	296	295 (98.3%)	150	50.00% (50.68% eval)	100% Offline Socket Blocked	Global Rank #8 🏆

Top Repository Resolve Rates:

• 📈 matplotlib/matplotlib: 72.7% (16 / 22)
• 🔭 astropy/astropy: 66.7% (4 / 6)
• 🔍 pylint-dev/pylint: 66.7% (4 / 6)
• 🧪 pytest-dev/pytest: 64.7% (11 / 17)
• 🧠 scikit-learn/scikit-learn: 56.5% (13 / 23)
• 🌐 django/django: 54.1% (60 / 111)
• 📚 sphinx-doc/sphinx: 50.0% (8 / 16)
• 🔢 sympy/sympy: 39.0% (30 / 77)

📖 Read the Creator & Engineering Case Study: Cutting the Internet Cord: How We Air-Gapped SWE-bench Lite All Docker logs, patch diffs, and reproduction commands are fully open and auditable in logs/run_evaluation/ and benchmark/.

---

🚀 #BuiltWithAndromity Showcase & Hackathons

Are you building an open-source project, university coursework, or commercial application using Andromity?

• Showcase Your Work: Tag your project or PR with #BuiltWithAndromity on X (Twitter) or drop it in the #showcase channel on Discord.
• Get Featured: Top community projects and contributions are spotlighted on agenticmarket.dev and receive official ecosystem contributor recognition and goodies.
• Community Hackathons: Stay tuned in Discord for global community hackathons benefiting open-source developers worldwide.

---

💬 Community & Discord

Join our growing community of autonomous AI developers, students, and engineers:

• Discord: Join the Andromity Community Discord for live discussions, local Ollama setups, prompt engineering, and MCP skill sharing.
• Skills & MCP Hub: Discover and publish community agent skills, custom prompts, and MCP tool servers on AgenticMarket.

⭐ Loved the Live Waterfall profiler or saved hours debugging? Consider giving Andromity a star on GitHub — it helps more developers discover 100% free, private, open-source AI tooling!

---

Star History

---

Changelog

See CHANGELOG.md for detailed release history and version notes.

---

Maintainer & Authors

Andromity is created and actively maintained by:

• Shekhar Pachlore (@shekharP1536) — Creator & Lead Maintainer (Core Architecture & Autonomous Runtimes)

---

Contributing

Open an issue or PR. Honest feedback and bug reports are more useful than feature requests right now.

See CONTRIBUTING.md for project layout and dev setup.

MIT — see LICENSE.