eVi — personal AI assistant

PyPI Downloads Docker (GHCR) GHCR pulls Python 3.13+ License: MIT

eVi 1.0 — shipped and public. Local-first personal assistant. Chat with a model on your hardware, let it use tools, generate images, automate scheduled tasks, drive your browser, and reach the same core from a terminal, a web app, or a native desktop window.

One Python core, three frontends, no cloud round-trips.

       ┌──────────────────────────────┐
       │       evi (core library)     │
       │  Agent · Tools · Memory ·    │
       │  Skills · Hooks · MCP ·      │
       │  Scheduler · Dream · …       │
       └────┬──────────┬──────────┬───┘
            │          │          │
        ┌───▼──┐   ┌───▼──┐   ┌───▼────┐
        │ CLI  │   │ Web  │   │Desktop │
        │      │   │ SSE  │   │ Tauri  │
        └──────┘   └──────┘   └────────┘

Requirements

Component Why Notes
Python 3.13+ Core runtime 3.13 tested
Git 2.17+ Optional — evi worktree 2.28+ for init -b
An LLM backend One of LM Studio / Ollama / llama-server / any OpenAI-compatible endpoint LM Studio default
NVIDIA GPU Optional — speeds up local LLMs and ComfyUI image gen CPU fallback works

Quickstart

Package name: the project is eVi, but the PyPI distribution is evi-assistant (the bare evi name was taken). Install with pip install evi-assistant; the import package and CLI command are both still evi (import evi, run evi).

pip install evi-assistant                # from PyPI
evi models recommend                     # honest read on what'll fit
evi chat                                 # off you go

Or work from a clone (editable install, all extras):

git clone https://github.com/evi-assistant/evi-ai.git evi && cd evi
py -3.13 -m venv .venv
.venv\Scripts\Activate.ps1            # Windows
# source .venv/bin/activate            # Linux / macOS

pip install -e .

# Pick a backend. LM Studio + a tool-capable model is the easiest first run.
# In LM Studio: load qwen2.5-7b-instruct → Developer → Start Server.

evi models recommend                    # honest read on what'll fit
evi chat                                # off you go

/help inside the REPL lists every slash command (goal tracking, plan mode, auto-approve, model switching, user-defined templates).

Three-machine setup

eVi is built to span machines. A typical setup:

Machine Role Backend
AI server (P40) LLM host + web UI Ollama or llama-server, evi web on port 8000
Desktop (16 GB) Full power workstation Local LM Studio
Laptop (2 GB) Thin client Profile points at the AI server

See docs/multi-machine.md for the wiring.

Major commands

evi chat                           Start the REPL
evi web --host 0.0.0.0             Run the FastAPI + SSE web UI
evi dream                          Curate long-term memory from yesterday's chats
evi models recommend / list / use  Hardware-aware model selection
evi models pull <ref>              Pull via Ollama tag or hf:<repo>:<file>
evi schedule add / list / run-now  Cron-style scheduled prompts
evi scheduler                      Foreground daemon for scheduled tasks
evi worktree create <branch>       Spin up a git worktree for parallel work
evi profile add home --backend …   Per-machine config overlays
evi voice listen / speak           STT + TTS
evi mcp list-tools                 Show MCP server-provided tools
evi mcp serve                      Run eVi AS an MCP server (other agents use eVi's tools)

What's built

Everything below ships in 1.0. Gmail / Microsoft 365 email is the one deferred surface — scaffolded but off by default.

Feature Status
Foundation, CLI, agent loop, fs/code tools ✅
ComfyUI image generation ✅
FastAPI + SSE web UI ✅
Tauri desktop shell (local + remote modes) ✅
Persistent memory + scoped subagents ✅
MCP (Model Context Protocol) integration ✅
Skills + scheduled tasks ✅
Backends, model registry, hardware recommender, profiles ✅
EVI.md, slash commands, /goal, plan mode ✅
Hooks, auto mode, git worktrees ✅
Transcripts, dreaming, web search, voice TTS, computer use ✅
STT, web UI parity, polish ✅
Gmail / Microsoft 365 email ⏸ deferred

Layout

evi/                core library
  agent.py          agent loop with permission + hooks
  backends/         LM Studio / Ollama / llama.cpp / OpenAI-compat
  llm/              client + subagent runner
  tools/            built-in tool catalog (fs, code, image, web, voice, …)
  mcp/              MCP client bridge + manager
  memory.py         long-term memory store
  skills.py         user skill packets
  scheduler.py      APScheduler driver
  dream.py          memory-consolidation runner
  hardware.py       GPU + RAM detection
  recommend.py      curated model picks per VRAM
  …
  apps/             frontends that consume the core (shipped in the wheel)
    cli/main.py     Typer CLI
    web/server.py   FastAPI + SSE
    web/static/     chat UI (vanilla JS)
desktop/            Tauri 2 shell (NOT a Python package; local-spawn or EVI_REMOTE_URL)
tests/              pytest
docs/               deeper guides
scripts/            install + dev helpers

Configuration

Per-user config lives in ~/.evi/. Highlights:

~/.evi/
  config.toml         primary settings — backend, tools, auto-approve
  profiles/*.toml     overlay profiles for per-machine config
  memory/*.md         long-term memory; `.attic/` holds soft-deleted entries
  skills/<name>/      installed skill packets (SKILL.md + assets)
  commands/<name>.md  user-defined slash command templates
  scheduled/*.json    saved scheduled prompts
  hooks.toml          before/after_tool_call hooks
  mcp.json            MCP server list
  transcripts/        per-session JSONL (input to dreaming)
  logs/               run logs (dreams, scheduled tasks)

See docs/configuration.md for the full reference, the feature catalog for what every feature does + how to use it, and surface parity for the CLI ↔ Web ↔ Desktop map.

Optional dependency groups

pip install -e '.[web]'        # FastAPI + uvicorn for `evi web`
pip install -e '.[mcp]'        # Model Context Protocol client
pip install -e '.[scheduler]'  # APScheduler for cron-style tasks
pip install -e '.[downloads]'  # huggingface_hub for `evi models pull hf:...`
pip install -e '.[web-tools]'  # DuckDuckGo search + BeautifulSoup
pip install -e '.[stt]'        # faster-whisper + sounddevice
pip install -e '.[computer]'   # pyautogui for mouse/keyboard control
pip install -e '.[dev]'        # pytest + ruff

Or all at once:

pip install -e '.[dev,web,mcp,scheduler,downloads,web-tools,stt,computer]'

Development

pip install -e '.[dev]'
pytest -q              # ~1,300+ unit tests (E2E are opt-in: -m e2e)
ruff check evi apps    # style + bug-pattern lint

See docs/development.md for architecture notes, and docs/self-build.md for developing/building eVi with eVi (the EVI.md project context + the one-command scripts/build-desktop build).

Safety posture

  • Default tool toggles lean conservative: shell, subagent, web, voice, computer, gmail, outlook, image, and mcp are all OFF until you flip them in config.toml.
  • auto.auto_approve lists categories that run without prompting. The defaults are fs, code, memory, skills, image. computer is never in this list — every mouse click / keystroke prompts.
  • Hook vetoes (~/.evi/hooks.toml) can block any tool by glob match.
  • Soft-delete memory sends "forgotten" entries to ~/.evi/memory/.attic/ so the dreaming engine can't permanently lose anything.

Code signing

See the Code signing policy for how eVi's desktop installers are signed, who approves releases, and how to verify a download.

Free code signing provided by SignPath.io, certificate by SignPath Foundation.

License

MIT - see LICENSE.

Project links

Data verified by PyPI on Aug 25, 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 (1.0.51)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for dmang-dev from gravatar.com dmang-dev

GitHub Statistics

Data verified by PyPI on Aug 25, 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

MIT License (MIT License)

Requires

Python >=3.12

Provides Extra

email web mcp scheduler downloads web-tools computer stt pdf index calendar rerank ast diarize doc claude-agent telemetry otel moderation e2e build-desktop dev

Tags

ai assistant llm agent local ollama lm-studio

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

evi_assistant-1.0.49.tar.gz (728.0 kB view details)

Uploaded Source

Built Distribution

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

evi_assistant-1.0.49-py3-none-any.whl (595.5 kB view details)

Uploaded Python 3

File details

Details for the file evi_assistant-1.0.49.tar.gz.

File metadata

  • Download URL: evi_assistant-1.0.49.tar.gz
  • Upload date:
  • Size: 728.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for evi_assistant-1.0.49.tar.gz
Algorithm Hash digest
SHA256 2efb98f33ea37fca8d9ee8ab379646bf0d4e41e384a26b5ed620fe1f989a1146
MD5 6984e2c4f6c9b3139bfd5f22f9c8d124
BLAKE2b-256 0a2d47043abe76c8beb62d4bbdbd56078d8abf3d493a67bbe5a71ecd48301a75

See more details on using hashes here.

Provenance

The following attestation bundles were made for evi_assistant-1.0.49.tar.gz:

Publisher: release.yml on evi-assistant/evi-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 evi_assistant-1.0.49-py3-none-any.whl.

File metadata

  • Download URL: evi_assistant-1.0.49-py3-none-any.whl
  • Upload date:
  • Size: 595.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for evi_assistant-1.0.49-py3-none-any.whl
Algorithm Hash digest
SHA256 56fcff5d8cefb7c3fbcd649082753d70960481d4e5fa02f7e9d1b30f40af99fc
MD5 7333a4635aafeec7706c787d42efb2b1
BLAKE2b-256 222d12c5e3ff34a7007ca2102f2aae89405c2b371d0ca4f59f216fd8a3f08359

See more details on using hashes here.

Provenance

The following attestation bundles were made for evi_assistant-1.0.49-py3-none-any.whl:

Publisher: release.yml on evi-assistant/evi-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

1.0.51

2 files

1.0.50

2 files

This release

1.0.49 This release

2 files

1.0.48

2 files

1.0.47

2 files

1.0.46

2 files

1.0.45

2 files

1.0.44

2 files

1.0.43

2 files

1.0.42

2 files

1.0.41

2 files

1.0.40

2 files

1.0.39

2 files

1.0.38

2 files

1.0.37

2 files

1.0.36

2 files

1.0.35

2 files

1.0.34

2 files

1.0.33

2 files

1.0.32

2 files

1.0.31

2 files

1.0.30

2 files

1.0.29

2 files

1.0.28

2 files

1.0.27

2 files

1.0.26

2 files

1.0.25

2 files

1.0.24

2 files

1.0.23

2 files

1.0.22

2 files

1.0.21

2 files

1.0.20

2 files

1.0.19

2 files

1.0.18

2 files

1.0.17

2 files

1.0.16

2 files

1.0.15

2 files

1.0.14

2 files

1.0.13

2 files

1.0.12

2 files

1.0.11

2 files

1.0.10

2 files

1.0.9

2 files

1.0.8

2 files

1.0.7

2 files

1.0.6

2 files

1.0.5

2 files

1.0.4

2 files

1.0.3

2 files

1.0.2

2 files

1.0.1

2 files

1.0.0

2 files

0.40.0

2 files

0.39.0

2 files

0.38.0

2 files

0.37.0

2 files

0.36.1

2 files

0.36.0

2 files

0.35.0

2 files

0.34.1

2 files

0.34.0

2 files

0.33.0

2 files

0.32.0

2 files

0.30.0

2 files

0.29.0

2 files

0.28.0

2 files

0.27.0

2 files

0.26.0

2 files

0.25.0

2 files

0.24.3

2 files

0.24.2

2 files

0.24.0

2 files

Supported by

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