New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See CONTRIBUTING.md.

Elyra is a terminal-first AI coding agent that adapts to your workflows instead of dictating them. Seven built-in tools (read, edit, write, bash, grep, find, ls), a growing ecosystem of extensions, and a small core that stays out of your way.

What makes it different:

• /goal — set a completion condition and the agent keeps working until it passes. No manual "continue."
• /rewind — roll back both conversation and files to any previous point with git-based checkpoints.
• Smart read — large files return structural outlines instead of raw dumps. Hash-annotated lines for precise edits.
• Post-edit diagnostics — the edit tool runs tsc after each change and reports errors immediately.
• /btw — parallel side conversations that don't touch the main context.
• /update — update and restart without leaving the session.
• Workflows — code-orchestrated pipelines where code handles control flow and the LLM handles judgment.

Extend with TypeScript Extensions, Skills, Prompt Templates, and Themes. Share via npm or git as Elyra Packages.

Four modes: interactive, print/JSON, RPC for process integration, and an SDK for embedding.

Share your OSS coding agent sessions

If you use elyra for open source work, please share your coding agent sessions.

Public OSS session data helps improve models, prompts, tools, and evaluations using real development workflows.

Table of Contents

• Quick Start
• Providers & Models
• Interactive Mode
  • Editor
  • Commands
  • Keyboard Shortcuts
  • Message Queue
• Sessions
  • Branching
  • Compaction
• Settings
• Context Files
• Customization
  • Prompt Templates
  • Skills
  • Extensions
  • Themes Elyra Packages
• Programmatic Usage
• Philosophy
• CLI Reference

Quick Start

Install with npm:

npm install -g @elyracode/coding-agent

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
elyra

Or use your existing subscription:

elyra
/login  # Then select provider

Then just talk to elyra. By default, elyra gives the model four tools: read, write, edit, and bash. The model uses these to fulfill your requests. Add capabilities via skills, prompt templates, extensions, or elyra packages.

Platform notes: Windows | Termux (Android) | tmux | Terminal setup | Shell aliases

Providers & Models

For each built-in provider, elyra maintains a list of tool-capable models, updated with every release. Authenticate via subscription (/login) or API key, then select any model from that provider via /model (or Ctrl+L).

Subscriptions:

• Anthropic Claude Pro/Max
• OpenAI ChatGPT Plus/Pro (Codex)
• GitHub Copilot

API keys:

• Anthropic
• OpenAI
• Azure OpenAI
• DeepSeek
• Google Gemini
• Google Vertex
• Amazon Bedrock
• Mistral
• Groq
• Cerebras
• Cloudflare AI Gateway
• Cloudflare Workers AI
• xAI
• OpenRouter
• Vercel AI Gateway
• ZAI
• OpenCode Zen
• OpenCode Go
• Hugging Face
• Fireworks
• Together AI
• Kimi For Coding
• MiniMax
• Xiaomi MiMo
• Xiaomi MiMo Token Plan (China)
• Xiaomi MiMo Token Plan (Amsterdam)
• Xiaomi MiMo Token Plan (Singapore)

See docs/providers.md for detailed setup instructions.

Custom providers & models: Add providers via ~/.elyra/agent/models.json if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See docs/models.md and docs/custom-provider.md.

Interactive Mode

The interface from top to bottom:

• Startup header - Shows shortcuts (/hotkeys for all), loaded AGENTS.md files, prompt templates, skills, and extensions
• Messages - Your messages, assistant responses, tool calls and results, notifications, errors, and extension UI
• Editor - Where you type; border color indicates thinking level
• Footer - Working directory, session name, total token/cache usage, cost, context usage, current model

The editor can be temporarily replaced by other UI, like built-in /settings or custom UI from extensions (e.g., a Q&A tool that lets the user answer model questions in a structured format). Extensions can also replace the editor, add widgets above/below it, a status line, custom footer, or overlays.

Editor

| Feature | How | |---------|-----| | File reference | Type @ to fuzzy-search project files | | Path completion | Tab to complete paths | | Multi-line | Shift+Enter (or Ctrl+Enter on Windows Terminal) | | Images | Ctrl+V to paste (Alt+V on Windows), or drag onto terminal | | Bash commands | !command runs and sends output to LLM, !!command runs without sending |

Standard editing keybindings for delete word, undo, etc. See docs/keybindings.md.

Commands

Type / in the editor to trigger commands. Extensions can register custom commands, skills are available as /skill:name, and prompt templates expand via /templatename.

| Command | Description | |---------|-------------| | /login, /logout | OAuth authentication | | /model | Switch models | | /scoped-models | Enable/disable models for Ctrl+P cycling | | /settings | Thinking level, theme, message delivery, transport | | /resume | Pick from previous sessions | | /new | Start a new session | | /name <name> | Set session display name | | /session | Show session info (file, ID, messages, tokens, cost) | | /tree | Jump to any point in the session and continue from there | | /rewind | Rewind session and file state to a previous checkpoint | | /fork | Create a new session from a previous user message | | /clone | Duplicate the current active branch into a new session | | /goal <cmd> | Agent keeps working until the command exits with code 0 | | /compact [prompt] | Manually compact context, optional custom instructions | | /copy | Copy last assistant message to clipboard | | /export [file] | Export session to HTML file | | /share | Upload as private GitHub gist with shareable HTML link | | /reload | Reload keybindings, extensions, skills, prompts, and context files | | /update | Update Elyra to the latest version and restart | | /hotkeys | Show all keyboard shortcuts | | /changelog | Display version history | | /quit | Quit elyra |

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.elyra/agent/keybindings.json. See docs/keybindings.md.

Commonly used:

| Key | Action | |-----|--------| | Ctrl+C | Clear editor | | Ctrl+C twice | Quit | | Escape | Cancel/abort | | Escape twice | Open /tree | | Ctrl+L | Open model selector | | Ctrl+P / Shift+Ctrl+P | Cycle scoped models forward/backward | | Shift+Tab | Cycle thinking level | | Ctrl+O | Collapse/expand tool output | | Ctrl+T | Collapse/expand thinking blocks |

Message Queue

Submit messages while the agent is working:

• Enter queues a steering message, delivered after the current assistant turn finishes executing its tool calls
• Alt+Enter queues a follow-up message, delivered only after the agent finishes all work
• Escape aborts and restores queued messages to editor
• Alt+Up retrieves queued messages back to editor

On Windows Terminal, Alt+Enter is fullscreen by default. Remap it in docs/terminal-setup.md so elyra can receive the follow-up shortcut.

Configure delivery in settings: steeringMode and followUpMode can be "one-at-a-time" (default, waits for response) or "all" (delivers all queued at once). transport selects provider transport preference ("sse", "websocket", or "auto") for providers that support multiple transports.

Sessions

Sessions are stored as JSONL files with a tree structure. Each entry has an id and parentId, enabling in-place branching without creating new files. See docs/session-format.md for file format.

Management

Sessions auto-save to ~/.elyra/agent/sessions/ organized by working directory.

elyra -c                  # Continue most recent session
elyra -r                  # Browse and select from past sessions
elyra --no-session        # Ephemeral mode (don't save)
elyra --session <path|id> # Use specific session file or ID
elyra --fork <path|id>    # Fork specific session file or ID into a new session

Use /session in interactive mode to see the current session ID before reusing it with --session <id> or --fork <id>.

Branching

/tree - Navigate the session tree in-place. Select any previous point, continue from there, and switch between branches. All history preserved in a single file.

• Search by typing, fold/unfold and jump between branches with Ctrl+←/Ctrl+→ or Alt+←/Alt+→, page with ←/→
• Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all
• Press Shift+L to label entries as bookmarks and Shift+T to toggle label timestamps

/fork - Create a new session file from a previous user message on the active branch. Opens a selector, copies the active path up to that point, and places the selected prompt in the editor for modification.

/clone - Duplicate the current active branch into a new session file at the current position. The new session keeps the full active-path history and opens with an empty editor.

/rewind - Roll back both conversation and file state to a previous point. Git checkpoints are created automatically before each agent turn. Select a checkpoint, and Elyra navigates the session tree and restores tracked files via git.

/goal <command> - Set a completion condition. After each agent turn, the command runs. Exit 0 = goal met, agent stops. Non-zero = output sent back to the agent, work continues automatically. Example: /goal npm run check.

--fork <path|id> - Fork an existing session file or partial session UUID directly from the CLI. This copies the full source session into a new session file in the current project.

Compaction

Long sessions can exhaust context windows. Compaction summarizes older messages while keeping recent ones.

Manual: /compact or /compact <custom instructions>

Automatic: Enabled by default. Triggers on context overflow (recovers and retries) or when approaching the limit (proactive). Configure via /settings or settings.json.

Compaction is lossy. The full history remains in the JSONL file; use /tree to revisit. Customize compaction behavior via extensions. See docs/compaction.md for internals.

Settings

Use /settings to modify common options, or edit JSON files directly:

| Location | Scope | |----------|-------| | ~/.elyra/agent/settings.json | Global (all projects) | | .elyra/settings.json | Project (overrides global) |

See docs/settings.md for all options.

Telemetry and update checks

Elyra has two separate startup features:

• Update check: fetches https://elyracode.app/api/latest-version to check whether a newer Elyra version exists. Disable it with ELYRA_SKIP_VERSION_CHECK=1. Disabling update checks only turns off this check.
• Install/update telemetry: after first install or a changelog-detected update, sends an anonymous version ping to https://elyracode.app/api/report-install. Opt out by setting enableInstallTelemetry to false in settings.json, or by setting ELYRA_TELEMETRY=0. This does not disable update checks; Elyra may still contact elyracode.app for the latest version unless update checks are disabled or offline mode is enabled.

Use --offline or ELYRA_OFFLINE=1 to disable all startup network operations described here, including update checks, package update checks, and install/update telemetry.

Context Files

Elyra loads AGENTS.md (or CLAUDE.md) at startup from:

• ~/.elyra/agent/AGENTS.md (global)
• Parent directories (walking up from cwd)
• Current directory

Use for project instructions, conventions, common commands. All matching files are concatenated.

Disable context file loading with --no-context-files (or -nc).

System Prompt

Replace the default system prompt with .elyra/SYSTEM.md (project) or ~/.elyra/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.

Customization

Prompt Templates

Reusable prompts as Markdown files. Type /name to expand.

<!-- ~/.elyra/agent/prompts/review.md -->
Review this code for bugs, security issues, and performance problems.
Focus on: {{focus}}

Place in ~/.elyra/agent/prompts/, .elyra/prompts/, or a elyra package to share with others. See docs/prompt-templates.md.

Skills

On-demand capability packages following the Agent Skills standard. Invoke via /skill:name or let the agent load them automatically.

<!-- ~/.elyra/agent/skills/my-skill/SKILL.md -->
# My Skill
Use this skill when the user asks about X.

## Steps
1. Do this
2. Then that

Place in ~/.elyra/agent/skills/, ~/.agents/skills/, .elyra/skills/, or .agents/skills/ (from cwd up through parent directories) or a elyra package to share with others. See docs/skills.md.

Extensions

TypeScript modules that extend elyra with custom tools, commands, keyboard shortcuts, event handlers, and UI components.

export default function (elyra: ExtensionAPI) {
  elyra.registerTool({ name: "deploy", ... });
  elyra.registerCommand("stats", { ... });
  elyra.on("tool_call", async (event, ctx) => { ... });
}

The default export can also be async. elyra waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling elyra.registerProvider().

What's possible:

• Custom tools (or replace built-in tools entirely)
• Sub-agents and plan mode
• Custom compaction and summarization
• Permission gates and path protection
• Custom editors and UI components
• Status lines, headers, footers
• Git checkpointing and auto-commit
• SSH and sandbox execution
• MCP server integration
• Make elyra look like Claude Code
• Games while waiting (yes, Doom runs)
• ...anything you can dream up

Place in ~/.elyra/agent/extensions/, .elyra/extensions/, or a elyra package to share with others. See docs/extensions.md and examples/extensions/.

Themes

Built-in: dark, light. Themes hot-reload: modify the active theme file and elyra immediately applies changes.

Place in ~/.elyra/agent/themes/, .elyra/themes/, or a elyra package to share with others. See docs/themes.md.

Elyra Packages

Bundle and share extensions, skills, prompts, and themes via npm or git. Find packages on npmjs.com or Discord.

Security: Elyra packages run with full system access. Extensions execute arbitrary code, and skills can instruct the model to perform any action including running executables. Review source code before installing third-party packages.

elyra install npm:@foo/elyra-tools
elyra install npm:@foo/[email protected]      # pinned version
elyra install git:github.com/user/repo
elyra install git:github.com/user/repo@v1  # tag or commit
elyra install git:[email protected]:user/repo
elyra install git:[email protected]:user/repo@v1  # tag or commit
elyra install https://github.com/user/repo
elyra install https://github.com/user/repo@v1      # tag or commit
elyra install ssh://[email protected]/user/repo
elyra install ssh://[email protected]/user/repo@v1    # tag or commit
elyra remove npm:@foo/elyra-tools
elyra uninstall npm:@foo/elyra-tools          # alias for remove
elyra list
elyra update                               # update elyra and packages (skips pinned packages)
elyra update --extensions                  # update packages only
elyra update --self                        # update elyra only
elyra update --self --force                # reinstall elyra even if current
elyra update npm:@foo/elyra-tools             # update one package
elyra config                               # enable/disable extensions, skills, prompts, themes

Packages install to ~/.elyra/agent/git/ (git) or global npm. Use -l for project-local installs (.elyra/git/, .elyra/npm/). Git packages install dependencies with npm install --omit=dev by default, so runtime deps must be listed under dependencies; when npmCommand is configured, git packages use plain install for compatibility with wrappers. If you use a Node version manager and want package installs to reuse a stable npm context, set npmCommand in settings.json, for example ["mise", "exec", "node@20", "--", "npm"].

Create a package by adding a elyra key to package.json:

{
  "name": "my-elyra-package",
  "keywords": ["elyra-package"],
  "elyra": {
    "extensions": ["./extensions"],
    "skills": ["./skills"],
    "prompts": ["./prompts"],
    "themes": ["./themes"]
  }
}

Without a elyra manifest, elyra auto-discovers from conventional directories (extensions/, skills/, prompts/, themes/).

See docs/packages.md.

Programmatic Usage

SDK

import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "@elyracode/coding-agent";

const authStorage = AuthStorage.create();
const modelRegistry = ModelRegistry.create(authStorage);
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  authStorage,
  modelRegistry,
});

await session.prompt("What files are in the current directory?");

For advanced multi-session runtime replacement, use createAgentSessionRuntime() and AgentSessionRuntime.

See docs/sdk.md and examples/sdk/.

RPC Mode

For non-Node.js integrations, use RPC mode over stdin/stdout:

elyra --mode rpc

RPC mode uses strict LF-delimited JSONL framing. Clients must split records on \n only. Do not use generic line readers like Node readline, which also split on Unicode separators inside JSON payloads.

See docs/rpc.md for the protocol.

Philosophy

Elyra keeps the core small and pushes workflow-specific behavior into extensions. The built-in tools handle reading, writing, editing, and searching. Everything else — Laravel support, SEO tools, LSP, workflows, side conversations — ships as installable extensions that you opt into.

Use code for what code is good at. Use models for what models are good at. The /goal command is a shell check, not an LLM judgment. The /workflow engine is a JSON runner, not an AI planner. Prompt caching is a message reorder, not a feature flag. The best optimizations don't involve the model at all.

No permission popups. The agent runs tools directly. If you need gating, build it with extensions or run in a container.

No built-in to-dos. They confuse models. Use a TODO.md file, or build your own with extensions.

See elyracode.com/blog for design rationale and release notes.

CLI Reference

elyra [options] [@files...] [messages...]

Package Commands

elyra install <source> [-l]     # Install package, -l for project-local
elyra remove <source> [-l]      # Remove package
elyra uninstall <source> [-l]   # Alias for remove
elyra update [source|self|elyra]   # Update elyra and packages (skips pinned packages)
elyra update --extensions       # Update packages only
elyra update --self             # Update elyra only
elyra update --self --force     # Reinstall elyra even if current
elyra update --extension <src>  # Update one package
elyra list                      # List installed packages
elyra config                    # Enable/disable package resources

Modes

| Flag | Description | |------|-------------| | (default) | Interactive mode | | -p, --print | Print response and exit | | --mode json | Output all events as JSON lines (see docs/json.md) | | --mode rpc | RPC mode for process integration (see docs/rpc.md) | | --export <in> [out] | Export session to HTML |

In print mode, elyra also reads piped stdin and merges it into the initial prompt:

cat README.md | elyra -p "Summarize this text"

Model Options

| Option | Description | |--------|-------------| | --provider <name> | Provider (anthropic, openai, google, etc.) | | --model <pattern> | Model pattern or ID (supports provider/id and optional :<thinking>) | | --api-key <key> | API key (overrides env vars) | | --thinking <level> | off, minimal, low, medium, high, xhigh | | --models <patterns> | Comma-separated patterns for Ctrl+P cycling | | --list-models [search] | List available models |

Session Options

| Option | Description | |--------|-------------| | -c, --continue | Continue most recent session | | -r, --resume | Browse and select session | | --session <path\|id> | Use specific session file or partial UUID | | --fork <path\|id> | Fork specific session file or partial UUID into a new session | | --session-dir <dir> | Custom session storage directory | | --no-session | Ephemeral mode (don't save) |

Tool Options

| Option | Description | |--------|-------------| | --tools <list>, -t <list> | Allowlist specific tool names across built-in, extension, and custom tools | | --no-builtin-tools, -nbt | Disable built-in tools by default but keep extension/custom tools enabled | | --no-tools, -nt | Disable all tools by default |

Available built-in tools: read, bash, edit, write, grep, find, ls

Resource Options

| Option | Description | |--------|-------------| | -e, --extension <source> | Load extension from path, npm, or git (repeatable) | | --no-extensions | Disable extension discovery | | --skill <path> | Load skill (repeatable) | | --no-skills | Disable skill discovery | | --prompt-template <path> | Load prompt template (repeatable) | | --no-prompt-templates | Disable prompt template discovery | | --theme <path> | Load theme (repeatable) | | --no-themes | Disable theme discovery | | --no-context-files, -nc | Disable AGENTS.md and CLAUDE.md context file discovery |

Combine --no-* with explicit flags to load exactly what you need, ignoring settings.json (e.g., --no-extensions -e ./my-ext.ts).

Other Options

| Option | Description | |--------|-------------| | --system-prompt <text> | Replace default prompt (context files and skills still appended) | | --append-system-prompt <text> | Append to system prompt | | --verbose | Force verbose startup | | -h, --help | Show help | | -v, --version | Show version |

File Arguments

Prefix files with @ to include in the message:

elyra @prompt.md "Answer this"
elyra -p @screenshot.png "What's in this image?"
elyra @code.ts @test.ts "Review these files"

Examples

# Interactive with initial prompt
elyra "List all .ts files in src/"

# Non-interactive
elyra -p "Summarize this codebase"

# Non-interactive with piped stdin
cat README.md | elyra -p "Summarize this text"

# Different model
elyra --provider openai --model gpt-4o "Help me refactor"

# Model with provider prefix (no --provider needed)
elyra --model openai/gpt-4o "Help me refactor"

# Model with thinking level shorthand
elyra --model sonnet:high "Solve this complex problem"

# Limit model cycling
elyra --models "claude-*,gpt-4o"

# Read-only mode
elyra --tools read,grep,find,ls -p "Review the code"

# High thinking level
elyra --thinking high "Solve this complex problem"

Environment Variables

| Variable | Description | |----------|-------------| | ELYRA_CODING_AGENT_DIR | Override config directory (default: ~/.elyra/agent) | | ELYRA_CODING_AGENT_SESSION_DIR | Override session storage directory (overridden by --session-dir) | | ELYRA_PACKAGE_DIR | Override package directory (useful for Nix/Guix where store paths tokenize poorly) | | ELYRA_OFFLINE | Disable startup network operations, including update checks, package update checks, and install/update telemetry | | ELYRA_SKIP_VERSION_CHECK | Skip the Elyra version update check at startup. This prevents the elyracode.app latest-version request | | ELYRA_TELEMETRY | Override install/update telemetry. Use 1/true/yes to enable or 0/false/no to disable. This does not disable update checks | | ELYRA_CACHE_RETENTION | Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h) | | VISUAL, EDITOR | External editor for Ctrl+G |

Contributing & Development

See CONTRIBUTING.md for guidelines and docs/development.md for setup, forking, and debugging.

License

MIT

See Also

• @elyracode/ai: Core LLM toolkit
• @elyracode/agent-core: Agent framework
• @elyracode/tui: Terminal UI components