:PROPERTIES:
:ID:       3aa22300-2f25-57b0-8787-9f199cc978b1
:CREATED:  [2026-05-22 Thu]
:END:
#+title: Competitive Analysis — AI Agent Landscape
#+filetags: :passepartout:strategy:competitive:

* Overview

Analyzed 9 competitor codebases alongside Passepartout. The competitive landscape
divides into three categories:

1. Coding agents — Aider, OpenCode, Codex CLI, Claude Code, Gemini CLI
2. Personal AI assistants — [[id:c652688a-1ea0-487c-9222-00e954efe8a1][Hermes Agent]], OpenClaw, [[id:416bab7c-4300-4d50-838a-5c7a8ad45d96][Thoth]]
3. CI/check-based systems — Continue

None of the nine compete with Passepartout on all axes simultaneously. Passepartout's
strongest differentiators — Org-mode data model, deterministic gate stack, ACL2
verification, Merkle-treed memory, and the [[id:1c3ec48b-446c-50d2-b53e-126a81f5143f][Passepartout architecture]] — are absent from
every competitor.

* Category 1: Coding Agents

- [[id:c3aab2e8-7e43-4abc-93f0-741675cfd78c][Aider]] — Python, ~40K lines, MIT. Oldest open-source coding agent. Chat-based Coder class with 5 edit formats. Purely prompt-based safety.
- [[id:7a060b36-36db-4eb7-b8cc-844bd6ac9d36][OpenCode]] — TypeScript/Bun, 163K★. Dominant open-source coding agent. Dual LLM runtime, ACP inter-agent protocol, SQLite state.
- [[id:e929ff32-28d8-4a29-bf74-d55babc040d1][Codex CLI]] — Rust, ~950K lines, OpenAI. Strongest sandboxing (Seatbelt/nsjail). Execution policy engine. No knowledge graph.
- [[id:512dd121-2292-4f3d-ac53-31bf3d12a60f][Claude Code]] — TypeScript/Bun, ~512K lines leaked. Most mature safety system (2,592 lines bash security). 7 permission modes. Proprietary.
- [[id:8d73ccb9-34e4-4899-b0c3-605998e9bebc][Gemini CLI]] — TypeScript, ~525K lines, Apache 2.0. CONSECA AI-driven policy generation. 6 sandbox methods. Google-locked.

* Category 2: Personal AI Assistants

- [[id:c652688a-1ea0-487c-9222-00e954efe8a1][Hermes Agent]] — Python, ~17K core, MIT. Running this conversation. 109+ providers, 15+ messaging platforms, MCP client. Heuristic safety layers.
- [[id:85ca69dd-d085-4a55-ad11-021910b1f82e][OpenClaw]] — TypeScript/Node.js, ~3.5M lines. Largest codebase. 25+ messaging channels, 135 bundled plugins. Tiered sandboxing.
- [[id:416bab7c-4300-4d50-838a-5c7a8ad45d96][Thoth]] — Python, ~151K lines, Apache 2.0. Personal knowledge graph (11 entity types, 67 relations, NetworkX+FAISS). LangGraph ReAct agent. Developer Studio.

* Category 3: CI/Check Systems

- [[id:22d0a159-68a2-4587-9375-5046beddc20c][Continue]] — TypeScript, ~328K lines, Apache 2.0. Source-controlled AI checks for CI/CD. Markdown-as-gate-policy. No persistent agent.

* The Passepartout Advantage

| Dimension | Passepartout | Best Competitor | Gap |
|-----------|--------------|-----------------|-----|
| Safety model | Type-level gates + 11-vector deterministic stack | Claude Code (7 permission modes + 23 bash checks) | Structural vs heuristic. Passepartout's type-level gates prevent self-modification at the category level; competitors block patterns. |
| Knowledge model | Org-mode (tree, properties, TODOs, timestamps, cross-refs, IDs, tags) | Claude Code (flat markdown memdir) | Org-mode's semantic richness is ~15 primitives markdown doesn't have. |
| Memory integrity | Merkle tree + SHA-256 + rollback | Hermes (file-based); Claude Code (flat files + git) | Content-addressed, tamper-evident memory no competitor has. |
| Self-verification | ACL2 → CIC prover (planned) | None | No competitor does provable correctness. |
| Cognitive architecture | 10-80-10 symbolic-first (planned) | 100% LLM (every competitor) | Post-flip, Passepartout uses ~10% of the tokens competitors use. |
| Data format | Org-mode (human-editable, machine-parseable, single file) | JSONL/Markdown/YAML/DB (competitors use 2-5 formats) | Unified format reduces translation layers to zero. |
| Self-modification | Type-level gates + hot-reload | Claude Code (skills), Hermes (skills) | Passepartout's guard against self-modification is structural (type level), not heuristic (pattern list). |
| Architecture | Passepartout ([[id:c3b3dc41-945f-54e9-84eb-ca014114f1be][environment subsystem]] + [[id:1d074690-a279-59cb-b91d-e9a22ae104ad][social protocol]]) | None | No competitor is building a full computing stack + social network. |
| Provider independence | Any OpenAI-compatible API | Hermes (109+), Gemini CLI (1 primary) | Comparable to Hermes, better than most. |

* Where Competitors Lead

| Dimension | Leader | Passepartout Status |
|-----------|--------|---------------------|
| Safety implementation maturity | Claude Code (2,592 lines bash security) | Gate stack exists but bash validation is minimal in comparison |
| Provider breadth | Hermes (109+), OpenClaw (50+) | 8 providers — adequate but not competitive |
| Channel/platform support | OpenClaw (25+ channels) | TUI only — no multi-channel |
| Plugin ecosystem | OpenClaw (ClawHub, npm registry) | No plugin marketplace |
| Subagent delegation | Claude Code (fork with context inheritance) | Planned via Screamer planner |
| Codebase size / features shipped | All competitors have working products | In development |
| MCP integration | Hermes, Codex (native), Continue | Planned |
| Sandboxing | Codex CLI (Seatbelt+nsjail), Gemini CLI (6 methods) | None |
| Business model | Hermes (MIT+services), Codex (tokens) | AGPL + appliances + SaaS |
| Cross-platform | Claude Code (macOS/*nix), Codex (macOS) | Linux only |

* Strategic Positioning

Passepartout is not competing in the existing AI agent market. It is building a
new category: provable personal infrastructure.

Competitors optimize for:
- Token efficiency (Aider's edit formats, OpenCode's LSP integration)
- Model flexibility (Hermes' 109 providers)
- Platform reach (OpenClaw's 25 channels)
- UI polish (Gemini CLI's Ink/React, Claude Code's permission dialogs)
- Sandbox security (Codex's Seatbelt, Gemini's gVisor)

Passepartout optimizes for:
- Provable correctness (ACL2 → CIC)
- Data integrity (Merkle tree)
- Cognitive architecture (10-80-10 symbolic-first)
- Safety by construction (type-level gates)
- Unified data model (Org-mode as everything)
- Network effects (social protocol)
- Full-stack ownership (environment subsystem)

These are not axes any competitor cares about. The risk is not that a competitor
builds a better Passepartout — it's that the market never develops a preference
for provable agents. If token-burning LLM agents remain the default and users
don't demand verification, the entire category Passepartout addresses may not
exist yet.

* Immediate Implications for Development

1. Claude Code's safety system is the benchmark to exceed. The type-level gate
   architecture is theoretically superior to Claude Code's heuristic patterns,
   but the implementation needs to prove it catches things Claude Code misses.

2. No competitor has anything resembling a neurosymbolic architecture. The 10-80-10
   plan has zero competition — but that also means zero market validation.

3. The Org-mode bet is invisible to competitors. They don't see the advantage
   because they've never tried to build a knowledge graph from flat markdown files.
   This is Passepartout's widest moat — it depends on a skill (Org-mode literate
   programming) that no competitor's team has.

4. Hermes is the closest full-stack competitor (tools, skills, cron, subagents,
   multi-platform), but architecturally conventional.

5. The coding agents (Aider, OpenCode, Codex) are not competitors — they are
   single-purpose tools Passepartout could eventually replace entirely when the
   planner matures.

* File references

Repository dumps and analysis artifacts at /tmp/:
- /tmp/aider/ — Aider source (Python)
- /tmp/opencode/ — OpenCode archived source  
- /tmp/codex/ — OpenAI Codex CLI (Rust)
- /tmp/claude-code-leaked-source/ — Claude Code leaked (TypeScript/Bun)
- /tmp/gemini-cli/ — Google Gemini CLI (TypeScript)
- /tmp/openclaw/ — OpenClaw source (TypeScript)
- /tmp/thoth/ — Thoth source (Python)
- /tmp/continue/ — Continue source (TypeScript)
- /usr/local/lib/hermes-agent/ — Hermes Agent (Python)