Federate.AI

Federate.AI is a cross-platform, terminal-based peer to peer AI orchestration and universal automation system.

It turns your terminal into an interactive workbench where you can run specialized teams of AI agents who talk to and collaborate with each other, use voice input and output, execute desktop automation commands, and much more.

Why We Built Federate.AI

In many underprivileged regions of the developing world, owning a desktop computer is often a luxury, yet nearly everyone has access to a smartphone. Federate.AI is written to bring the joy of programming to those pocket-sized screens. It is designed to run natively and comfortably inside Termux on Android, transforming a sub-$100 smartphone into a fully capable engineering workstation.

But Federate.AI is also built for the most advanced power-users on high-end hardware. It runs on any Mac or PC you can throw at it, unlocking system-level features like desktop automation, local speech-to-text with hotword detection, and text-to-speech voice generation.

It is designed to be the ultimate equalizer: accessible to everyone, yet incredibly powerful for those with top-tier setups.

What Makes Federate.AI Different?

1. Orchestration Freedom

Most multi-agent frameworks force you to write rigid, complex Python graphs and state-machine code to define how agents interact. Federate.AI replaces this overhead with simple prompt driven system.

You organize your team of agents simply by writing their backstories. Describe how they relate to one another, and Federate.AI builds the communication network dynamically. You can create:

  • A true Peer-to-Peer hierarchy where every agent is equal to every other agent. This is the default and exclusive to Federate.AI. No other agentic system does this as of date (2nd July 2026). We are the first to implement it (though many will likely follow suit).
  • A strict corporate hierarchy or military style chain-of-command.
  • A collaborative Hub-and-Spoke swarm.
  • Anything else you can think of.

2. Multi-Model, Cross-Provider Collaboration

Federate.AI supports a true multi-model ecosystem. Because it abstracts the underlying LLM provider, you can bring different models into the same session. You can easily watch ChatGPT and Gemini debate a technical architecture decision, a code optimization, or a creative writing prompt directly inside your terminal window.

3. Native Desktop Vision & Speech (Computer Only)

On desktop machines, agents can physically interact with your computer, listen for input and also talk back to you, using any model not just those with speech understanding or synthesis baked in.

4. Pocket-Sized Software Engineering

Even on mobile, you can delegate complex multi-step coding tasks to an autonomous sub-agent. The system spawns an isolated local git worktree, writes and edits code, runs your local tests, and presents you with a clean commit diff to approve—ensuring your active development workspace remains untouched. Did you know your old Android can compile Rust?

Feature Checklist

  • Context Injection (&): Type & followed by a file or directory (e.g., &src/app.py or &src/) to instantly parse and inject that code directly into your prompt.
  • Direct Shell Passthrough (!): Type ! followed by a command (e.g., !git diff) to run it in your local workspace and feed the output to the AI.
  • Integrated Text IDE: Press F6 to instantly toggle between the chat view, a local file tree, a code editor with symbol outline, and an execution dashboard.
  • And a lot more: Offline Persistent memory with semantic search, goal management, skills (passive and active skills, the latter again a Federate.AI exclusive as on date), speech to text, text to speech, research orchestration, computer use, telegram integration, task scheduling etc already baked in, more features might be added in the future.

Installation

Install the package via pip. We recommend installing with all optional extras to enable local voice/audio and serving capabilities:

pip install "federate[all]"

(For a lightweight installation without audio or computer usage capabilities, run pip install federate instead on Termux and Raspberry Pi).

Quickstart

Start the application from your terminal:

federate

(You can also open a specific project directory directly: federate path/to/folder)

Basic Setup

  1. Once the interface loads, press F4 to open the Agent Editor.
  2. Set up your active agent, including your API keys and model choices (Federate.AI is pre-configured for OpenRouter, but works with any OpenAI-compatible API).
  3. Federate.AI will securely encrypt and save your credentials inside your native OS keychain.

Changing Safety Modes (Ctrl+T / /arm)

To protect your workspace, the system boots in SAFE (PLAN) mode. In this mode, agents can search the web and read files, but they cannot edit code, run terminal commands, or control your computer.

  • Press Ctrl+T or type /arm to cycle permissions:
    • SAFE (PLAN): Read-only. Great for planning and research.
    • SEMI-AUTO: Agents can edit and execute, but Federate.AI will present a popup asking you to approve every single tool execution.
    • FULL-AUTO: Agents can run autonomous toolchains in the background.

Command Reference

  • Inject Files: Type & followed by the file path (e.g., &src/main.py). Use UP/DOWN arrow keys to cycle through autocomplete suggestions.
  • Mention Agents: Type @ followed by the agent name to route your message to a specific agent. Use @team to broadcast to everyone, or @room to talk to agents active in the current session. Agents can also use @ to invoke other agents, which is the core of the peer to peer system.
  • Key Bindings:
    • F2: Session Manager (Create a new chat or load historical multi-agent sessions)
    • F4: Open the Active Agent configuration
    • F5: Cycle the host agent
    • F6: Cycle through UI panels (Chat ↔ IDE Editor ↔ Executions Dashboard)
    • F8: Change your workspace directory
    • Ctrl+K: Start fresh conversation
    • Ctrl+A: ABORT (Emergency stop for any running AI tasks or terminal commands)
    • Ctrl+Q: Quit Federate.AI

Statutory Warning

  • Federate.AI contains full unrestricted code/command execution capabilities. This lets you hand full control of the device to the agent(s) running. This includes the ability to run potentially destructive code/commands. It is recommended to run it on a spare machine that contains no sensitive/valuable data and one that you do not mind wiping and resetting from time to time.
  • AI systems inherently navigate a trade-off between capability and safety; Federate.AI leans heavily toward the capability aspect. For safe and secure coding with AI assistance, please consider using KittySuite IDE, where the AI does not have the capability to execute code, run commands, or read files you don't explicitly share.

Project links

Data verified by PyPI on Jul 4, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (1.0.38)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for geoarkadeep from gravatar.com geoarkadeep

Credits

Author: ROCK-LAB-PRIVATE-LIMITED

GitHub Statistics

Data verified by PyPI on Jul 4, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

Apache Software License (Apache Software License)

Requires

Python >=3.11

Provides Extra

audio vision pdf telegram browser all

Tags

ai agent tui coding llm

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

federate-0.9.20.tar.gz (15.4 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

federate-0.9.20-py3-none-win_amd64.whl (26.3 MB view details)

Uploaded Python 3Windows x86-64

federate-0.9.20-py3-none-manylinux2014_x86_64.whl (26.1 MB view details)

Uploaded Python 3

federate-0.9.20-py3-none-manylinux2014_aarch64.whl (25.2 MB view details)

Uploaded Python 3

federate-0.9.20-py3-none-macosx_11_0_arm64.whl (25.5 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

federate-0.9.20-py3-none-macosx_10_9_x86_64.whl (26.2 MB view details)

Uploaded Python 3macOS 10.9+ x86-64

federate-0.9.20-py3-none-android_24_arm64_v8a.whl (25.6 MB view details)

Uploaded Android API level 24+ ARM64 v8aPython 3

File details

Details for the file federate-0.9.20.tar.gz.

File metadata

  • Download URL: federate-0.9.20.tar.gz
  • Upload date:
  • Size: 15.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for federate-0.9.20.tar.gz
Algorithm Hash digest
SHA256 21c5f0ab7654ebf71275a23bca1e5eabe21f76c5ef29bd5a6ace0278c6d5e4f0
MD5 c186ae66913a26fe9d70866ac2e98918
BLAKE2b-256 0db02f10e249190571203c1ae05e45f2a20841bebe25b9fe95c4ff58990c1424

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20.tar.gz:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-win_amd64.whl.

File metadata

  • Download URL: federate-0.9.20-py3-none-win_amd64.whl
  • Upload date:
  • Size: 26.3 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for federate-0.9.20-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 16a31d799759e5fe48821ed680211d45d7324cc329da0b19d98fa6dfef865a28
MD5 b8f4f8c686e12f8afb503a26672cfe4e
BLAKE2b-256 51420a1bfb9b68a5fd2117343f33fa1b77ffe6233af28b1dc3d5e035bf57202f

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-win_amd64.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for federate-0.9.20-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 a8f82f52f49a8496f516c698429c297b868ff64255699f7e6679566f5d785da5
MD5 aa1b83eabee11e1f9ecf69aa623a1923
BLAKE2b-256 fb972bcd9579ebc5aec0073ec8e347d72caf2bc81b0ad46526f8eb40acb2b791

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-manylinux2014_x86_64.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for federate-0.9.20-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 290e3225e37516b4ef3aaa4e0c79f1d32c077f90d606a968f617909b3c4d4279
MD5 1b0fec4cfee98f65c5d1ba9c3e0039b5
BLAKE2b-256 34ef98237cdc13cadf2c28712d1068da2f7cb02be53980209cfef527ccd2076a

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-manylinux2014_aarch64.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for federate-0.9.20-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 90b04c234e165a7fffb261cfa63fc813f30327385eaf013fe697384417fc5472
MD5 2c80a3456b5e77fecad739c537d4271c
BLAKE2b-256 ddc5fd52539573e68f98f3d2f7ab569ee26b5f8181f19c7ab53a195fb2b4610e

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-macosx_11_0_arm64.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for federate-0.9.20-py3-none-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 1d351b5a188773bebc32bde9cc4ee77e4334b6986b46760306981fb7dc78c041
MD5 302cb7f304c5ae3fbf618ffc07d0cd45
BLAKE2b-256 41c8194086cfe9026331ad523275b37dd42e603b61b9f22662a286d5458eb2e8

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-macosx_10_9_x86_64.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file federate-0.9.20-py3-none-android_24_arm64_v8a.whl.

File metadata

File hashes

Hashes for federate-0.9.20-py3-none-android_24_arm64_v8a.whl
Algorithm Hash digest
SHA256 52b5acab2cf48b0727f534b35f4b53e44d3911f332c977b52f0ac6fce009de5d
MD5 28aa4e176635e24f96b7865c4281cf77
BLAKE2b-256 0482a71d45adbb609a4357e03fc6703b2a09f18489b47f6107022e0a6e5788a7

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.20-py3-none-android_24_arm64_v8a.whl:

Publisher: release.yml on ROCK-LAB-PRIVATE-LIMITED/federate.ai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

1.0.38

7 files

1.0.37

7 files

1.0.36

7 files

1.0.35

7 files

1.0.34

7 files

1.0.33

7 files

1.0.32

7 files

1.0.31

7 files

1.0.30

7 files

1.0.29

7 files

1.0.28

7 files

1.0.27

7 files

1.0.26

7 files

1.0.25

7 files

1.0.24

7 files

1.0.23

7 files

1.0.22

7 files

1.0.21

7 files

1.0.20

7 files

1.0.19

7 files

1.0.18

7 files

1.0.17

7 files

1.0.16

7 files

1.0.15

7 files

1.0.14

7 files

1.0.13

7 files

1.0.12

7 files

1.0.11

7 files

1.0.10

7 files

1.0.9

7 files

1.0.8

7 files

1.0.7

7 files

1.0.6

7 files

1.0.5

7 files

1.0.3

7 files

1.0.0

7 files

0.9.43

7 files

0.9.42

7 files

0.9.41

7 files

0.9.40

7 files

0.9.39

7 files

0.9.38

7 files

0.9.37

7 files

0.9.36

7 files

0.9.35

7 files

0.9.34

7 files

0.9.33

7 files

0.9.32

7 files

0.9.31

7 files

0.9.30

7 files

0.9.29

7 files

0.9.28

7 files

0.9.27

7 files

0.9.26

7 files

0.9.25

7 files

0.9.24

7 files

0.9.23

7 files

0.9.21

7 files

This release

0.9.20 This release

7 files

0.9.19

7 files

0.9.18

7 files

0.9.17

7 files

0.9.16

7 files

0.9.14

7 files

0.9.11

7 files

0.9.10

7 files

0.9.9

7 files

0.9.7

7 files

0.9.6

7 files

0.9.5

7 files

0.9.4

7 files

0.9.3

7 files

0.9.2

7 files

0.9.1

7 files

0.9.0

7 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page