"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
Python
Merge remote-tracking branch 'upstream/main' into codex/nsight-graphics-agent-harness
aimidi8ac706575df2
diff --cc .gitignoreindex 24a99465a,a36b1d0bd..47ca0e880--- a/.gitignore+++ b/.gitignore@@@ -99,7 -99,7 +99,8 @@@!/n8n/!/obsidian/!/unrealinsights/+!/nsight-graphics/+ !/lldb/# Step 5: Inside each software dir, ignore everything (including dotfiles)/gimp/*@@@ -184,8 -184,8 +185,10 @@@/obsidian/.*/unrealinsights/*/unrealinsights/.*+/nsight-graphics/*+/nsight-graphics/.*+ /lldb/*+ /lldb/.*# Step 6: ...except agent-harness/!/gimp/agent-harness/@@@ -235,7 -235,7 +238,8 @@@!/safari/!/safari/agent-harness/!/unrealinsights/agent-harness/+!/nsight-graphics/agent-harness/+ !/lldb/agent-harness/# Step 7: Ignore build artifacts within allowed dirs**/__pycache__/diff --cc README.mdindex 47c94604d,7951ec53d..0bd2fed71--- a/README.md+++ b/README.md@@@ -14,8 -14,8 +14,8 @@@ CLI-Anything: Bridging the Gap Between<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="https://hkuds.github.io/CLI-Anything/"><img src="https://img.shields.io/badge/CLI_Hub-Browse_%26_Install-ff69b4?style=for-the-badge" alt="CLI Hub"></a>-- <a href="#-demonstrations"><img src="https://img.shields.io/badge/Demos-17_Apps-green?style=for-the-badge" alt="Demos"></a>- <a href="#-test-results"><img src="https://img.shields.io/badge/Tests-2%2C242_Passing-brightgreen?style=for-the-badge" alt="Tests"></a>- <a href="#-test-results"><img src="https://img.shields.io/badge/Tests-2%2C229_Passing-brightgreen?style=for-the-badge" alt="Tests"></a>++ <a href="#-demonstrations"><img src="https://img.shields.io/badge/Demos-18_Apps-green?style=for-the-badge" alt="Demos"></a>++ <a href="#-test-results"><img src="https://img.shields.io/badge/Tests-2%2C269_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>@@@ -596,7 -596,7 +596,7 @@@ AI agents are great at reasoning but te| 💸 "UI automation breaks constantly" | No screenshots, no clicking, no RPA fragility. Pure command-line reliability with structured interfaces || 📊 "Agents need structured data" | Built-in JSON output for seamless agent consumption + human-readable formats for debugging || 🔧 "Custom integrations are expensive" | One Claude plugin auto-generates CLIs for ANY codebase through proven 7-phase pipeline |- | ⚡ "Prototype vs Production gap" | 2,242+ tests with real software validation. Battle-tested across 17 major applications |-| ⚡ "Prototype vs Production gap" | 2,229+ tests with real software validation. Battle-tested across 17 major applications |++| ⚡ "Prototype vs Production gap" | 2,269+ tests with real software validation. Battle-tested across 18 major applications |---@@@ -755,7 -755,7 +755,7 @@@ An agent uses the VideoCaptioner CLI tCLI-Anything works on any software with a codebase — no domain restrictions or architectural limitations.### 🏭 Professional-Grade Testing--Tested across 16 diverse, complex applications spanning creative, productivity, communication, diagramming, AI image generation, AI content generation, network ad blocking, and local LLM inference domains previously inaccessible to AI agents.++Tested across 18 diverse, complex applications spanning creative, productivity, communication, diagramming, AI image generation, AI content generation, network ad blocking, local LLM inference, native debugging, and graphics profiling domains previously inaccessible to AI agents.### 🎨 Diverse Domain CoverageFrom creative workflows (image editing, 3D modeling, vector graphics) to production tools (audio, office, live streaming, video editing).@@@ -968,13 -968,13 +968,20 @@@ Each application received complete, pro<td align="center">✅ 24</td></tr><tr>+ <td align="center"><strong>🐞 <a href="lldb/agent-harness/">LLDB</a></strong></td>+ <td>Native Debugging</td>+ <td><code>cli-anything-lldb</code></td>+ <td>LLDB Python API</td>+ <td align="center">✅ 27</td>+ </tr>+ <tr>+<td align="center"><strong>🟩 <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td>+<td>GPU Debugging & Profiling</td>+<td><code>cli-anything-nsight-graphics</code></td>+<td>Official ngfx / ngfx-capture orchestration + GPU Trace summary</td>+<td align="center">✅ 40</td>+</tr>+<tr><td align="center"><strong>🔍 <a href="exa/agent-harness/">Exa</a></strong></td><td>AI-Native Web Search</td><td><code>cli-anything-exa</code></td>@@@ -1004,11 -1004,11 +1011,11 @@@</tr><tr><td align="center" colspan="4"><strong>Total</strong></td>- <td align="center"><strong>✅ 2,242</strong></td>-<td align="center"><strong>✅ 2,229</strong></td>++<td align="center"><strong>✅ 2,269</strong></td></tr></table>- > **100% pass rate** across all 2,242 tests — 1,649 unit tests + 574 end-to-end tests + 19 Node.js tests.-> **100% pass rate** across all 2,229 tests — 1,636 unit tests + 574 end-to-end tests + 19 Node.js tests.++> **100% pass rate** across all 2,269 tests — 1,672 unit tests + 578 end-to-end tests + 19 Node.js tests.---@@@ -1047,11 -1047,11 +1054,12 @@@ sketch 19 passed ✅ (19 jesrenderdoc 59 passed ✅ (45 unit + 14 e2e)cloudcompare 88 passed ✅ (49 unit + 39 e2e)openscreen 101 passed ✅ (78 unit + 23 e2e)+ lldb 27 passed ✅ (23 unit + 4 e2e)+nsight-graphics 40 passed ✅ (36 unit + 4 e2e)unrealinsights 50 passed ✅ (49 unit + 1 e2e, 9 backend-gated e2e skipped)cloudanalyzer 14 passed ✅ (7 unit + 7 e2e)──────────────────────────────────────────────────────────────────────────────- TOTAL 2,242 passed ✅ 100% pass rate-TOTAL 2,229 passed ✅ 100% pass rate++TOTAL 2,269 passed ✅ 100% pass rate```---@@@ -1125,7 -1125,7 +1133,8 @@@ cli-anything├── 🎮 godot/agent-harness/ # Godot Engine CLI (24 tests)├── 🎨 sketch/agent-harness/ # Sketch CLI (19 tests, Node.js)├── 🔬 renderdoc/agent-harness/ # RenderDoc CLI (59 tests)+├── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI (40 tests)+ ├── 🐞 lldb/agent-harness/ # LLDB CLI (27 tests)├── 📈 unrealinsights/agent-harness/ # Unreal Insights CLI (50 tests)├── 🎬 videocaptioner/agent-harness/ # VideoCaptioner CLI (26 tests)├── 🎬 openscreen/agent-harness/ # Openscreen CLI — screen recording editor (101 tests)@@@ -1232,7 -1232,7 +1241,7 @@@ HARNESS.md is our definitive SOP for maIt encodes proven patterns and methodologies refined through automated generation processes.--The playbook distills key insights from successfully building all 17 diverse, production-ready harnesses.++The playbook distills key insights from successfully building all 18 diverse, production-ready harnesses.### Critical Lessons@@@ -1357,7 -1357,7 +1366,7 @@@ MIT License — free to use, modify, an**CLI-Anything** — *Make any software with a codebase Agent-native.*- <sub>A methodology for the age of AI agents | 17 professional software demos | 2,242 passing tests</sub>-<sub>A methodology for the age of AI agents | 17 professional software demos | 2,229 passing tests</sub>++<sub>A methodology for the age of AI agents | 18 professional software demos | 2,269 passing tests</sub><br>diff --cc README_CN.mdindex 67cd66ba7,6c9bfaaba..f66cca05b--- a/README_CN.md+++ b/README_CN.md@@@ -9,8 -9,8 +9,8 @@@ CLI-Anything:连接 AI Agent 与全�<p align="center"><a href="#-快速上手"><img src="https://img.shields.io/badge/快速上手-5_分钟-blue?style=for-the-badge" alt="Quick Start"></a>-- <a href="#-实测展示"><img src="https://img.shields.io/badge/Demo-11_款软件-green?style=for-the-badge" alt="Demos"></a>-- <a href="#-测试结果"><img src="https://img.shields.io/badge/测试-1%2C508_通过-brightgreen?style=for-the-badge" alt="Tests"></a>++ <a href="#-实测展示"><img src="https://img.shields.io/badge/Demo-13_款软件-green?style=for-the-badge" alt="Demos"></a>++ <a href="#-测试结果"><img src="https://img.shields.io/badge/测试-1%2C741_通过-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>@@@ -374,7 -374,7 +374,7 @@@ AI Agent 推理能力很强,但操控| 💸 "GUI 自动化三天两头崩" | 告别截图、点击和 RPA 的脆弱性,纯命令行操控,结构化接口 || 📊 "Agent 需要结构化数据" | 内置 JSON 输出供 Agent 直接消费,同时保留可读格式方便调试 || 🔧 "定制集成太贵了" | 一个插件就能为任意代码库自动生成 CLI,经过验证的 7 阶段流水线 |- | ⚡ "原型和生产之间差十万八千里" | 1,714+ 测试用例,全部在真实软件上验证通过,覆盖 12 款主流应用 |-| ⚡ "原型和生产之间差十万八千里" | 1,701+ 测试用例,全部在真实软件上验证通过,覆盖 12 款主流应用 |++| ⚡ "原型和生产之间差十万八千里" | 1,741+ 测试用例,全部在真实软件上验证通过,覆盖 13 款主流应用 |---@@@ -471,7 -471,7 +471,7 @@@ CLI-Anything 适用于任何有代码�### 🏭 专业级测试--在 12 款复杂应用上进行了实测,涵盖创意、生产力、通信、图表和 AI 内容生成领域 —— 这些软件此前对 AI Agent 来说几乎不可触及。++在 13 款复杂应用上进行了实测,涵盖创意、生产力、通信、图表、原生调试、GPU 分析和 AI 内容生成领域 —— 这些软件此前对 AI Agent 来说几乎不可触及。### 🎨 覆盖多元领域@@@ -581,13 -581,13 +581,20 @@@<td align="center">✅ 50</td></tr><tr>+ <td align="center"><strong>🐞 <a href="lldb/agent-harness/">LLDB</a></strong></td>+ <td>原生调试</td>+ <td><code>cli-anything-lldb</code></td>+ <td>LLDB Python API</td>+ <td align="center">✅ 27</td>+ </tr>+ <tr>+<td align="center"><strong>🟩 <a href="nsight-graphics/agent-harness/">Nsight Graphics CLI</a></strong></td>+<td>GPU 调试与分析</td>+<td><code>cli-anything-nsight-graphics</code></td>+<td>官方 ngfx / ngfx-capture 编排 + GPU Trace 摘要</td>+<td align="center">✅ 40</td>+</tr>+<tr><td align="center"><strong>📈 <a href="unrealinsights/agent-harness/">Unreal Insights</a></strong></td><td>性能分析</td><td><code>cli-anything-unrealinsights</code></td>@@@ -603,11 -603,11 +610,11 @@@</tr><tr><td align="center" colspan="4"><strong>合计</strong></td>- <td align="center"><strong>✅ 1,714</strong></td>-<td align="center"><strong>✅ 1,701</strong></td>++<td align="center"><strong>✅ 1,741</strong></td></tr></table>- > 全部 1,714 项测试 **100% 通过** —— 1,233 项单元测试 + 462 项端到端测试 + 19 项 Node.js 测试。-> 全部 1,701 项测试 **100% 通过** —— 1,220 项单元测试 + 462 项端到端测试 + 19 项 Node.js 测试。++> 全部 1,741 项测试 **100% 通过** —— 1,256 项单元测试 + 466 项端到端测试 + 19 项 Node.js 测试。---@@@ -636,11 -636,11 +643,12 @@@ openscreen 101 passed ✅ (78 unizoom 22 passed ✅ (22 unit + 0 e2e)drawio 138 passed ✅ (116 unit + 22 e2e)anygen 50 passed ✅ (40 unit + 10 e2e)+ lldb 27 passed ✅ (23 unit + 4 e2e)+nsight-graphics 40 passed ✅ (36 unit + 4 e2e)unrealinsights 50 passed ✅ (49 unit + 1 e2e, 9 backend-gated e2e skipped)sketch 19 passed ✅ (19 jest, Node.js)──────────────────────────────────────────────────────────────────────────────- TOTAL 1,714 passed ✅ 100% pass rate-TOTAL 1,701 passed ✅ 100% pass rate++TOTAL 1,741 passed ✅ 100% pass rate```---@@@ -707,7 -707,7 +715,8 @@@ cli-anything├── 📞 zoom/agent-harness/ # Zoom CLI(22 项测试)├── 📐 drawio/agent-harness/ # Draw.io CLI(138 项测试)├── ✨ anygen/agent-harness/ # AnyGen CLI(50 项测试)+├── 🟩 nsight-graphics/agent-harness/ # Nsight Graphics CLI(40 项测试)+ ├── 🐞 lldb/agent-harness/ # LLDB CLI(27 项测试)├── 📈 unrealinsights/agent-harness/ # Unreal Insights CLI(50 项测试)└── 🎨 sketch/agent-harness/ # Sketch CLI(19 项测试,Node.js)```@@@ -811,7 -811,7 +820,7 @@@ HARNESS.md 是我们通过自动化 CL它记录了在自动化生成过程中经验证并沉淀出的模式与方法论。--这本手册提炼了成功构建全部 12 套生产级 CLI 的关键经验。++这本手册提炼了成功构建全部 13 套生产级 CLI 的关键经验。### 核心经验@@@ -945,7 -945,7 +954,7 @@@ MIT License — 可自由使用、修�**CLI-Anything** — *一行命令,让任何软件成为 Agent 的原生工具。*- <sub>为 AI Agent 时代而生 | 12 款专业软件实测 | 1,714 项测试全部通过</sub>-<sub>为 AI Agent 时代而生 | 12 款专业软件实测 | 1,701 项测试全部通过</sub>++<sub>为 AI Agent 时代而生 | 13 款专业软件实测 | 1,741 项测试全部通过</sub><br>