📦 Entities on LLM Wiki — Agentic AI Landscapehttps://blog.imfsoftware.com/llm-wiki/docs/entities/Recent content in 📦 Entities on LLM Wiki — Agentic AI LandscapeHugoen-us<link>https://blog.imfsoftware.com/llm-wiki/docs/entities/andrej-karpathy/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/andrej-karpathy/</guid><description><h1 id="andrej-karpathy">Andrej Karpathy<a class="anchor" href="#andrej-karpathy">#</a></h1> <p>AI researcher and educator. Former Director of AI at Tesla, founding member of OpenAI. Known for neural network education (cs231n, Zero to Hero series) and practical AI tooling.</p> <h2 id="relevant-work">Relevant Work<a class="anchor" href="#relevant-work">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/sources/llm-wiki-karpathy/">llm-wiki-karpathy</a> — The LLM Wiki pattern: using LLMs to incrementally build and maintain personal knowledge bases. The foundational idea behind this wiki.</li> </ul> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/llm-wiki-pattern/">llm-wiki-pattern</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/anthropic/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/anthropic/</guid><description><h1 id="anthropic">Anthropic<a class="anchor" href="#anthropic">#</a></h1> <p>AI safety company. Builds the Claude family of models and <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a>.</p> <h2 id="related-projects">Related Projects<a class="anchor" href="#related-projects">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a> — Agentic coding tool (terminal, IDE, web, Slack, GitHub)</li> </ul> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/mcp-protocol/">mcp-protocol</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/aws/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/aws/</guid><description><h1 id="aws">AWS<a class="anchor" href="#aws">#</a></h1> <p>Amazon Web Services. Cloud computing platform by Amazon.</p> <h2 id="related-projects">Related Projects<a class="anchor" href="#related-projects">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/kiro/">kiro</a> — Agentic IDE with autonomous agent capabilities</li> <li>Defines the concept of <a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/frontier-agent/">frontier-agent</a>s</li> </ul> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/kiro/">kiro</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/frontier-agent/">frontier-agent</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/bmad-method/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/bmad-method/</guid><description><h1 id="bmad-method">BMad Method<a class="anchor" href="#bmad-method">#</a></h1> <p>AI-driven agile development framework with scale-adaptive intelligence. &ldquo;Build More Architect Dreams.&rdquo; MIT licensed.</p> <p>&ldquo;Traditional AI tools do the thinking for you. BMad agents guide you through a structured process to bring out your best thinking.&rdquo;</p> <h2 id="core-features">Core Features<a class="anchor" href="#core-features">#</a></h2> <ul> <li><strong>12+ specialized agent personas</strong>: PM, Architect, Developer, UX, and more</li> <li><strong>34+ structured workflows</strong>: Grounded in agile best practices</li> <li><strong>Scale-Domain-Adaptive</strong>: Adjusts planning depth from bug fixes to enterprise systems</li> <li><strong>Party Mode</strong>: Multiple agent personas collaborate in one session</li> <li><strong>bmad-help</strong>: Context-aware guidance on what&rsquo;s next</li> <li><strong>Complete lifecycle</strong>: Brainstorming → analysis → architecture → implementation → deployment</li> </ul> <h2 id="modular-ecosystem">Modular Ecosystem<a class="anchor" href="#modular-ecosystem">#</a></h2> <table> <thead> <tr> <th>Module</th> <th>Purpose</th> </tr> </thead> <tbody> <tr> <td>BMM (core)</td> <td>34+ workflows, 12+ agents</td> </tr> <tr> <td>BMad Builder</td> <td>Create custom agents and workflows</td> </tr> <tr> <td>Test Architect (TEA)</td> <td>Risk-based test strategy</td> </tr> <tr> <td>Game Dev Studio</td> <td>Unity, Unreal, Godot workflows</td> </tr> <tr> <td>Creative Intelligence Suite</td> <td>Innovation, brainstorming, design thinking</td> </tr> </tbody> </table> <h2 id="in-the-ecosystem">In the Ecosystem<a class="anchor" href="#in-the-ecosystem">#</a></h2> <p>BMad operates at the <strong>methodology layer</strong> alongside <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/spec-kit/">spec-kit</a>, but with a different philosophy:</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/</guid><description><h1 id="claude-code">Claude Code<a class="anchor" href="#claude-code">#</a></h1> <p>An agentic coding tool by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/anthropic/">anthropic</a> that lives in your terminal, understands your codebase, and helps you code faster through natural language commands.</p> <h2 id="architecture">Architecture<a class="anchor" href="#architecture">#</a></h2> <p>Claude Code is the &ldquo;agentic harness&rdquo; around Claude models. It provides tools, context management, and execution environment that turn a language model into a coding agent.</p> <h3 id="the-agentic-loop">The Agentic Loop<a class="anchor" href="#the-agentic-loop">#</a></h3> <p>Three phases: <strong>gather context → take action → verify results</strong>, chained together with course-correction. Claude decides what each step requires based on what it learned from the previous step.</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/daniel-miessler/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/daniel-miessler/</guid><description><h1 id="daniel-miessler">Daniel Miessler<a class="anchor" href="#daniel-miessler">#</a></h1> <p>Security researcher and AI practitioner. Creator of <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/fabric/">fabric</a> and <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/pai/">pai</a>.</p> <h2 id="relevant-work">Relevant Work<a class="anchor" href="#relevant-work">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/fabric/">fabric</a> — Open-source framework with 251+ curated AI prompt patterns</li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/pai/">pai</a> — Personal AI Infrastructure built on <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a>. Persistent memory, skills, goals, continuous learning.</li> </ul> <p>The two projects are complementary: Fabric = patterns (what to ask AI). PAI = infrastructure (how the AI operates).</p> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/fabric/">fabric</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/pai/">pai</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/fabric/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/fabric/</guid><description><h1 id="fabric">Fabric<a class="anchor" href="#fabric">#</a></h1> <p>An open-source framework (Go, MIT) for augmenting humans using AI. Created by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/daniel-miessler/">daniel-miessler</a>.</p> <p>Mission: &ldquo;human flourishing via AI augmentation&rdquo;</p> <h2 id="core-concept-patterns">Core Concept: Patterns<a class="anchor" href="#core-concept-patterns">#</a></h2> <p>Patterns are curated, well-structured prompts organized by real-world task. 251+ patterns covering:</p> <ul> <li>Content extraction (YouTube, podcasts, articles)</li> <li>Writing (essays, social media, documentation)</li> <li>Analysis (code, claims, debates, incidents, logs)</li> <li>Creation (art prompts, concept maps, changelogs)</li> <li>And many more</li> </ul> <p>Each pattern is a directory with a <code>system.md</code> file. Markdown-based, clear instructions, System section focused.</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/google-cloud-platform/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/google-cloud-platform/</guid><description><h1 id="google-cloud-platform">Google Cloud Platform<a class="anchor" href="#google-cloud-platform">#</a></h1> <p>Cloud computing platform by Google. Relevant to this wiki as the organization behind <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/scion/">scion</a>.</p> <h2 id="related-projects">Related Projects<a class="anchor" href="#related-projects">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/scion/">scion</a> — Multi-agent orchestration testbed (hosted on GCP&rsquo;s GitHub)</li> </ul> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/scion/">scion</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/kiro/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/kiro/</guid><description><h1 id="kiro">Kiro<a class="anchor" href="#kiro">#</a></h1> <p>Kiro is an agentic IDE by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/aws/">aws</a> for software development. It has three main surfaces:</p> <h2 id="kiro-ide">Kiro IDE<a class="anchor" href="#kiro-ide">#</a></h2> <p>Interactive, synchronous collaboration on your local machine. Pair programming, suggestions, real-time code iteration. Spec-driven development.</p> <h2 id="kiro-cli">Kiro CLI<a class="anchor" href="#kiro-cli">#</a></h2> <p>Custom agents as configuration files that customize Kiro&rsquo;s behavior for specific workflows. Define tool access, permissions, and context. Pre-approve tools, reduce interruptions, optimize for specific tasks. Interactive, runs on your local machine.</p> <h2 id="kiro-autonomous-agent">Kiro Autonomous Agent<a class="anchor" href="#kiro-autonomous-agent">#</a></h2> <p>A <a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/frontier-agent/">frontier-agent</a> that works asynchronously in the background on complex, multi-step development tasks. Key capabilities:</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/notebooklm/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/notebooklm/</guid><description><h1 id="notebooklm">NotebookLM<a class="anchor" href="#notebooklm">#</a></h1> <p>A Gemini-powered writing and research tool from Google Labs. Co-founded by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/steven-johnson/">steven-johnson</a>. Designed for AI-assisted knowledge work grounded in user-curated sources.</p> <h2 id="core-design">Core Design<a class="anchor" href="#core-design">#</a></h2> <ul> <li>Users upload sources (documents, articles, notes) — the AI only reasons over those sources, not the open web</li> <li>Two note types: Written Notes (user-authored, editable) and Saved Responses (AI-generated, immutable)</li> <li>Provenance tracking built in: clear separation between human-written and AI-generated content</li> <li>Source-integrated reading with AI actions (summarize, explain, find related ideas)</li> </ul> <h2 id="relationship-to-the-wiki-landscape">Relationship to the Wiki Landscape<a class="anchor" href="#relationship-to-the-wiki-landscape">#</a></h2> <p>NotebookLM occupies a different point in the AI knowledge management space than the tools tracked elsewhere in this wiki:</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/pai/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/pai/</guid><description><h1 id="pai-personal-ai-infrastructure">PAI (Personal AI Infrastructure)<a class="anchor" href="#pai-personal-ai-infrastructure">#</a></h1> <p>An open-source personalized AI platform by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/daniel-miessler/">daniel-miessler</a>, built natively on <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/claude-code/">claude-code</a>. Turns Claude Code from a stateless tool into a persistent assistant that knows your goals, preferences, and history.</p> <p>Mission: &ldquo;AI should magnify everyone — not just the top 1%.&rdquo;</p> <h2 id="three-levels-of-ai">Three Levels of AI<a class="anchor" href="#three-levels-of-ai">#</a></h2> <ol> <li><strong>Chatbots</strong>: Ask → Answer → Forget</li> <li><strong>Agentic Platforms</strong>: Ask → Use tools → Get result</li> <li><strong>PAI</strong>: Observe → Think → Plan → Execute → Verify → <strong>Learn</strong> → Improve</li> </ol> <p>The key differentiator is the <strong>learn</strong> step.</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/paperclip/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/paperclip/</guid><description><h1 id="paperclip">Paperclip<a class="anchor" href="#paperclip">#</a></h1> <p>Open-source orchestration for zero-human companies. Node.js server + React UI. MIT licensed.</p> <p>&ldquo;If OpenClaw is an employee, Paperclip is the company.&rdquo;</p> <h2 id="what-it-does">What It Does<a class="anchor" href="#what-it-does">#</a></h2> <p>Orchestrates teams of AI agents into companies with:</p> <ul> <li><strong>Org charts</strong>: Hierarchies, roles, reporting lines</li> <li><strong>Goal alignment</strong>: Every task traces to company mission</li> <li><strong>Budgets</strong>: Monthly per-agent, atomic enforcement</li> <li><strong>Governance</strong>: Approval gates, rollback, audit logs</li> <li><strong>Heartbeats</strong>: Scheduled agent wake cycles</li> <li><strong>Ticket system</strong>: Every conversation traced, every decision explained</li> <li><strong>Multi-company</strong>: One deployment, many isolated companies</li> </ul> <h2 id="agent-support">Agent Support<a class="anchor" href="#agent-support">#</a></h2> <p>Agent-agnostic: Claude Code, Codex, Cursor, OpenClaw, Bash, HTTP. &ldquo;If it can receive a heartbeat, it&rsquo;s hired.&rdquo;</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/promptfoo/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/promptfoo/</guid><description><h1 id="promptfoo">Promptfoo<a class="anchor" href="#promptfoo">#</a></h1> <p>Open-source CLI for LLM evaluation and red teaming. Now part of OpenAI. MIT licensed.</p> <p>YAML-based test cases, CI/CD integration, model comparison, red teaming. Runs locally — prompts never leave your machine. Powers apps serving 10M+ users.</p> <p>The closest existing tool to a turnkey skill eval pipeline.</p> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/skill-evaluation/">skill-evaluation</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/analyses/how-to-eval-a-skill/">how-to-eval-a-skill</a></li> </ul></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/scion/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/scion/</guid><description><h1 id="scion">Scion<a class="anchor" href="#scion">#</a></h1> <p>Scion is an experimental multi-agent orchestration testbed by <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/google-cloud-platform/">google-cloud-platform</a>. It manages concurrent LLM-based <a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/agent/">agent</a>s running in <strong>container</strong>s across local machines and remote clusters.</p> <h2 id="what-it-is">What It Is<a class="anchor" href="#what-it-is">#</a></h2> <p>A &ldquo;hypervisor for agents&rdquo; — infrastructure for running, isolating, and managing LLM agent processes. It is explicitly <em>not</em> a full multi-agent framework. Components like agent memory, chatrooms, and task management are treated as orthogonal concerns.</p> <h2 id="architecture">Architecture<a class="anchor" href="#architecture">#</a></h2> <p>Scion follows a Manager-Worker pattern:</p> <ul> <li><strong>CLI</strong> (<code>scion</code>): Host-side orchestrator managing agent lifecycle and <a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/grove/">grove</a>s</li> <li><strong>Agents</strong>: Isolated containers running LLM software via <a href="https://blog.imfsoftware.com/llm-wiki/docs/concepts/harness/">harness</a> adapters</li> </ul> <p>Two operating modes:</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/spec-kit/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/spec-kit/</guid><description><h1 id="spec-kit">Spec Kit<a class="anchor" href="#spec-kit">#</a></h1> <p>Open-source toolkit by GitHub for Spec-Driven Development. CLI (<code>specify</code>) + slash commands across 30+ AI agents. MIT licensed.</p> <p>&ldquo;Build high-quality software faster. Focus on product scenarios and predictable outcomes instead of vibe coding.&rdquo;</p> <h2 id="core-workflow">Core Workflow<a class="anchor" href="#core-workflow">#</a></h2> <pre tabindex="0"><code>/speckit.constitution → Establish project principles /speckit.specify → Define requirements (the &#34;what&#34; and &#34;why&#34;) /speckit.clarify → Structured questioning to reduce rework /speckit.plan → Technical implementation plan (the &#34;how&#34;) /speckit.tasks → Actionable task breakdown with dependencies /speckit.implement → Execute all tasks</code></pre><p>Optional: <code>/speckit.analyze</code> (consistency check), <code>/speckit.checklist</code> (quality validation)</p></description></item><item><title/><link>https://blog.imfsoftware.com/llm-wiki/docs/entities/steven-johnson/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://blog.imfsoftware.com/llm-wiki/docs/entities/steven-johnson/</guid><description><h1 id="steven-johnson">Steven Johnson<a class="anchor" href="#steven-johnson">#</a></h1> <p>Editorial Director and Co-Founder of <a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/notebooklm/">notebooklm</a>. Author of 14 books (latest: <em>The Infernal Machine</em>). Writes how-to guides and thought pieces on using NotebookLM for research and writing workflows.</p> <h2 id="role-in-the-wiki">Role in the Wiki<a class="anchor" href="#role-in-the-wiki">#</a></h2> <p>Johnson is the primary voice explaining NotebookLM&rsquo;s design philosophy — particularly the &ldquo;pin → organize → structure&rdquo; workflow and the deliberate separation of human-written vs. AI-generated notes for provenance tracking.</p> <h2 id="see-also">See Also<a class="anchor" href="#see-also">#</a></h2> <ul> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/entities/notebooklm/">notebooklm</a></li> <li><a href="https://blog.imfsoftware.com/llm-wiki/docs/sources/notebooklm-notes-guide/">notebooklm-notes-guide</a></li> </ul></description></item></channel></rss>