"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Python
docs: add ComfyUI harness to README
Andrew Barnesa6cc783dd751
diff --git a/README.md b/README.mdindex c2bd6fa7a..34b266fa6 100644--- a/README.md+++ b/README.md@@ -7,8 +7,8 @@ CLI-Anything: Bridging the Gap Between AI Agents and the World's Software</stron<p align="center"><a href="#-quick-start"><img src="https://img.shields.io/badge/Quick_Start-5_min-blue?style=for-the-badge" alt="Quick Start"></a>- <a href="#-demonstrations"><img src="https://img.shields.io/badge/Demos-11_Apps-green?style=for-the-badge" alt="Demos"></a>- <a href="#-test-results"><img src="https://img.shields.io/badge/Tests-1%2C508_Passing-brightgreen?style=for-the-badge" alt="Tests"></a>+ <a href="#-demonstrations"><img src="https://img.shields.io/badge/Demos-12_Apps-green?style=for-the-badge" alt="Demos"></a>+ <a href="#-test-results"><img src="https://img.shields.io/badge/Tests-1%2C578_Passing-brightgreen?style=for-the-badge" alt="Tests"></a><a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge" alt="License"></a></p>@@ -320,7 +320,7 @@ AI agents are great at reasoning but terrible at using real professional softwar| πΈ "UI automation breaks constantly" | No screenshots, no clicking, no RPA fragility. Pure command-line reliability with structured interfaces || π "Agents need structured data" | Built-in JSON output for seamless agent consumption + human-readable formats for debugging || π§ "Custom integrations are expensive" | One Claude plugin auto-generates CLIs for ANY codebase through proven 7-phase pipeline |-| β‘ "Prototype vs Production gap" | 1,508+ tests with real software validation. Battle-tested across 11 major applications |+| β‘ "Prototype vs Production gap" | 1,578+ tests with real software validation. Battle-tested across 12 major applications |---@@ -409,7 +409,7 @@ All CLIs organized under cli_anything.* namespace β conflict-free, pip-installCLI-Anything works on any software with a codebase β no domain restrictions or architectural limitations.### π Professional-Grade Testing-Tested across 11 diverse, complex applications spanning creative, productivity, communication, diagramming, and AI content generation domains previously inaccessible to AI agents.+Tested across 12 diverse, complex applications spanning creative, productivity, communication, diagramming, AI image generation, and AI content generation domains previously inaccessible to AI agents.### π¨ Diverse Domain CoverageFrom creative workflows (image editing, 3D modeling, vector graphics) to production tools (audio, office, live streaming, video editing).@@ -503,12 +503,19 @@ Each application received complete, production-ready CLI interfaces β not demo<td align="center">β 50</td></tr><tr>+<td align="center"><strong>πΌοΈ ComfyUI</strong></td>+<td>AI Image Generation</td>+<td><code>cli-anything-comfyui</code></td>+<td>ComfyUI REST API</td>+<td align="center">β 70</td>+</tr>+<tr><td align="center" colspan="4"><strong>Total</strong></td>-<td align="center"><strong>β 1,508</strong></td>+<td align="center"><strong>β 1,578</strong></td></tr></table>-> **100% pass rate** across all 1,508 tests β 1,073 unit tests + 435 end-to-end tests.+> **100% pass rate** across all 1,578 tests β 1,133 unit tests + 445 end-to-end tests.---@@ -536,8 +543,9 @@ shotcut 154 passed β (110 unit + 44 e2e)zoom 22 passed β (22 unit + 0 e2e)drawio 138 passed β (116 unit + 22 e2e)anygen 50 passed β (40 unit + 10 e2e)+comfyui 70 passed β (60 unit + 10 e2e)ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ-TOTAL 1,508 passed β 100% pass rate+TOTAL 1,578 passed β 100% pass rate```---@@ -596,7 +604,8 @@ cli-anything/βββ π¬ shotcut/agent-harness/ # Shotcut CLI (154 tests)βββ π zoom/agent-harness/ # Zoom CLI (22 tests)βββ π drawio/agent-harness/ # Draw.io CLI (138 tests)-βββ β¨ anygen/agent-harness/ # AnyGen CLI (50 tests)+βββ β¨ anygen/agent-harness/ # AnyGen CLI (50 tests)+βββ πΌοΈ comfyui/agent-harness/ # ComfyUI CLI (70 tests)```Each `agent-harness/` contains an installable Python package under `cli_anything.<software>/` with Click CLI, core modules, utils (including `repl_skin.py` and backend wrapper), and comprehensive tests.@@ -697,7 +706,7 @@ HARNESS.md is our definitive SOP for making any software agent-accessible via auIt encodes proven patterns and methodologies refined through automated generation processes.-The playbook distills key insights from successfully building all 11 diverse, production-ready harnesses.+The playbook distills key insights from successfully building all 12 diverse, production-ready harnesses.### Critical Lessons@@ -822,7 +831,7 @@ MIT License β free to use, modify, and distribute.**CLI-Anything** β *Make any software with a codebase Agent-native.*-<sub>A methodology for the age of AI agents | 11 professional software demos | 1,508 passing tests</sub>+<sub>A methodology for the age of AI agents | 12 professional software demos | 1,578 passing tests</sub><br>