This release is a pre-release and may not be stable for production use.
Elephant Agent
Do more without thinking less.
A Mother Elephant that grows to understand you, then helps shape the paths you are trying to move.
What It Is
Elephant Agent starts from the person, not the task.
The mother elephant grows a correctable Personal Model of who you are, what surrounds you, what is alive right now, and what your path has taught you. That understanding keeps deepening through interaction, correction, and gentle questions.
Once Elephant Agent understands enough, it can help design living Paths: work, health, habits, learning, relationships, recovery, research, code, and any other long-running direction you want to move. It can break a Path into Steps, bring in baby elephants when useful, and return to you at Checkpoints where your judgment matters.
Personal Agent Levels
|
L1
Executes tasks. Claude Code, Cursor, Devin, and Codex-style agents make execution cheaper and faster. |
L2
Carries context. OpenClaw publicly emphasizes local agents, persistent memory, full system access, skills, plugins, and integrations. |
L3
Improves procedures. Hermes Agent publicly positions itself around a self-improving learning loop, skill creation, recall, and user modeling. |
L4
Grows with the person. Elephant Agent's product position: Mother understands the person, shapes Paths, and keeps judgment, evidence, questions, and learning close to the person. |
Personal Model
- Identity — who you are, your values, boundaries, decision style, and stable preferences.
- World — the people, projects, tools, places, and relationships around you.
- Pulse — what is alive right now: focus, pressure, constraints, energy, and priorities.
- Journey — what your path has taught: lessons, failures, recovery patterns, and long-running growth.
The goal is not to remember everything. The goal is to understand what matters, show why it matters, let you change it, and turn that understanding into better Paths over time.
macOS Desktop App
The macOS app is the recommended product surface. Chat / Wake is where you talk to Mother; Paths are where long-running life and work arcs become visible; the rest of the app keeps the Personal Model, Herd, skills, messaging, calendar, usage, and advanced runtime settings inspectable instead of hidden behind a chat box.
Home — start from what Mother understands before shaping the next Path.
|
Preferences Choose language, boundaries, model posture, and curiosity effort. |
Chat / Wake Return to Mother and the same path, not a blank prompt. |
|
Personal Model Inspect the understanding that shapes future Paths. |
Providers Use local or hosted models as advanced posture, not the product center. |
|
Skills See which skills help Mother and the Herd move a Path. |
Tools Keep browser, filesystem, MCP, and operator actions explicit. |
|
Herd Coordinate Mother and baby elephants under one understanding. |
Messaging Connect WeChat, Feishu, Discord, DingDing, or WeCom when you want it. |
|
Calendar Keep routines, reminders, and long-running Paths visible. |
Usage Inspect local token flow and runtime events instead of treating cost as a black box. |
Quickstart
Elephant Agent has two supported product shapes.
1. macOS desktop app (recommended)
Use this path for the full local desktop workspace: Chat / Wake, Paths, Personal Model, Herd, skills, messaging, calendar, usage, and settings in one native app.
- Download the latest macOS build from GitHub Releases.
- Open
Elephant Agent.app. - Create your first elephant, choose a provider, and set curiosity effort.
- Return through Chat / Wake when you want Mother to continue the same path.
2. CLI + Dashboard (Linux / Cloud)
Use this path for Linux, cloud machines, SSH workflows, and terminal-first operators. The CLI is the daily terminal surface; the Dashboard is the visual inspection surface for Personal Model, evidence, jobs, skills, and runtime state.
|
CLI |
Dashboard |
Install:
curl -fsSL https://elephant.agentic-in.ai/install.sh | bash
First run:
elephant init # choose identity, provider, and curiosity effort
elephant status # check provider and local runtime readiness
elephant wake # enter the chat TUI
elephant dashboard # open Personal Model, questions, evidence, and runtime state
For remote or cloud use, elephant dashboard --no-open prints the local URL so
you can attach through your preferred tunnel or browser setup.
Read More
README and the homepage stay product-first. The deeper system story lives here:
Contributors
Agentic Intelligence Lab
Metadata
Release files for elephant-agent 1.0.0.dev20260530041731
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| elephant_agent-1.0.0.dev20260530041731.tar.gz | 1.7 MB | Without provenance | Details for elephant_agent-1.0.0.dev20260530041731.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| elephant_agent-1.0.0.dev20260530041731-py3-none-any.whl | Python 3 | none | any | Details for elephant_agent-1.0.0.dev20260530041731-py3-none-any.whl |
Total release size: 3.7 MB
Release files / elephant_agent-1.0.0.dev20260530041731.tar.gz
| Download URL | elephant_agent-1.0.0.dev20260530041731.tar.gz |
|---|---|
| Size | 1.7 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ea04e036e33039c78440e31d124c6a0942d4e2805944fb56284bd859a4f34539
|
|
BLAKE2b-256 checksum How to use checksums |
49ce1609cb3d07913fb3af1b1a5b19ef1cf1ce9ecdeb8dee3d8674efaa56d3c9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Release files / elephant_agent-1.0.0.dev20260530041731-py3-none-any.whl
| Download URL | elephant_agent-1.0.0.dev20260530041731-py3-none-any.whl |
|---|---|
| Size | 2.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ee4927af29e35239659d4422121898199a8ad92558d4746c6091e16d5f2b2b89
|
|
BLAKE2b-256 checksum How to use checksums |
0a3055f94bfcd6c45d48ba82189ae9858428f782302ccc347afbbbab33bf1ebf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.13
|
Security for elephant-agent 1.0.0.dev20260530041731
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.