Skip to main content

A cross-platform terminal based p2p agent orchestration harness and universal automation system

Project description

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: Wipe the memory of all agents
    • 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 details


Download files

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

Source Distribution

federate-0.9.3.tar.gz (123.8 kB view details)

Uploaded Source

Built Distributions

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

federate-0.9.3-py3-none-win_amd64.whl (11.0 MB view details)

Uploaded Python 3Windows x86-64

federate-0.9.3-py3-none-manylinux2014_x86_64.whl (10.8 MB view details)

Uploaded Python 3

federate-0.9.3-py3-none-manylinux2014_aarch64.whl (9.9 MB view details)

Uploaded Python 3

federate-0.9.3-py3-none-macosx_11_0_arm64.whl (10.2 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

federate-0.9.3-py3-none-macosx_10_9_x86_64.whl (10.8 MB view details)

Uploaded Python 3macOS 10.9+ x86-64

federate-0.9.3-py3-none-android_24_arm64_v8a.whl (10.3 MB view details)

Uploaded Android API level 24+ ARM64 v8aPython 3

File details

Details for the file federate-0.9.3.tar.gz.

File metadata

  • Download URL: federate-0.9.3.tar.gz
  • Upload date:
  • Size: 123.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for federate-0.9.3.tar.gz
Algorithm Hash digest
SHA256 e6716def807fdd67c736edbff78945b853c5d900ea3ade0516a843e70ba2a16e
MD5 858a0a8493489d0c4a877040450441a2
BLAKE2b-256 aceb4020a2c1b31e901e9785db295e29a3a22f233f7c5e4e38f3567174856c58

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3.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-0.9.3-py3-none-win_amd64.whl.

File metadata

  • Download URL: federate-0.9.3-py3-none-win_amd64.whl
  • Upload date:
  • Size: 11.0 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-0.9.3-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 3061e33a885deb94059c31bf108ba5e7355093d4a5767310f6735086d9c98837
MD5 16939a31851db7bc8f7aaf47ccb215c1
BLAKE2b-256 ce1e85a77a9c7512224bce909f3d0e0dd931a1f373bb9efa470bc58f76c6052f

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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-0.9.3-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for federate-0.9.3-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 d64ee43df41d02ca0baa1f2db78b5bdb4955220bad9ebe1a97a43d2295929a5c
MD5 0cab000e743d09eb0bcb7680286652b8
BLAKE2b-256 1c0cdea97afe569a81c318c22575b7e07b8186929b20b8faee09f180a1db5523

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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-0.9.3-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for federate-0.9.3-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 1f71757179fe30fc13a1cd78fb0ac92212ffed96cfa45e2d78ed78d2b9a87d17
MD5 47dd6dd2272d37929ae8d55e8c26dba0
BLAKE2b-256 9cf7e2254e3e37d632b31b833cc500b8a86bbc43e8a4ca44576a229c93ef3c2b

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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-0.9.3-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for federate-0.9.3-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 6945b26be23b99083d45569683d206f3cc5cc617f4690c8b67b25238550fbbf8
MD5 3e4fc6093a081f642729293a483dfb7c
BLAKE2b-256 a966a55029965ff6387de4dae91462fcb452abbd6ced9d8d36471b388748bc38

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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-0.9.3-py3-none-macosx_10_9_x86_64.whl.

File metadata

File hashes

Hashes for federate-0.9.3-py3-none-macosx_10_9_x86_64.whl
Algorithm Hash digest
SHA256 dad9107748f2c50c8c6cb04ce25757195a7cd84d76f58c37a58b52938a479629
MD5 892788f2f523227c03229a6fec47aa6a
BLAKE2b-256 922f5076aedd5f5a84d64c6f123d71d385bd2aa35334c4b483abf2a2cf451217

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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-0.9.3-py3-none-android_24_arm64_v8a.whl.

File metadata

File hashes

Hashes for federate-0.9.3-py3-none-android_24_arm64_v8a.whl
Algorithm Hash digest
SHA256 69ddf1c252067eb10b6baf1893a9f066dbb5effe0e476585b780b472be38be13
MD5 6f8cb7383d276b391925d956d9d3f003
BLAKE2b-256 97e7770d7236713853f7890467863a05aea83f9e74d2618adb15a8303d8b6046

See more details on using hashes here.

Provenance

The following attestation bundles were made for federate-0.9.3-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.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page