Amr Gharbeia 26bfce61f1
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
fix: CLI test, TUI integration harness — all non-blockers resolved
- gateway-cli: add load-time sanity check, fix FiveAM prefix for
  jailed-package compatibility
- TUI integration: switch all tests from file-grep to tmux capture-pane
  (agent-responds, cascade-failure, eval-command, connection-drop).
  Fixes file-buffering false negatives. Increase eval sleep to 3s.
- Cherry-pick: system-integration-tests.org org source updated
2026-05-05 20:58:41 -04:00

Passepartout — Your Autonomous, Plain-Text Life Assistant

Passepartout is an AI assistant that runs in your terminal, reads and writes your Org-mode files, executes tasks through a verified safety gate, and works fully offline with local LLMs. Everything it knows is a folder of plain text files that you own.

One-line install:

curl -fsSL https://raw.githubusercontent.com/amrgharbeia/opencortex/main/passepartout | bash -s configure

Then passepartout tui to start chatting.

Quick Start

You need SBCL (Common Lisp), git, and curl.

git clone https://github.com/amrgharbeia/opencortex.git ~/projects/passepartout
cd ~/projects/passepartout
./passepartout configure       # install deps, tangle, setup wizard
passepartout tui                # launch the terminal interface

See User Manual for the full guide.

Why Passepartout

Your data stays yours.** No database, no vector store, no cloud silo. Your entire memory is a folder of Org files. You can read them with any text editor, search them with grep, and back them up however you like. If Passepartout stops existing, your data doesn't disappear.

The LLM can't do damage.** Every action the LLM proposes passes through a deterministic safety gate before it touches a file, runs a command, or sends a message. The LLM suggests; the gate decides. Hallucinations are blocked, not corrected after the fact.

Runs on your hardware.** Works fully offline with Ollama and local models. Cloud providers (OpenRouter, OpenAI, Anthropic, Groq, Gemini, DeepSeek, NVIDIA NIM) are optional add-ons.

Written in Common Lisp.** Code is data. The agent reads its own source the same way it reads a text file — it parses, modifies, and hot-reloads its skills without restarting. One language from the kernel to the TUI to the build system.

Architecture

  • Metabolic Loop — Perceive → Reason → Act, the fundamental cognitive cycle
  • Dispatcher — 9-vector safety gate: secret scanning, path protection, shell safety, lisp validation, network exfiltration, privacy filtering
  • Memory — Single-address-space object store with Merkle-tree integrity and snapshot rollback
  • Skill Engine — 20 hot-reloadable skills loaded at boot, each an independent Org file
  • TUI — Croatoan-based terminal interface connected via framed TCP protocol
  • LLM Dispatch — Central dispatch for model inference requests

Project Documentation

Document Answers
User Manual How do I use it?
Architecture How does it work inside?
Design Decisions Why was it built this way?
Roadmap Where is it going? When?
TODO Who is doing what?
Contributing How do I contribute?

License

Passepartout is released under the AGPLv3 license. See CLA.org for the Contributor License Agreement.

Description
No description provided
Readme AGPL-3.0 62 MiB
Languages
Shell 67.5%
Emacs Lisp 19.1%
Common Lisp 9.6%
C 2.2%
Dockerfile 1.6%