Skip to content

coding-agent

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

coding-agent

README.md

Athena

npm

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

Athena is a codebase-intelligent terminal coding agent. Built-in CodeGraph integration gives the model structural repository context, built-in web search adds current external knowledge, and Athena's gated development workflow keeps substantial changes reviewable from product intent through verified vertical slices.

Adapt Athena to your workflows, not the other way around. Extend it with TypeScript Extensions, Skills, Prompt Templates, and Themes. Put those resources in Athena Packages and share them through npm or git without forking Athena internals.

Athena runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps.

Table of Contents

Quick Start

npm install -g --ignore-scripts @kushalbanda/athena

--ignore-scripts disables dependency lifecycle scripts during install. Athena does not require install scripts for normal npm installs.

Installer alternatives:

# curl (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/kushalBanda/Athena/main/install.sh | sh

# Homebrew (macOS/Linux)
brew tap kushalBanda/Athena https://github.com/kushalBanda/Athena
brew install athena

Authenticate with an API key:

export ANTHROPIC_API_KEY=sk-ant-...
athena

Or use your existing subscription:

athena
/login  # Then select provider

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

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

Providers & Models

For each built-in provider, athena maintains a list of tool-capable models. Configured provider catalogs refresh automatically; run athena update --models to force an immediate refresh. 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
  • Ant Ling
  • OpenAI
  • Azure OpenAI
  • DeepSeek
  • NVIDIA NIM
  • Google Gemini
  • Google Vertex
  • Amazon Bedrock
  • Mistral
  • Groq
  • Cerebras
  • Cloudflare AI Gateway
  • Cloudflare Workers AI
  • xAI
  • OpenRouter
  • Vercel AI Gateway
  • ZAI Coding Plan (Global)
  • ZAI Coding Plan (China)
  • OpenCode Zen
  • OpenCode Go
  • Hugging Face
  • Fireworks
  • Together AI
  • Baseten
  • Kimi For Coding
  • MiniMax
  • Xiaomi MiMo
  • Xiaomi MiMo Token Plan (China)
  • Xiaomi MiMo Token Plan (Amsterdam)
  • Xiaomi MiMo Token Plan (Singapore)

Athena also supports the llama.cpp router server. Configure it with /login llama.cpp, manage downloads and loaded models with /llama, then select a loaded model with /model. See docs/llama-cpp.md for setup and usage.

See docs/providers.md for other provider setup instructions.

Custom providers & models: Add providers via ~/.athena/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

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 (↑ input, ↓ output, R cache read, W cache write, CH latest cache hit rate), cost, context usage, current model. Totals include assistant responses, usage reported by tools, and summary generation.

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)
External editor Ctrl+G opens externalEditor, $VISUAL, $EDITOR, Notepad on Windows, or nano elsewhere
Clipboard Ctrl+V to paste an image or text (Alt+V on Windows), or drag images 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 Manage provider credentials
/llama Download, load, and unload llama.cpp router models
/model Switch models
/scoped-models Enable/disable models for Ctrl+P cycling
/settings Thinking level, theme, message delivery, transport
/resume Pick from previous sessions
/clear 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
/trust Save project trust decision for future sessions (restart required)
/fork Create a new session from a previous user message
/clone Duplicate the current active branch into a new session
/compact [prompt] Manually compact context, optional custom instructions
/copy Copy last assistant message to clipboard
/export [file] Export session to HTML or JSONL file
/import <file> Import and resume a session from a JSONL file
/share Upload as private GitHub gist with shareable HTML link
/reload Reload keybindings, extensions, skills, prompts, themes, and context files
/hotkeys Show all keyboard shortcuts
/changelog Display version history
/quit Quit athena

Keyboard Shortcuts

See /hotkeys for the full list. Customize via ~/.athena/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
Ctrl+X Copy the last assistant message

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 athena 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 ~/.athena/agent/sessions/ organized by working directory.

athena -c                  # Continue most recent session
athena -r                  # Browse and select from past sessions
athena --no-session        # Ephemeral mode (don't save)
athena --name "my task"    # Set session display name at startup
athena --session <path|id> # Use specific session file or ID
athena --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.

Tree View

  • 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 Ctrl+X to copy the selected message
  • 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.

--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
~/.athena/agent/settings.json Global (all projects)
.athena/settings.json Project (overrides global)

See docs/settings.md for all options.

Project Trust

On interactive startup, athena asks before trusting a project folder that contains project-local settings, resources, or project .agents/skills and has no saved decision for the folder or a parent folder in ~/.athena/agent/trust.json. Trusting a project allows athena to load .athena/settings.json and .athena resources, install missing project packages, and execute project extensions.

Before the trust decision, athena loads only context files, user/global extensions, and CLI -e extensions so they can handle the project_trust event. Project-local extensions, project package-managed extensions, and project settings are loaded only after the project is trusted. This split also applies when switching to a session from a different cwd whose trust has not been resolved in the current process.

Non-interactive modes (-p, --mode json, and --mode rpc) do not show a trust prompt. Without an applicable saved trust decision, they use defaultProjectTrust from global settings: ask (default) and never ignore those project resources, while always trusts them. Pass --approve/-a or --no-approve/-na to override project trust for one run.

If no extension or saved decision applies, defaultProjectTrust controls the fallback behavior. Set it to "ask", "always", or "never" in ~/.athena/agent/settings.json, or change it with /settings.

athena config and package commands use the same project trust flow, except athena update never prompts. Pass --approve to trust project-local settings for one command or --no-approve to ignore them.

Use /trust in interactive mode to save a project trust decision for future sessions, including trust for the immediate parent folder. It writes ~/.athena/agent/trust.json only; the current session is not reloaded, so restart athena for changes to take effect.

Context Files

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

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

If a directory contains AGENTS.override.md, Athena loads it instead of AGENTS.md or CLAUDE.md from that directory. Context files from other directories are still concatenated.

Use for project instructions (AGENTS.md/CLAUDE.md), 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 .athena/SYSTEM.md (project) or ~/.athena/agent/SYSTEM.md (global). Append without replacing via APPEND_SYSTEM.md.

Development Workflow

Athena's default prompt applies a four-gate workflow to substantial development tasks: new features, multi-file changes, endpoints, schemas, screens, architecture changes, or work likely to create a large diff.

  1. Product : Define the user problem, measurable success, user-facing outcome, and interactions before choosing implementation details.
  2. Architecture : Inspect the repository first, use CodeGraph when available, and record affected modules, interfaces, data, external systems, end-to-end flow, and blast radius.
  3. Program Design : Agree on files, types, method signatures, call paths, test cases, and least-confident decisions before implementation bodies exist.
  4. Vertical Slices : Approve a slice plan, build a thin end-to-end tracer bullet, then add one testable capability per slice.

Each gate requires approval. Athena records durable state in docs/plans/<feature-slug>/:

00-status.md
01-product.md
mockups/              # UI work only
02-architecture.md
03-program-design.md
04-slices.md

Athena updates status after each approval and completed slice. Fresh sessions can resume from repository state instead of reconstructing decisions from chat history. Later discoveries reopen any invalidated gate.

Narrow fixes, renames, copy or style changes, small configuration edits, throwaway prototypes, and explicit fast-execution requests skip the workflow. When scope is unclear, Athena asks once which path to use.

Customization

Prompt Templates

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

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

Place in ~/.athena/agent/prompts/ or an Athena 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.

<!-- ~/.athena/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 ~/.athena/agent/skills/, ~/.agents/skills/, or .agents/skills/ (from cwd up through parent directories) or an Athena package to share with others. See docs/skills.md.

Extensions

Doom Extension

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

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

The default export can also be async. athena waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling athena.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 athena look like Claude Code
  • Games while waiting (yes, Doom runs)
  • ...anything you can dream up

Place in ~/.athena/agent/extensions/ or an Athena package to share with others. See docs/extensions.md and examples/extensions/.

MCP

Athena includes an MCP client for stdio, HTTP, and SSE servers. HTTP servers can use bearer-token environment variables or OAuth. Use /mcp to inspect servers, enable or disable built-ins, and authenticate configured servers.

CodeGraph is Athena's built-in MCP server. When its optional package is installed, Athena starts it automatically and exposes its structural code tools to the model. Set ATHENA_CODEGRAPH=off to disable automatic discovery. User-configured MCP servers can be added through mcpServers settings.

Themes

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

Place in ~/.athena/agent/themes/ or an Athena package to share with others. See docs/themes.md.

Athena Packages

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

Security: Athena 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.

athena install npm:@foo/athena-tools
athena install npm:@foo/athena-tools@1.2.3      # pinned version
athena install git:github.com/user/repo
athena install git:github.com/user/repo@v1  # tag or commit
athena install git:git@github.com:user/repo
athena install git:git@github.com:user/repo@v1  # tag or commit
athena install https://github.com/user/repo
athena install https://github.com/user/repo@v1      # tag or commit
athena install ssh://git@github.com/user/repo
athena install ssh://git@github.com/user/repo@v1    # tag or commit
athena remove npm:@foo/athena-tools
athena uninstall npm:@foo/athena-tools          # alias for remove
athena list
athena update                               # update athena only
athena update --all                         # update athena and packages
athena update --extensions                  # update packages only
athena update --models                      # refresh model catalogs only
athena update --self                        # update athena only
athena update --self --force                # reinstall athena even if current
athena update npm:@foo/athena-tools         # update one package
athena config                               # enable/disable extensions, skills, prompts, themes

Packages install to ~/.athena/agent/git/ (git) or ~/.athena/agent/npm/ (npm). Use -l for project-local installs (.athena/git/, .athena/npm/). Git @ref values are pinned tags or commits; pinned packages are skipped by athena update --extensions and athena update --all, so use athena install git:host/user/repo@new-ref to move an existing package to a new ref. 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 an athena key to package.json:

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

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

See docs/packages.md.

Programmatic Usage

SDK

import { createAgentSession, ModelRuntime, SessionManager } from "@kushalbanda/athena";

const modelRuntime = await ModelRuntime.create();
const { session } = await createAgentSession({
  sessionManager: SessionManager.inMemory(),
  modelRuntime,
});

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:

athena --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

Athena is aggressively extensible so it doesn't have to dictate your workflow. Features that other tools bake in can be built with extensions, skills, or installed from third-party Athena packages. This keeps the core minimal while letting you shape Athena to fit how you work.

CodeGraph-first, MCP-open. Athena automatically discovers its built-in CodeGraph server and can connect to custom stdio, HTTP, and SSE MCP servers. Skills and ordinary CLI tools remain useful when a full MCP integration is unnecessary.

No sub-agents. There's many ways to do this. Spawn athena instances via tmux, or build your own with extensions, or install a package that does it your way.

No permission popups. Run in a container, or build your own confirmation flow with extensions inline with your environment and security requirements.

No plan mode. Write plans to files, or build it with extensions, or install a package.

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

No background bash. Use tmux. Full observability, direct interaction.

CLI Reference

athena [options] [@files...] [messages...]

Package Commands

athena install <source> [-l]     # Install package, -l for project-local
athena remove <source> [-l]      # Remove package
athena uninstall <source> [-l]   # Alias for remove
athena update [source|self|athena]   # Update athena only, or one package source
athena update --all              # Update athena and packages
athena update --extensions       # Update packages only
athena update --models           # Refresh model catalogs only
athena update --self             # Update athena only
athena update --self --force     # Reinstall athena even if current
athena update --extension <src>  # Update one package
athena list                      # List installed packages
athena config                    # Enable/disable package resources

athena config and project package commands accept --approve/--no-approve to trust or ignore project-local settings for one command. athena update never prompts for project trust.

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, athena also reads piped stdin and merges it into the initial prompt:

cat README.md | athena -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, max
--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)
--name <name>, -n <name> Set session display name at startup

Tool Options

Option Description
--tools <list>, -t <list> Allowlist specific tool names across built-in, extension, and custom tools
--exclude-tools <list>, -xt <list> Disable 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, websearch

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
--tui-mode <mode> TUI mode: regular (default) or experimental fullscreen
--use-theme <name[/name]> Set the initial interactive theme for this run without changing settings
--verbose Force verbose startup
-a, --approve Trust project-local files for this run
-na, --no-approve Ignore project-local files for this run
-h, --help Show help
-v, --version Show version

File Arguments

Prefix files with @ to include in the message:

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

Examples

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

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

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

# Named one-shot session
athena --name "release audit" -p "Audit this repository"

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

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

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

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

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

# Disable one extension or built-in tool while keeping the rest available
athena --exclude-tools ask_question

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

Environment Variables

Variable Description
AI_AGENT Set to athena by the CLI and RPC entry points so generic tooling can attribute child processes to Athena
ATHENA_CODING_AGENT Set to true by the CLI and RPC entry points so child processes can detect that they run inside Athena
ATHENA_CODING_AGENT_DIR Override config directory (default: ~/.athena/agent)
ATHENA_CODING_AGENT_SESSION_DIR Override session storage directory (overridden by --session-dir)
ATHENA_PACKAGE_DIR Override package directory (useful for Nix/Guix where store paths tokenize poorly)
ATHENA_OFFLINE Disable startup network operations, including update checks, package update checks, and install/update telemetry
ATHENA_SKIP_VERSION_CHECK Skip the Athena version update check at startup
ATHENA_TELEMETRY Override install/update telemetry and provider attribution headers. Use 1/true/yes to enable or 0/false/no to disable. This does not disable update checks
ATHENA_CACHE_RETENTION Set to long for extended prompt cache (Anthropic: 1h, OpenAI: 24h)
VISUAL, EDITOR Fallback external editor for Ctrl+G when externalEditor is unset; defaults to Notepad on Windows and nano elsewhere

Commands run by the LLM-callable bash tool also receive current session metadata:

Variable Description
ATHENA_SESSION_ID Current session ID
ATHENA_SESSION_FILE Absolute session JSONL path; unset for ephemeral sessions
ATHENA_PROVIDER Currently selected model provider
ATHENA_MODEL Currently selected model ID
ATHENA_REASONING_LEVEL Current effective reasoning level

These values are resolved when each command starts. See Environment Variables for semantics, examples, and custom-tool opt-out.

Contributing & Development

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

License

MIT

See Also