See it

Slash autocomplete with fuzzy filtering, right in the prompt:

A grounded answer — real tools, real system data, streamed live:

Screenshots are real SVG captures of the app running headless (docs/shot.py), not mockups.

$ sk brief
╭─ sidekick brief  Sat 2026-09-19 11:58 ─╮
│ CPU: AMD Ryzen 7 4800H (16 threads)     │
│ Mem: 7.2Gi · GPU: GTX 1650 4GB          │
│ /dev/nvme0n1p8  133G  117G  8.5G  94% / │
╰─────────────────────────────────────────╯
│ ! disk 94% full — clean ~/Downloads…    │

$ sk run "what is the ideal llm i can run on my device"
• qwen3:4b (2.5 GB): fits comfortably in your 4096 MiB VRAM.
• llama3.2:3b (2.0 GB): another good option.

$ sk talk
[Enter] to record, [Enter] to stop. /quit exits.
heard> what files are in the sidekick repo

Why sidekick

Quickstart

uv tool install sidekick-agent[voice]   # global `sk`, STT included
sk init                                  # guided first-run: hardware → model → verify
sk                                       # fullscreen chat — start here (`sk tui` works too)

No clone, no build — installs straight from PyPI. Requires Python 3.12+. Without [voice] you get everything except Talk/mic (installs on first use instead). Local path needs Ollama (ollama serve, pull qwen2.5-coder:7b for smarts or llama3.2:3b for speed).

Install

The published name is sidekick-agent (the sidekick name is taken on PyPI); the command stays sk. Version is a single source of truth in src/sk/__init__.py. Publishing is automatic and credential-free: when a PR is merged to main of the canonical repo Faisal01011/sidekick with a bumped __version__, GitHub Actions trusted-publishes to PyPI and opens a GitHub Release (forks can never publish) — details in packaging/README.md.

From source (dev):

git clone https://github.com/Faisal01011/sidekick && cd sidekick
uv tool install -e ".[voice]"   # editable dev install; STT included
sk doctor

Chat

One input, two surfaces — fullscreen TUI and plain-text REPL share every command:

sk                   # fullscreen chat with streaming + themes — start here
sk tui --model fast  # same, explicit form
sk chat              # fallback REPL: dumb terminals, screen readers, broken TUIs

Type / and an autocomplete popup filters all 20+ commands — Enter completes, Tab too, Esc dismisses, ↑/↓ navigates. F1 opens a generated cheatsheet (keys + commands, built from the same tables as the dispatcher, so it can't rot).

TUI keys: Enter sends · ctrl+j/alt+enter newline · ↑/↓ history · ctrl+y copies · ctrl+t push-to-talk · ctrl+b/f scroll · F1 help. Answers stream live with role colors; the footer shows model · session · last-turn time/tokens.

Voice

sk talk [-d SECS] [--stt-model base] [--device hw:2,0]  # Enter records, Enter stops
sk mic-test                                             # peak dB + silent/quiet/good verdict

Capture via the OS-native recorder (arecord/ALSA on Linux, sox/ffmpeg on macOS), transcription via local faster-whisper int8, transcript lands editable in the prompt. In the TUI, ctrl+t (or the mic pill) does the same. Voice never leaves your machine; recordings are temp files, deleted after each take.

Providers (BYO key)

sk connect     # pick provider → paste key (hidden) → pick model → ping. Done.

One guided flow: numbered provider list (local ones skip keys), live validation before anything saves, curated model list (TTS/image junk filtered, recommended pre-highlighted, Enter accepts), and a 5-token ping instead of a full agent turn. Advanced paths still work: sk auth add/list/status/remove, sk model, sk setup (connect + hook), sk config --provider openai --api-key sk-..., /provider groq inside chat.

Presets: ollama|openai|groq|together|deepseek|openrouter|google|lmstudio|anthropic|custom (anthropic speaks the native Messages API; the rest are OpenAI-compatible). Any OpenAI-compatible endpoint works via --provider custom --base-url https://... --api-key .... Preferred: SIDEKICK_API_KEY env (never touches disk); file keys are chmod 600 and masked in --show.

Command reference

Packs use the SKILL.md frontmatter format. The prompt carries a relevance-ranked index; the agent loads full instructions on demand via the skill tool. fast/smart resolve per provider (Ollama: llama3.2:3b/qwen2.5-coder:7b, Groq: gpt-oss-20b/120b).

Architecture

flowchart TB
    U([you]) --> CLI[sk / sk run]
    U --> TUI[sk tui: autocomplete, streaming, mic pill]
    U --> VOICE[sk talk: arecord + faster-whisper]
    CLI --> SLASH[slash.py: /commands, no LLM]
    TUI --> SLASH
    VOICE --> AGENT
    CLI --> AGENT[agent.py: stream → tools → synthesize]
    TUI --> AGENT
    AGENT --> GROUND[deterministic grounding: ~/paths, URLs,\nsysinfo — injected before the model sees the prompt]
    AGENT --> TOOLS[tools.py: 17 tools, allowlists,\nhard-blocks, SSRF guard]
    AGENT --> MEM[(store.py: history, memories FTS5,\ntodos, shell log)]
    AGENT --> SKILLS[skills: relevance-ranked SKILL.md index]

Design bets that paid off: deterministic grounding beats prompt instructions (small models ignore rules but can't argue with injected facts), text-JSON fallback (coders emit tools as text over the OpenAI endpoint), FTS5 over vectors (zero deps, instant, no embedding server on a 4GB box).

Safety

Reads auto-run. Writes, deletes, and general shell need approval (inline [y/N] in TUI, prompt in CLI), HOME//tmp only, ≤100KB, never ~/.ssh, ~/.gnupg, /etc, /usr. shell hard-refuses rm -rf /, mkfs, dd to devices, fork bombs even with approval. read_url/web_search block localhost/private IPs. API keys chmod 600, masked in output.

Tests

uv run --python 3.12 --with ".[test]" pytest tests -q   # 256 passed: unit + regression + Textual pilot, no Ollama needed

The eval harness (tests/test_eval.py) locks in every past quality bug as an offline regression test. A suite-wide fixture guarantees tests never touch your live ~/.sidekick/.

Config

~/.sidekick/config.toml (provider, model, base_url override, api_key, …). Env overrides: SIDEKICK_PROVIDER, SIDEKICK_MODEL, SIDEKICK_BASE_URL, SIDEKICK_API_KEY. Data stays home: history.db, skills/, nudges.log, input_history, tui-errors.log.

Per-project config: a .sidekick.toml in any repo layers over the global file (nearest one walking up from cwd). It may set provider, model, max_steps, temperature, plus a [project] table (docs files injected into the prompt, memory_namespace, approved_commands for shell). api_key/base_url are never read from project files (global/env only) — sk config --show prints the active project and any ignored keys. sk --cwd PATH runs any command as if in that directory.

Roadmap

See ROADMAP.md — the shared plan (vision, v0.2.0 / v0.3.0 milestones, done list). It changes by pull request only.

License

MIT — do what you want, shout-outs appreciated.