aegis-ag 1.0.0.dev20260413091006

Aegis CLI-first persistent agent runtime.

Aegis

Your own persistent AI.
An agent that remembers, reasons, and endures across time.

Aegis is building toward a personal AI agent that does not lose the thread when a single chat ends. The goal is not just tool calling or session orchestration, but continuity: an agent that becomes more useful as it accumulates the right history, goals, and context.

Positioning

Aegis is for long-running work that should survive interruption.

• It should remember what matters.
• It should reason across longer horizons than the current turn.
• It should recover the right context instead of collapsing when the window fills.

In product terms, Aegis is aiming at a persistent personal AI, not a disposable chat session.

Why Aegis Exists

Most current agents fail in three predictable ways:

• Amnesia: decisions, preferences, and project state disappear when the session ends.
• Myopia: current-turn optimization wins over next-week usefulness.
• Overflow: context windows fill up, and naive truncation replaces structured memory and retrieval.

The product thesis behind Aegis is that a useful agent should behave more like a persistent collaborator: it should remember, plan, and recover the right context when work resumes.

Thesis

• Long-term memory: durable episodic, semantic, and procedural memory instead of session-only state.
• Long-horizon decision making: persistent goals, task decomposition, and deadline-aware planning.
• Long-context understanding: layered context management, compression, and retrieval instead of naive truncation.

Quickstart

Aegis is used from the terminal. The path is simple: install it, run aegis, let it hatch your first named clone, and continue directly into grow. Use aegis clone <name> only when you want another Aegis individual.

Install from remote

curl -fsSL https://aegis.agentic-in.ai/install.sh | bash

This installs the public aegis launcher into ~/.local/bin and prepares the default durable runtime under ~/.local/share/aegis. The public installer now tracks the latest published development package by default. If you want the latest stable package instead:

curl -fsSL https://aegis.agentic-in.ai/install.sh | bash -s -- --channel stable

Install from source

git clone https://github.com/agentic-in/aegis.git
cd aegis
bash scripts/install.sh

This creates a local launcher and the default durable layout:

• AEGIS_HOME
• AEGIS_STATE_DIR
• AEGIS_PROFILE_DIR

If ~/.local/bin is not already on PATH, use the launcher path printed by the install script directly.

CLI overview

aegis
aegis born
aegis grow
aegis clone nova
aegis clones
aegis health
aegis grow --message "Who are you?"

The CLI surface stays intentionally small:

• aegis is the default entry: on the first run it starts birth, and later it re-enters grow directly or asks which clone to open.
• aegis born brings the first Aegis to life, persists identity and CLONE.md, binds the provider path, asks for the first durable goal, hatches the first clone, and in interactive use hands off straight into grow.
• aegis grow is the normal way back in and enters the current live clone directly when one exists.
• aegis grow --message "..." runs a single turn without staying in the TUI.
• aegis health checks whether the current companion is ready to grow.
• aegis clone <name> creates another named Aegis individual only when you want a second continuity line, and can seed its first durable goal with --initial-goal.
• aegis clones lists known clones.
• aegis clones bye <name> retires one clone.
• aegis clones bye --all clears every clone.
• aegis grow --clone-id <name> opens one clone directly.

Inside grow, the conversation stays primary. Slash commands such as /status, /memory, /goals, /identity, and /help are there when you need to inspect or steer continuity without leaving the session.

Shipped Capability Overview

Aegis already ships these core runtime surfaces on main:

• Durable memory, planning, and context recovery backing the normal grow path.
• Persistent clones with isolated continuity, personality, and CLONE.md.
• Provider onboarding and a pluggable catalog covering openai-compatible, openai, openrouter, anthropic, google, groq, deepseek, xai, mistral, together, fireworks, moonshot, minimax, ollama, and vllm.
• Built-in tools now ship as a curated runtime catalog:

• terminal: tool.terminal.exec
• process: tool.process.manage
• file: tool.file.read, tool.file.write, tool.file.patch, tool.file.search
• web: tool.web.search, tool.web.read
• browser: tool.browser.navigate, tool.browser.snapshot, tool.browser.click, tool.browser.type, tool.browser.scroll, tool.browser.back, tool.browser.press, tool.browser.images, tool.browser.vision, tool.browser.console
• clarify: tool.clarify
• cron: tool.cron.manage
• code_execution: tool.code.execute
• memory: tool.memory.manage
• messaging: tool.message.send
• todo: tool.todo.manage
• continuity-native: tool.companion.manage, tool.goal.manage, tool.skill.manage, tool.mcp.manage

• Built-in skills for shell, workspace search, web search/read, continuity, cron scheduling, and voice reply guidance.
• Local skill-hub search/install plus MCP discovery/install for servers such as Fetch, Filesystem, GitHub, Playwright, and Brave Search.
• Durable agent-run checkpoints for resumable multi-step tool loops and long-horizon follow-up.

The public docs now cover the supported operator path plus the currently shipped provider, capability, automation, and extension surfaces. Internal design docs under docs/system-design/ still describe the broader target architecture.