PacificaPilot 🤖⚡
AI trading agent for Pacifica Perpetual Futures — with persistent memory, multi-provider AI, and natural language trading.
pip install pacificapilot
pacifica init
pacifica start
Features
- Persistent memory — Every trade, pattern, and preference stored in Supermemory across sessions
- Agentic chat — Multi-turn tool loop: gathers data, reasons, then responds
- Autonomous loop agent — 24/7 AI-driven market monitoring
- 9 trading tools — place/close orders, market analysis, performance metrics, regime detection
- Live technical analysis — RSI, MACD, Bollinger Bands, funding, volume, market regime
- Multi-provider AI — Anthropic, OpenAI, Google Gemini, OpenRouter (BYOK)
- Textual TUI — 3-panel layout with slash autocomplete, live sidebar, keyboard shortcuts
- Non-custodial — Your keys, your machine. Nothing leaves.
- Dual-mode memory — Local (
localhost:6767) or cloud (Supermemory API)
Quick Start
# Install
pip install pacificapilot
# Setup wizard
pacifica init
# → Pacifica keys → AI provider → Trading config → Supermemory → Telegram
# Launch TUI
pacifica start
Inside the TUI:
- Type
/helpfor commands, or just chat naturally /startboots the Loop Agent,/stopstops it/configto view/edit settings/apikey supermemory <key> [local|cloud]
Keyboard shortcuts
Ctrl+P — Command palette Ctrl+M — Switch AI provider
Ctrl+S — Settings toggles Ctrl+L — Clear chat
Ctrl+R — Refresh sidebar Ctrl+D — Toggle dry run
Ctrl+K — API key management Ctrl+T — Mode switch
Ctrl+Q — Quit
Example
You: how are BTC markets right now?
Agent: BTC — $63,996
Regime: Weak uptrend (MACD bullish)
RSI 5m: 35 (leaning oversold) | RSI 1h: 51 (neutral)
Bollinger: Upper half, bandwidth 4.2%
→ NEUTRAL with slight bullish bias. No clear entry.
Architecture
Chat Agent (tool loop) ←→ Trading Core ←→ Pacifica API
↕ ↕
Loop Agent (autonomous) Supermemory
↕
Textual TUI (3-panel)
Tools
place_order · close_position · close_all_positions · get_positions · get_account_balance · get_market_price (enriched) · get_trade_history · get_performance_metrics · get_market_regime
Supermemory
Every AI decision, market pattern, user preference, and daily summary is stored in Supermemory — a persistent, searchable memory layer that survives restarts.
decisions → "LONG BTC, confidence 75%, RSI 35"
patterns → "Funding spike on ETH: 0.003"
preferences → "Never trade BONK" — said once, remembered forever
performance → "Daily: 3 trades, +$12.50, 67% win rate"
Two modes:
- Cloud:
https://app.supermemory.ai(default) - Local:
npx supermemory local(offline, zero data leaves your machine)
Security
- Non-custodial — Keys stored in
~/.pacificapilot/secrets.env(chmod 600) - BYOK — Your AI keys go directly to your provider
- Confirmation prompts — Every trade requires explicit yes/no
- Testnet first — Dry run by default, mainnet with confirmation
Links
Disclaimer: PacificaPilot is experimental software for educational purposes. Trading perpetual futures carries significant risk. AI decisions are not financial advice. Start with testnet.
Metadata
Release files for pacificapilot 0.1.0
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 |
|---|---|---|---|---|
| pacificapilot-0.1.0.tar.gz | 107.5 kB | With provenance | Details for pacificapilot-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pacificapilot-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for pacificapilot-0.1.0-py3-none-any.whl |
Total release size: 233.6 kB
Release files / pacificapilot-0.1.0.tar.gz
| Download URL | pacificapilot-0.1.0.tar.gz |
|---|---|
| Size | 107.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c16d8fd7254a652c3a32203253a771b6ca73b52a2e50ae705a1727609dc8d84f
|
|
BLAKE2b-256 checksum How to use checksums |
c8a452d5ebf4c7cd7c6c2016ed51bceb5232f2550d16f78fe4e315f06f851656
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logRelease files / pacificapilot-0.1.0-py3-none-any.whl
| Download URL | pacificapilot-0.1.0-py3-none-any.whl |
|---|---|
| Size | 126.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8f988379919777feee1cb92eeefae71fe808a0c36aa8de22108c35fb795c3059
|
|
BLAKE2b-256 checksum How to use checksums |
7dc1f24f011a87a3c2fb7cf3461c6fcde154a5447f27a3955e2000f6296c2c90
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logSecurity for pacificapilot 0.1.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for pacificapilot-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logA 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.