AlysisCode

<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/banner-dark.svg"> <img src="docs/assets/banner.svg" alt="Alysis Code — Everyone's Coding Agent" width="640"> </picture> </p> <p align="center"> An open-source coding agent for your terminal.<br> Bring your own model. Turn plans into reviewed, PR-ready code. </p> <p align="center"> <a href="https://alysiscode.com/">Website</a> · <a href="https://alysiscode.com/docs">Documentation</a> · <a href="docs/quickstart.md">Quickstart</a> · <a href="docs/CHANGELOG.md">Changelog</a> </p> <p align="center"> <a href="https://github.com/AlysisAi/AlysisCode/stargazers"><img src="https://img.shields.io/github/stars/AlysisAi/AlysisCode?style=flat&logo=github" alt="GitHub stars"></a> <a href="https://github.com/AlysisAi/AlysisCode/actions/workflows/ci.yml"><img src="https://github.com/AlysisAi/AlysisCode/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://pypi.org/project/alysis-code/"><img src="https://img.shields.io/pypi/v/alysis-code.svg" alt="PyPI version"></a> <a href="https://pypi.org/project/alysis-code/"><img src="https://img.shields.io/pypi/dm/alysis-code.svg" alt="PyPI downloads"></a> <a href="https://pypi.org/project/alysis-code/"><img src="https://img.shields.io/pypi/pyversions/alysis-code.svg" alt="Python versions"></a> <a href="https://github.com/AlysisAi/AlysisCode/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/alysis-code.svg" alt="License"></a> </p> <p align="center"> <a href="https://x.com/alysiscode">Follow on X</a> · <a href="https://github.com/sponsors/AlysisAi">Sponsor the project</a> </p> <p align="center"> <img src="docs/assets/demo.gif" alt="Alysis Code fixes a free-shipping bug and verifies the tests" width="960"> <br> _{A real CLI session fixing a failing test. Playback condensed.} </p> --- ## Get Started Alysis Code requires **Python 3.11+** and runs on macOS, Linux, and Windows. **1 — Install** On Windows, paste this into **PowerShell**: ```powershell irm https://raw.githubusercontent.com/AlysisAi/AlysisCode/main/scripts/install.ps1 | iex ``` On Linux, macOS, or inside a **WSL/Ubuntu terminal**: ```sh curl -LsSf https://raw.githubusercontent.com/AlysisAi/AlysisCode/main/scripts/install.sh | sh ``` The installers provision uv and Python 3.12 when needed. No existing Python or pipx is required. PowerShell can use `alysis` immediately; after the shell installer, follow its PATH instructions or open a new terminal. If you already use pipx, `pipx install alysis-code` also works; run `pipx ensurepath` and restart your terminal if the command is missing. Already installed? Run `alysis update` to get the latest release. **2 — Choose how to connect to a model** Pick one path. You can switch later with `/config` or by re-running `alysis-code setup`. *Path A — Your own API key or a local model (no Alysis account needed)* ```bash cd your-project alysis-code ``` The first run opens a guided setup wizard. Choose **Use an API key**, connect a provider (OpenAI, Anthropic, DeepSeek, Gemini, OpenRouter, and more), and pick your default model. To run fully offline, point Alysis Code at a local endpoint (Ollama, LM Studio, vLLM) from the `/config` picker, which lists every preset. Prefer to configure it by hand? ```bash export ALYSIS_API_KEY="YOUR_KEY" alysis config set base_url "https://api.openai.com/v1" alysis config set model "gpt-4.1-mini" ``` Have a ChatGPT subscription instead? Choose **Use an AI subscription** in the wizard, or run `alysis auth login openai-codex`. *Path B — Alysis account* ```sh alysis login ``` Approve the code in your browser to use your Alysis credits. No provider key and no cloud environment variables are needed. **3 — Start building** ```bash cd your-project alysis-code chat # interactive coding session alysis-code run "Fix the failing tests" # one-shot task ``` (`alysis` works too, as a short alias.) The `/config` picker lists every provider preset. Full walkthrough: [Quickstart guide](docs/quickstart.md). ## Alysis Code App Alysis Code App is powered by the open-source Alysis Code engine, bringing an agentic desktop experience to coding and broader everyday work. --- ## Why Alysis Code - **Easy to use** — a full coding agent behind a clean, convenient terminal interface that anyone can pick up and play with in minutes: slash commands, interactive pickers, and live status built in. - **Built for every developer** — from solo scripts to team servers and CI, the same agent fits every workflow. - **[Forge Mode](https://alysiscode.com/docs/concepts/tasks)** — plan-driven execution for larger work: plan, dispatch parallel workers, verify each task, ship PR-ready code. - **[Orchestrated subagents](https://alysiscode.com/docs/concepts/agents)** — isolated workers run in parallel, verification is pinned to their exact candidates, and changes apply only after host-side conflict checks. - **Free built-in web search** — model-independent `web_search` that works with any provider, at no extra cost. - **[Bring your own model](https://alysiscode.com/docs/config/models)** — OpenAI, Anthropic, DeepSeek, Qwen, Gemini, Mistral, Xiaomi MiMo, OpenRouter, xAI, and more — plus local endpoints (Ollama, LM Studio, vLLM) for fully offline use. - **[Deeply extensible](https://alysiscode.com/docs/concepts/plugins)** — skills, custom tools, MCP servers, hooks, subagents, and plugins, bundled in one declarative manifest. - **[Sandboxed by default](https://alysiscode.com/docs/safety/sandbox-modes)** — Docker or Bubblewrap isolation with an always-on denylist that refuses `rm -rf /`, `curl | sh`, and `sudo` — even in `fullaccess`. Shell and verification commands default to strict sandboxing. Verification can run outside that sandbox only when explicitly configured with `verify_sandbox.mode="off"` or `ALYSIS_VERIFY_SANDBOX_MODE=off`. ## How it compares A quick, good-faith snapshot based on each project's public README and docs (October 2026). "—" means we couldn't confirm it from their docs; corrections welcome via an issue. | | Alysis Code | [Claude Code](https://github.com/anthropics/claude-code) | [Aider](https://github.com/Aider-AI/aider) | [Codex CLI](https://github.com/openai/codex) | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | | --- | --- | --- | --- | --- | --- | | License | Apache-2.0 | Proprietary | Apache-2.0 | Apache-2.0 | Apache-2.0 | | Models | Any supported provider | Claude | Almost any LLM | OpenAI (ChatGPT sign-in or API key), plus local models | Gemini | | Local models | Yes (Ollama, LM Studio, vLLM) | — | Yes | Yes (Ollama, LM Studio) | — | | MCP servers | Yes | Yes | — | Yes | Yes | | Sandboxed shell | Yes, on by default (Docker / Bubblewrap) | Yes (sandboxed Bash tool) | — | Yes | Yes | | Editor integration | VS Code (pre-release), JetBrains (preview) | Yes | Yes | Yes (VS Code, Cursor, Windsurf) | Yes (VS Code companion, ACP integrations) | References: [Codex CLI local-provider options](https://learn.chatgpt.com/docs/developer-commands?surface=cli) · [Gemini CLI editor integrations](https://github.com/google-gemini/gemini-cli/blob/main/docs/ide-integration/index.md). ## Permissions & Personas Two layers control what the agent may do — one enforces, one focuses. **Permissions** are the enforcement layer. Choose one per command with `--mode`, select the next message's level in chat with `/permissions` or **Shift+Tab**, or set a default with `alysis-code config set default_mode <mode>`. A selection takes effect when the next user message starts; it does not change a turn already running: | Mode | Behavior | | --- | --- | | `readonly` | Inspection plus top-level read-only delegation — no file writes, shell, MCP, candidate apply/discard, or nested delegation. | | `review` | The safe default — previews and asks before every write and shell command. | | `auto` | Applies routine edits with fewer prompts; dangerous operations stay blocked. | | `fullaccess` | No mode-level prompts for trusted workspaces — the denylist and audit log stay active. | **Personas** are working postures layered on top. Switch with `/persona`, or cycle with **Tab** in the TUI: | Persona | Posture | | --- | --- | | `code` | Implementation — the default, full coding workflow. | | `architect` | Planning and design — may write markdown documents only. | | `ask` | Read-only questions and codebase exploration. | | `debug` | Reproduce the failure first, then fix minimally and rerun the reproduction. | A persona is a convention, never a permission: it can keep or lower your execution mode, but can never raise it. Define your own in `.alysis_personas/*.md`. [Learn more](https://alysiscode.com/docs/concepts/personas) Use `/persona architect` for planning in chat, or `/forge` for a plan-driven execution workflow. The former chat `/plan` commands have been removed; Forge retains its plan views and editor. Persona changes made during a running turn apply after that turn finishes. ## Project Links - [Website](https://alysiscode.com/) - [Documentation](https://alysiscode.com/docs) — also mirrored in [docs/](docs/README.md) - [Changelog](docs/CHANGELOG.md) - [Contributing](.github/CONTRIBUTING.md) — local setup and PR expectations - [Security policy](.github/SECURITY.md) — report vulnerabilities privately, never through public issues ## License Apache-2.0. You're free to use, modify, and distribute this code, including commercially, as long as you keep the attribution and license notices. See [LICENSE](LICENSE) and [NOTICE](NOTICE). The shared editor sidebar includes MIT-licensed adaptations from Kilo Code/OpenCode; retain its [third-party notices](extensions/shared-ui/THIRD_PARTY_NOTICES.txt). ## FAQ <details> <summary><b>Where did Alysis Code come from?</b></summary> Alysis Code is not a fork. The agent runtime, Forge orchestration, subagent system, terminal interface, and sandbox layer were designed and built from zero by the Alysis AI team. </details> <details> <summary><b>Is Alysis Code really open source?</b></summary> Yes. The entire CLI is Apache-2.0 licensed. Bring your own API key from any supported provider, or run fully offline against a local endpoint — nothing in the agent requires a paid account. </details> More questions? See the [full FAQ](https://alysiscode.com/docs/faq). --- **Join the community** — [X](https://x.com/alysiscode) | [GitHub Issues](https://github.com/AlysisAi/AlysisCode/issues) ## Editor integrations [VS Code](extensions/vscode-alysis/README.md) uses the shared Alysis sidebar and Python IDE bridge. [JetBrains](extensions/jetbrains-alysis/README.md) is a development preview with a smaller feature set. The VS Code Marketplace pre-release is pending production signing and acceptance; see the [IDE release status](docs/vscode-marketplace-launch.md) before installing component packages.