Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools.
agentic-in/elephant-agent
A personal AI agent that builds a correctable model of its user over time and helps shape long-running life and work goals into Paths.
- Stars
- 583
- Forks
- 62
- Open issues
- 19
- Last commit
- 2 months ago
What is it?
Elephant Agent starts from the person rather than the task. It grows a correctable Personal Model covering identity, surrounding people and projects, current focus and pressure, and lessons from past experience. The model deepens through interaction, corrections, and questions from the agent.
Once it understands enough context, the agent helps design long-running Paths for areas such as work, health, habits, learning, relationships, research, or code. It breaks each Path into Steps, can bring in helper agents, and returns to the user at Checkpoints where human judgment is needed.
The project ships as a macOS desktop app with chat, Paths, a Personal Model viewer, skills, tools, messaging integrations, and calendar views. A CLI and web Dashboard are available for Linux and cloud setups, with support for local or hosted model providers.
Key features
- 01Builds an editable Personal Model of identity, world, current pulse, and journey
- 02Designs long-running Paths and breaks them into Steps with Checkpoints
- 03Coordinates helper agents under one shared understanding
- 04Provides a macOS desktop app and a CLI with a web Dashboard
- 05Connects to messaging apps such as WeChat, Feishu, Discord, DingTalk, and WeCom
- 06Supports local or hosted model providers
Use cases
- Tracking a long-term goal like a learning plan or health routine with periodic check-ins
- Giving a personal assistant persistent context about your people, projects, and priorities
- Running a terminal-first personal agent on a Linux or cloud machine
Topics
FAQ
- What is elephant-agent?
- A personal AI agent that builds a correctable model of its user over time and helps shape long-running life and work goals into Paths. Elephant Agent starts from the person rather than the task. It grows a correctable Personal Model covering identity, surrounding people and projects, current focus and pressure, and lessons from past experience. The model deepens through interaction, corrections, and questions from the agent.
- Is elephant-agent free to use? What license does it have?
- elephant-agent has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is elephant-agent still maintained?
- Updated within 6 months. The last commit to elephant-agent was on Aug 27, 2026.
- What can I use elephant-agent for?
- Tracking a long-term goal like a learning plan or health routine with periodic check-ins Giving a personal assistant persistent context about your people, projects, and priorities Running a terminal-first personal agent on a Linux or cloud machine
- Where can I get elephant-agent?
- The source code and installation instructions are on GitHub: https://github.com/agentic-in/elephant-agent
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A personal AI assistant that runs on macOS, Windows, iOS, Telegram, Slack and more, with persistent memory and proactive follow-ups.
A community-maintained collection of ready-made tools that Strands AI agents can call for files, shell, web search, memory, AWS and more.
A local, self-hosted memory hub that gives multiple AI agents such as Claude Code, Codex and OpenClaw one shared, persistent memory of you.
Code-first Python framework from Google for building, evaluating, and deploying AI agents, optimized for Gemini but model-agnostic.
A code-first Java toolkit from Google for building, evaluating, and deploying AI agents, with a Python-ADK-style API.